40results about How to "Improve detection rate" patented technology

The application discloses a threshold segmentation method for an infrared small target background suppressed image, which realizes threshold segmentation of the infrared small target image after background suppression by calculating the similarity between a Gaussian filter template and an image block, fully utilizes the gray scale features and structural features of the small target, and accurately extracts all the small targets in the image. The application improves the problem that the traditional threshold segmentation method is prone to missing small targets in a multi-target detection task, realizes image segmentation with high detection rate and high real-time rate, provides guarantee for accurate detection of the infrared small target, and has the advantages of simple segmentation process, high efficiency and the like.

The application relates to a wireless communication same-frequency interference detection method based on a CNN-SVM and a particle swarm optimization, which comprises the following steps: performing short-time Fourier transform on a received baseband signal to generate a log power spectrum time-frequency graph; automatically extracting a deep space feature vector through a convolutional neural network; performing global self-adaptive optimization on a penalty parameter and a kernel parameter of a support vector machine through a particle swarm optimization algorithm; and training the support vector machine with optimal parameters to perform binary classification judgment on a to-be-detected feature. Through a triple coordination mechanism, the application overcomes the problems of fixed parameters, poor robustness and the need for a large amount of labeled data in traditional methods, and realizes high detection probability and low false alarm rate under different signal-to-interference-and-noise ratios and bandwidth conditions.

The invention relates to a DPU-based fog cloud collaborative Internet of Things intrusion detection system and method. The system comprises an edge node used for receiving target data sent by Internet of Things equipment, encoding the target data through a pre-trained stacked auto-encoder to obtain a plurality of encoding features, determining a prediction capability index of each encoding feature, and determining a target encoding feature according to each prediction capability index; the cloud server is used for receiving the target coding features sent by the edge node, inputting the target coding features into a pre-trained Internet of Things intrusion identification model, extracting target global features, target local features and target time features associated with the target coding features and Internet of Things intrusion through different branch networks in the Internet of Things intrusion identification model, and sending the extracted target global features, target local features and target time features to the edge node; and outputting an Internet of Things intrusion detection result according to the target global feature, the target local feature and the target time feature. By adopting the system, Internet of Things intrusion detection with low resource occupation, high precision and high efficiency can be realized.

This invention discloses an air conditioning device that determines the initial and equilibrium temperatures of a power module; controls the compressor's operating state to ensure the IGBT output current has a relative zero temperature coefficient; determines the total power module losses at the equilibrium temperature based on the IGBT's relative zero temperature coefficient parameters; acquires the thermal resistance of the inverter driver and refrigerant radiator, and determines the theoretical temperature based on the thermal resistance and total losses; determines the theoretical temperature rise based on the theoretical and initial temperatures, and determines the measured temperature rise based on the equilibrium and initial temperatures; determines the deviation value based on the theoretical and measured temperature rises; acquires the standard deviation value, and compares the deviation value with the standard deviation value to determine whether the refrigerant radiator is qualified. The air conditioning device can intelligently assess the reliability of the refrigerant radiator and its installation.

The application provides a large frequency offset processing method suitable for a multi-user scenario of PUCCH format 1, which comprises the following steps: obtaining user-level PUCCH format 1 frequency domain data, performing zero setting on the first and last subcarriers; performing IFFT on the subcarrier dimension to obtain time domain data from which adjacent user interference is removed; calculating a frequency offset compensation factor according to a historical frequency offset and a sampling rate conversion relationship; multiplying the time domain data and the frequency offset compensation factor to obtain frequency offset compensated time domain data; obtaining frequency offset compensated frequency domain data; taking out PUCCH data and pilot symbols, multiplying the data and the pilot symbols with a data and pilot template to obtain LS channel estimation results; and filling the zero values at the positions of the first and last subcarriers of the LS with the LS channel estimation results of adjacent subcarriers. The method of the application performs zero setting on the first and last subcarriers of the user-level frequency domain data, reduces the interference caused by power leakage of other frequency division adjacent users, and is suitable for a frequency division multi-user large frequency offset communication scenario.

Embodiments of the application disclose a kind of distributed communication signal detection method, device and system based on generalized likelihood ratio, wherein the method is applied to fusion center, comprising the following steps: S1: receiving the observation data transmitted by multiple receiving nodes; S2: under the assumption that radiation source does not exist and radiation source exists, respectively construct the joint conditional probability density function of all observation data of all receiving nodes within the observation time; S3: adopt NP criterion to construct the expression of generalized likelihood ratio test statistic; S4: according to maximum likelihood criterion, estimate the covariance matrix in the joint conditional probability density function under the assumption of two kinds; S5: the estimated value of the covariance matrix under the assumption of two kinds is substituted into the expression of generalized likelihood ratio test statistic, and compared with the decision threshold set according to false alarm probability, to complete distributed communication signal detection. The application can improve the detection probability of communication signal under low signal-to-noise ratio, and has good noise resistance when there is noise fluctuation in different receiving nodes.

The present application relates to the field of radar technology, provide a kind of frequency diversity array multiple-input multiple-output radar target detection system.The system includes detection statistics construction module, detection optimization module, detection threshold determination module and target determination module;Wherein: the detection statistics construction module is used to construct detection statistics;According to the detection statistics, the optimization model of semi-definite programming is constructed;The detection optimization module is used to construct the optimization model of semi-definite programming according to the detection statistics;The detection optimization module is also used to solve the optimization model, obtain the optimal value of detection statistics;The target determination module is used to compare the optimal value of detection statistics with detection threshold, to detect whether target exists, realize the promotion of frequency diversity array multiple-input multiple-output radar target detection probability and anti-interference ability under complex environment.

The utility model discloses a rapid inspection tool for an arc-shaped component of a heavy-duty gas turbine. The rapid inspection tool comprises a test platform, the upper end of the test platform is provided with an arc-shaped combination surface used for bearing the heavy-duty gas turbine ceramic tile, and the arc-shaped combination surface is connected with the back arc-shaped surface of the heavy-duty gas turbine ceramic tile in a matched manner. Guide rail assemblies are arranged on the left and right sides of the test platform. A measuring assembly is arranged on one side of the guide rail assembly. The tool has the beneficial effects that the tool can replace three coordinates to carry out geometric measurement on the ceramic tile, the measurement efficiency is greatly improved, and the production cost is reduced while the detection rate is improved.

The utility model discloses a concrete segment flaw detection device, which relates to the field of concrete segments, and comprises a base, the top of the base is provided with a first support column and a second support column, one side of the first support column is connected with a cross beam, the bottom end of a connecting block is provided with two groups of fixing blocks, one side of each fixing block is connected with a rotating column, and the rotating column is connected with a rotating shaft. A detector is installed at the bottom of the rotating column, and four pulleys are installed at the bottom of the detector. The first supporting column is moved to one side of a segment to-be-detected area, then the handle is rotated, the threaded rod drives the cross beam to descend through the limiting block, and when the pulley makes contact with the outer wall of the segment, the detector can be turned over and adjusted due to different radians of the outer wall of the segment, so that the segment is detected. Four groups of pulleys at the bottom of the detector are all in contact with the outer wall of the duct piece, and the contraction hydraulic cylinder pushes the detector to slide on the outer wall of the duct piece for detection through the moving plate, so that the detection rate of personnel on the duct piece by using the detector is accelerated.

The application discloses a sea surface small target detection method based on multi-domain multi-dimensional feature combination, and adaptively extracts deep features of sea clutter and target echo signals by using a stack sparse auto-encoder, so that the feature dimension is improved to ensure the feature feasibility. Since the feature extraction is a complete adaptive process, the complexity of the model is reduced. Meanwhile, aiming at the problem that the feature distinction degree of the sea clutter and target echo data in a single domain is low, a time-frequency domain feature combination method is provided to improve the feature difference and ensure the stable and efficient detection performance of the detector. Through an adaptive genetic algorithm, the convergence process of the super parameter group optimization is accelerated, and the local optimization of the super parameter is prevented to a certain extent, so that the final detection probability is effectively improved. The experimental results show that the detector provided by the application has better detection effect on high sea state data, the detection probability is improved by 27.6%, and the sea surface small target detection under high sea state can be coped with.

The utility model relates to microswitch detection device technical field, especially for a microswitch detection device, including device main part, device main part one side fixed connection microswitch, front is equipped with controller, the bottom of device main part is equipped with detachable magnetic attraction subassembly, the device main part extends adjustable detection arm, the detection arm end is equipped with contact type detection head and laser ranging sensor utility model discloses through laser ranging sensor real -time monitoring press displacement, combines the contact signal of three -jaw type detection head, only when both satisfy the condition simultaneously judges as effective trigger, the misjudgment rate reduces, three claw floating structure ensures that even detection head and switch surface exist inclination, still can keep stable contact, avoid the misjudgment that single point stress uneven leads.

The present invention provides a novel method which makes it possible to obtain, from a piece of tissue, a sample enriched with cells or cell nuclei of interest. A piece of tissue is subjected to pretreatment comprising water flow disruption and / or ultrasonic disruption to obtain a population of particles including individually separated cells or cell nuclei. A population of particles significantly abundant in cells or cell nuclei of interest is sorted or fractionated on the basis of optical properties of the cell nuclei in the separated cells or of the separated cell nuclei or on the basis of physical properties of the cell nuclei in the separated cells or of the separated cell nuclei.

This invention relates to a target detection method against a sea and sky background, comprising: classifying the visibility of an acquired field-of-view image against a sea and sky background, wherein the visibility levels include poor, moderate, and good; images with poor visibility are classified as difficult samples and not subject to target detection, while images with moderate and good visibility are subject to subsequent target detection; on the sea-sky line in the moderate and good visibility field-of-view images, a target search region is extracted near the sea-sky line to detect targets that are difficult to distinguish with the naked eye and require recording with an optical detector; target edges are extracted in the extracted target search region; after the target edges are extracted, image segmentation is performed according to the target edges to obtain the target image. This invention improves the detection probability by classifying the visibility of the sea and sky background, performing target detection on images with moderate and good visibility, and performing subsequent target detection on images with moderate and good visibility.

The application provides a general adversarial attack detection method based on token loss information. The target sample is segmented into independent sequence tokens, and then loss weight information of each token sequence is calculated and converted into a TLV (Token-Loss Value, TLV) metric value, and a full sample sequence query table T is established. A difference detector threshold is set to judge the adversarial sample, effectively solving the disturbance detection of the learnable non-instance adversarial sample, and high performance can be achieved on long and short texts, and the optimal detection result is achieved in the current task.

The application discloses a detachable and replaceable stator core laminating mould structure and relates to the technical field of motors. The stator core laminating mould structure comprises a laminating tool lower bottom plate, a plurality of internal support rings are arranged at the middle position of the laminating tool lower bottom plate, a plurality of support ring equal-height columns are arranged between every two internal support rings for connection, the outer ring surface of the internal support ring is provided with thirty-two planes, a group of pin holes and a group of threaded holes are arranged on each plane, and the pin holes are arranged above the threaded holes. The structure in the laminating tool can be conveniently and quickly assembled, the laminating height can be adjusted according to actual requirements, the practicability of the laminating tool is greatly improved, every part in the laminating tool can be separately disassembled, the structure maintenance of the laminating tool can be conveniently and quickly completed by the staff, the universality of the laminating tool is improved, and the service life of the laminating mould structure is further improved.

The application provides a three-feature sea surface target detection method based on smoothing filtering, and the implementation steps are as follows: initializing parameters; dividing each group of sea clutter data; performing smoothing filtering on each group of sea clutter data; extracting three-dimensional features of each data block in which the clutter is suppressed; and obtaining a target detection result under the sea clutter background. The application reconstructs each data block by using part of data of the adjacent data block of each distance unit, the reconstructed data block contains part of historical data and future data of the adjacent data block, the smoothing filter with the coefficient a is used to perform smoothing filtering on each data block by calculating the coefficient of the smoothing filter with the coefficient a from all the reconstructed data blocks, the ability to suppress the clutter in the data block is improved, the signal-to-clutter ratio of the target echo is improved, the defect that the existing technology is difficult to separate the small radar cross section (RCS) maneuvering target from the clutter is avoided, and the detection probability is effectively improved.

The invention discloses a magnesia carbon brick online quality inspection method and system based on knocking detection, and relates to the field of acoustic detection, a reciprocating swing knocking mechanism driven by a stepping motor is adopted to carry out fixed-point knocking on the surface of a magnesia carbon brick according to a preset interval, and multichannel knocking sound wave signals are synchronously collected through a pickup array; time domain, frequency domain and time-frequency domain features are extracted from the preprocessed sound wave signals, and a fusion feature vector is constructed after normalization processing; and inputting the fusion feature vector into an attention mechanism enhanced extreme learning machine model, and outputting the defect type and confidence of the magnesia carbon brick. According to the invention, visual identification and self-adaptive regulation and control technologies are combined, real-time detection can be completed without stripping a production process, the detection rate is greatly improved, and continuous operation requirements of an automatic production line are met. Characteristic parameters of magnesia carbon brick materials are deeply fused into the whole process of detection parameter regulation and control, signal processing and model construction, and accurate recognition and grading of different types of defects are achieved by means of an intelligent model with an attention mechanism enhanced.

A method and apparatus for detecting objects, particularly distant objects within a field of view (FOV), using light pulses with non-uniform pulse power without exceeding the Accessible Emitted Limit (AEL) is provided. Multiple light pulses comprising two or more pulse power levels can be emitted to detect objects within the FOV. Information related to the objects can be generated from the returned light pulses. The light pulses with non-uniform pulse power can improve the probability of detection of pulses returned from the distant objects, thus increasing the point cloud density of distant objects.

The present application relates to the technical field of anti-scaling detection, in particular to a kind of enamel steel plate anti-scaling detection device and detection method, including hydrogen permeation cell, hydrogen permeation cell includes left electrolytic cell and right electrolytic cell, and the left electrolytic cell and right electrolytic cell are all opened with permeation mouth, the left electrolytic cell and right electrolytic cell are all fixedly connected with clamp, sealing ring one is arranged on the clamp, and two clamps are used to clamp steel plate, the detection assembly is set on hydrogen permeation cell device in the present application, when two clamps are clamped steel plate, fill water in detection cell, at this time, pressure is applied to two sides of piston respectively, if sealing ring one is not sealed with steel plate at this time, bubble will be generated at sealing place, whether bubble is generated is observed to judge the sealing effect of the sealing ring one on both sides of steel plate, reduce the detection time, and other solutions do not need to be added to the left electrolytic cell and right electrolytic cell, thereby avoiding the cleaning step before subsequent test, facilitate the operation step, improve the detection rate of sealing property.

The invention relates to the technical field of nondestructive testing, and provides an electric power fitting crack nondestructive testing method based on bimodal and related equipment. Scanning the electric power fitting through an ultrasonic module to obtain an ultrasonic signal, and obtaining an infrared signal of the electric power fitting through an infrared module; performing space-time alignment and integration based on deviation parameters between the ultrasonic signals and the infrared signals to generate a bimodal data cube; the data cube is decoupled through a convolution solution network obtained through pre-training, and an ultrasonic characteristic spectrum and an infrared characteristic spectrum are generated; performing crack probability prediction based on topological characteristics of the characteristic spectrum, and generating a crack probability heat map and a topological structure map; and performing multi-scale verification on the crack probability heat map and the topological structure diagram to generate crack parameters. Crack parameters can be accurately obtained by integrating the internal structure and surface temperature information, crack prediction and multi-scale verification, and the accuracy and reliability of crack detection are effectively improved.

A defect detection method and a defect detection apparatus are provided. The defect detection apparatus is used to detect a sample including a periodic structure. The defect detection apparatus includes a light source, an image detector and a controller. The light source is used to provide a light beam incident on the periodic structure, wherein the periodic structure converts the light beam into an interference light beam. The image detector is disposed in a path of the interference light beam, wherein the interference light beam forms an interference intensity distribution on the image detector. The controller is electrically connected to the image detector, and is used to determine whether the periodic structure has a defect by determining whether the interference intensity distribution has a normal waveform.

The utility model discloses a vacuum cup leak hunting device suitable for a multi-station production line, which comprises a rack, a detection module is arranged on the top of the rack, the detection module comprises a base, a mounting plate, a first sealing unit and a positioning unit, the base is also provided with a negative pressure channel, and the inner wall of the positioning unit forms a positioning part. When the vacuum cup is installed in the positioning part, the outer wall of the vacuum cup abuts against the positioning part, the negative pressure channel is communicated with an inner cavity of the vacuum cup, and a cup opening of the vacuum cup abuts against the first sealing unit in a sealed mode. The input end of the vacuum assembly is connected with an external air source, and the output end of the vacuum assembly is communicated with the negative pressure channel. According to the utility model, a plurality of detection modules are provided, so that the leak detection equipment is adaptive to a multi-station production line; and the detection module comprises a positioning unit and a first sealing unit, so that the vacuum cup is automatically adsorbed on the first sealing unit through negative pressure in the retesting process, the action flow during testing is simplified, and the detection rate is improved.

This invention discloses a method and apparatus for frame signal detection and synchronization based on a BPLC system. The method involves: determining a first CIR peak value based on at least two sets of first time-domain data; determining a CIR peak-to-average power ratio (PAPR) based on the first CIR peak value; determining the last set of first time-domain data in the at least two sets of first time-domain data as an OFDM symbol of SYNCP, and determining the position index of the first CIR peak value in the OFDM symbol of SYNCP; adjusting the timing point to the beginning position of the OFDM symbol of the preamble signal based on the position index of the first CIR peak value; receiving at least four sets of second time-domain data, and determining at least three second CIR peak values ​​based on the at least four sets of second time-domain data; and determining the last set of second time-domain data as the second OFDM symbol of SYNCP in response to the latest three second CIR peak values ​​conforming to a V-shaped characteristic and satisfying a set polarity characteristic. This method improves the probability of frame signal detection and frame signal synchronization performance while reducing computational load.

The invention relates to a display equipment electromagnetic leakage signal detection method, which belongs to the technical field of electromagnetic detection, and specifically comprises the following steps: firstly, acquiring a space electromagnetic signal through broadband receiving equipment, and preprocessing to obtain a baseband complex signal; by improving a multiple autocorrelation algorithm, initial detection of leakage signals and extraction of core parameters such as a pixel clock and line-field synchronization can be completed without prior parameters; then constructing a confidence discrimination matrix based on pixel amplitude and phase time sequence characteristics, and accurately distinguishing effective leakage signals from various interferences; and then weak signal enhancement is realized through self-adaptive threshold feature preferential selection and confidence coefficient weighted multi-frame coherent accumulation, and finally detection result output is completed, so that the problems that weak leakage signals are submerged by noise and the detection probability is low in a long-distance and high-interference scene can be effectively solved.

A device, method, and computer equipment for detecting internal and external microcracks in blades are disclosed. The device includes a projector stabilization mechanism; an infrared camera mechanism, a first industrial camera mechanism, and a second industrial camera mechanism, arranged circumferentially and connected to the projector stabilization mechanism for adjusting camera yaw and rotational degrees of freedom; and a connecting component for connecting the projector stabilization mechanism and a robotic arm. The method includes: adjusting the detection positions of the projector, infrared camera, and industrial cameras; developing a segmented image information acquisition scheme based on the non-destructive blade at the detection position; capturing infrared thermal images, visible light images, and 3D point cloud images of the blade to be detected using the set acquisition scheme to obtain a 3D information dataset for a single blade; and inputting the information dataset into a microcrack detection model to detect and distinguish internal and external microcracks in the blade to be detected. This invention features a compact structure, high detection efficiency, and reduced false detection rate.

This application relates to a sample introduction module and a single-molecule immunoassay analyzer including the same. The sample introduction module comprises 2 to 4 sample racks, each arranged parallel to each other in the vertical direction and having the same structure. Each sample rack includes a microplate, a stage, and a linear reciprocating motion mechanism. The linear reciprocating motion mechanism includes a linear guide rail, a drive mechanism, a drawer slide rail, a synchronous belt, a drive wheel, a driven wheel, and a zero-position sensor. The single-molecule immunoassay analyzer includes a sample introduction module, a detection module, an incubation module, and a reagent processing module. The sample introduction module of this application can effectively reduce the size of the module while ensuring sample storage capacity. The single-molecule immunoassay analyzer of this application has a high degree of automation, a compact structure, low operation difficulty, and improved detection efficiency, reaching over 90 tests / hour.

The utility model discloses a novel displacement imaging mechanism of side-mounted short cantilever belongs to machine vision detection technical field, including camera, lens, actuator, light source, V type fixed block and mounting plate, the camera with the lens passes through transition sheet and is installed on the actuator, and with the actuator realizes up and down movement, the actuator is motor, screw, guide rail slider integrated packaging structure, and the mounting direction of actuator is perpendicular with the mounting plate and is in vertical layout, the V type fixed block is locked on the mounting plate of actuator, and the linear contact is formed with the cylindrical surface of lens through V type surface to fix lens end, the light source is set up on the lower plate, and provides illumination for imaging. Solve the problem such as long cantilever, poor imaging stability, limited application scene in the prior art.

The invention discloses a Wi-Fi packet detection method based on a phase. The method comprises the following steps: receiving a complex baseband signal; carrying out RSSI calculation through components in the complex baseband signal and obtaining a signal strength indication; when the signal strength indication is greater than a preset threshold value, weak interference environment detection is carried out; and when the signal strength indication is smaller than or equal to a preset threshold value, carrying out strong interference environment detection. Phase difference detection is matched with amplitude weighting to replace traditional phase detection, IIR exponential smoothing is adopted to solve the problems of large fluctuation of detection statistics and noise sensitivity, and by providing multiple optimized packet detection modes and establishing a mode selection strategy, the system can configure an optimal detection algorithm according to different application scenes and channel conditions.

The invention relates to the technical field of wireless communication, in particular to a DMF (Dimethyl Formamide)-based peak-to-average ratio tracking adaptive threshold detection method and device and a medium, and the method comprises the following steps: transmitting a data frame containing two sections of same synchronization sequences, and carrying out correlation operation at a receiving end by using a digital matched filter; an absolute threshold capable of being dynamically updated is set for preliminary screening, and correlation values exceeding the threshold are continuously stored; calculating peak-to-average ratios of correlation values in the window, and if continuous peak-to-average ratios are greater than a relative threshold, judging that an effective peak value is captured and updating an absolute threshold; synchronous capturing is completed through tracking detection and double-peak position verification. According to the method, the threshold self-adaptive adjustment under the resource limited condition is realized, and the detection probability and the system stability under the low signal-to-noise ratio environment are remarkably improved.

This invention relates to the field of low-altitude security and discloses an intelligent identification and counter-jamming system for low-altitude aircraft. The system includes a radar detection module, a radio detection module, a data fusion module, a data processing module, and an early warning and countermeasure module. Through coordinated radar and radio detection, it acquires the micro-motion, trajectory, and signal fingerprint features of the target. Then, using a pre-trained UAV identification model, it performs in-depth analysis and time-series verification on the fused multi-dimensional features to achieve high-confidence UAV identification, model identification, and threat level assessment. Finally, based on a dynamically calculated comprehensive threat index, it initiates a countermeasure process including dynamic review and effect evaluation, capable of adaptively selecting and switching countermeasures to achieve precise, layered, and effective handling of suspicious UAVs. This invention solves the problems of low identification accuracy, high false alarm rate, and rigid and singular countermeasures in existing technologies, thus improving the effectiveness of low-altitude security.