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

573results about How to "Improve detection reliability" patented technology

Method and system for automatically detecting defects of semiconductor chip based on hyperspectral imaging

The invention provides a semiconductor chip defect automatic detection method and system based on hyperspectral imaging, and relates to the technical field of chip detection, and the method comprises the steps: collecting a chip hyperspectral image, carrying out the image enhancement and illumination non-uniformity correction through an improved neuromorphic adaptive processing network and a dual-path diffusion model, and carrying out the detection of the hyperspectral image. Extracting multi-level features by using a dynamic mixed feature enhancement network based on neural architecture search, fusing the features through a cross-layer attention mechanism, generating an initial defect detection result by using a multi-branch expert decision-making module and an uncertainty dynamic integration strategy, constructing a space-time knowledge inference graph, and determining a defect detection result; and performing reliability evaluation and optimization on the initial defect detection result in combination with the form similarity, the spatial position relationship and the process parameter influence model to obtain a final defect detection result.
Owner:BEIJING KEYANG TECH CO LTD

Power distribution network traveling wave head fault calibration method, device, equipment and medium

The invention provides a power distribution network traveling wave head fault calibration method. The method comprises the steps that initial fault voltage traveling waves of all measurement points in a power distribution network are collected; constructing a first phase-mode transformation matrix to perform phase-mode transformation on the initial fault voltage traveling wave, and selecting a fault voltage line-mode component of the initial fault voltage traveling wave; performing first characteristic mode decomposition on the fault voltage line mode component to obtain a square envelope spectrum Gini coefficient of the fault voltage line mode component; determining an optimal parameter combination corresponding to the Gini coefficient of the square envelope spectrum, performing second characteristic mode decomposition on the optimal parameter combination, calculating a kurtosis value of each initial fault traveling wave signal, and determining a wave head calibration mode component of the fault traveling wave signal; and carrying out differential operation on the wave head calibration mode component, introducing a differential energy operator, and determining the traveling wave head arrival time of the fault traveling wave signal. According to the technical scheme of the embodiment, the detection precision and reliability of the fault traveling wave head can be effectively improved, and the accuracy of power distribution network fault positioning is enhanced.
Owner:ZHUHAI XJ ELECTRIC

Imaging method and system based on cosmic ray muon transmission

The invention discloses an imaging method and system based on cosmic ray muon transmission, which are applied to a control mechanism, and the control mechanism is electrically connected with at least one detection module. The imaging method based on cosmic ray muon transmission comprises the steps that the response state of at least one detection module is obtained, the detection module comprises a plurality of sensor units, and the sensor units are arranged in a string shape. And preprocessing the response state to obtain muon flux in unit area, unit time and unit solid angle. Based on the topographic data, the landform data and the muon flux, the density distribution in the muon ray irradiation range is reversely deduced through a preset algorithm. And performing visual imaging based on a density distribution result. According to the method, the working efficiency of muon geological imaging is improved, the system complexity is reduced, the adaptability in a narrow working environment is remarkably enhanced, and an efficient and convenient solution is provided for the fields of geological exploration, engineering detection and the like.
Owner:SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Intelligent detection system and method for consumer electronic functional device

The invention relates to the technical field of electronic product detection, in particular to an intelligent detection system and method for consumer electronic functional devices, and the system comprises a signal collection module, an interference recognition module, a signal processing module, a data analysis module, an anomaly detection module, a self-adaptive learning module and a central control unit. Wherein the signal acquisition module is used for acquiring an original electric signal; the interference identification module is used for identifying and isolating electromagnetic interference and radio frequency interference components in the signals; the signal processing module is used for extracting and recovering the interfered original signal; the data analysis module is used for determining the function state of the product; the abnormity detection module is used for judging whether the function state of the product is abnormal; and the self-adaptive learning module is used for automatically adjusting signal processing parameters and analysis algorithms. According to the invention, through continuous data collection and analysis, the accuracy of fault diagnosis is improved, the accidental downtime can be reduced through predictive maintenance, and greater value is provided for consumer electronics manufacturers and users.
Owner:SKYCONN TECH (JIANGSU) CO LTD

Fabric polyester fiber detection method based on spectral imaging and curve fitting

The invention discloses a textile fabric polyester fiber detection method based on spectral imaging and curve fitting, and relates to the technical field of hyperspectral imaging analysis, and the method comprises the steps: carrying out the characteristic decomposition and principal component analysis of a reflectivity function after baseline correction, and obtaining a characteristic curve; extracting feature information of the hyperspectral image, and fusing the feature information of the hyperspectral image with the feature curve to generate a multi-dimensional feature vector; and constructing a hyperspectral fiber content detection model, inputting the multi-dimensional feature vector and the feature parameter vector into the hyperspectral fiber content detection model, and generating the polyester fiber content. Not only are the problems of background noise and drift interference solved, but also the multi-dimensional characteristics of the hyperspectral data are fully mined. The content of the polyester fibers in the waste textile fabrics can be efficiently detected on line. Finally, according to the method, the detection precision and reliability are remarkably improved, and an efficient, environment-friendly and accurate technical means is provided for resource utilization of the waste textile fabrics.
Owner:ZHEJIANG UNIV +1

Atmospheric pollutant sensor data calibration method suitable for being deployed at embedded terminal

The invention relates to a data calibration method suitable for an atmospheric pollutant sensor deployed in an embedded terminal. The method comprises the following steps: acquiring original response data of different sensors with different concentrations in different atmospheric environments after temperature compensation, and corresponding temperature, humidity, air pressure data and sampling time; collecting real concentration values of detection objects corresponding to different sensors at corresponding moments given by a national control station or a provincial control station; preprocessing the obtained data to obtain a final data set; a random forest algorithm is used as a teacher model, a gradient elevator algorithm is used as a student model, and hyper-parameters of the gradient elevator algorithm and the random forest algorithm are optimized by using a hedera helix algorithm; substituting a hyper-parameter optimal solution found by optimization into a corresponding algorithm, and retraining the teacher model and the student model by using hyper-parameter combinations; and deploying, updating and displaying the model in the embedded equipment. And the model size is reduced to realize the deployment of the embedded end on the premise of ensuring the accuracy.
Owner:HEBEI UNIV OF TECH +1

Gait analysis system and gait analysis method

ActiveCN118975793AEliminate the problem of inaccurate gait analysisReduce error interferenceSensorsDiagnostic recording/measuringMedicineGait analysis
The invention discloses a gait analysis system and a gait analysis method.The gait analysis system comprises a plurality of inertial measurement modules, a plurality of pressure measurement modules, a depth camera, an optical motion capture module, a data filtering module and a main control module, through cooperation of the multiple modules, various types of data capable of reflecting gait characteristics are collected, and the gait analysis result is obtained. All the data can compensate mutually and reflect gait features of the user cooperatively, finally, a gait analysis result of the user is obtained through the main control module, and comprehensive analysis of the gait features such as the step length, the stride width, the stride frequency, the gait rhythm, the gait periodicity, the gait stability and the gait coordination of the user is achieved. According to the gait analysis system, the problem that gait analysis is inaccurate due to the fact that the amount of information collected by a single sensor is small can be solved, error interference of external environment influences on gait analysis is reduced, the detection precision and reliability are improved, and accurate and comprehensive analysis of the gait of the user is achieved.
Owner:SOUTH CHINA UNIV OF TECH

Adaptive CFAR detection method based on scene classification

The invention provides an adaptive CFAR detection method based on scene classification, and the method comprises the steps: carrying out the scene classification of an input SAR image through employing a K-means clustering algorithm, carrying out the target detection of a pure sea area obtained through classification through employing VI-CFAR, and carrying out the CFAR detection of a coastal area through employing a significance model. According to the method, the problems that a traditional CFAR algorithm is high in false alarm rate and unstable in detection performance in port and land complex backgrounds are effectively solved, detection parameters are optimized according to the complexity of different scene backgrounds, and therefore it is ensured that the CFAR algorithm can still maintain the constant false alarm rate in the sea clutter background, and the robustness of target detection is remarkably improved. The ocean area and the land area in the image are effectively distinguished, and the land area is shielded. According to the technical scheme, the problem that a traditional CFAR detection algorithm is interfered by a complex land background when detecting ships on the sea surface is solved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Power equipment detection method and system

The invention discloses a power equipment detection method and system, and relates to the technical field of power equipment detection, and the method comprises the steps: inputting a power equipment image into a trained enhanced target detection model; the trained enhanced target detection model comprises a backbone network, a neck network and a head network; performing multi-level feature extraction enhancement on the power equipment image through the backbone network to generate a low-level feature, a middle-level feature and a high-level feature; inputting the low-layer features, the middle-layer features and the high-layer features into a neck network for feature pyramid fusion, and outputting a plurality of fusion features; and respectively detecting each fusion feature by using a head network, adding elements one by one, and determining a detection result of the power equipment. The electrical equipment image is detected through the enhanced target detection model with an improved structure, so that the feature extraction capability is enhanced, the interaction of multi-scale information is realized, the accuracy and robustness of target detection are improved, and the detection reliability of the electrical equipment is improved.
Owner:GUANGDONG UNIV OF TECH

Method and device for detecting and positioning surface defects of PCB (Printed Circuit Board)

The invention discloses a method and a device for detecting and positioning surface defects of a PCB (Printed Circuit Board). The method comprises the following steps: acquiring a reference image and a sample image of the PCB; processing the light and shade distribution of the sample image to obtain a sample image with uniform illumination; correcting a pixel difference between the sample image and the reference image to enable the reference image and the sample image to achieve pixel-level alignment; carrying out defect detection index calculation on the reference image and the sample image according to regions, and detecting and positioning defects. According to the method, the detection accuracy and efficiency are improved, the hardware cost and the calculation overhead are reduced, and deployment and implementation in the actual production and manufacturing process are easy; meanwhile, due to the high automation attribute, the detection reliability and the flexible adjustment capability, the method has wide application prospects and practical value.
Owner:NO 24 RES INST OF CETC

Photovoltaic cell hot spot intelligent detection method fusing multi-modal data

The invention discloses a photovoltaic cell hot spot intelligent detection method fusing multi-modal data. The method comprises the following steps: S1, collecting multi-modal data of a photovoltaic cell; s2, carrying out preprocessing on the multi-modal data; s3, constructing a photovoltaic cell sample data set; s4, extracting features of the multi-modal data; s5, fusing the multi-modal features to generate a comprehensive feature vector; s6, training and optimizing a dynamic hot spot detection model based on the space-time convolutional network; s7, identifying a hot spot area in the photovoltaic cell by using the model; s8, positioning and outputting a hot spot detection result; and S9, optimizing the detection model in real time in combination with a dynamic adaptive algorithm. According to the method, the multi-modal data fusion, the space-time convolutional network and the dynamic adaptive optimization algorithm are introduced, so that the hot spots in the photovoltaic cell can be detected and positioned more accurately and quickly, the false detection rate in a complex environment is effectively reduced, and the operation efficiency and reliability of a photovoltaic cell system are remarkably improved.
Owner:XUZHOU YAORI ENERGY RESEARCH CO LTD

Construction project engineering management audit doubtful point extraction method based on three-dimensional point cloud

The invention relates to the field of engineering auditing, in particular to a construction project engineering management auditing doubtful point extraction method based on three-dimensional point clouds, which comprises the following steps: step 1, constructing and forming an auditing data resource pool based on a BIM model as a main body; 2, placing the two types of non-homologous data in the same coordinate system; 3, associating geometric data of the BIM model with project management information; 4, pre-training the laser point cloud semantic segmentation model, and accurately identifying key components in the actually measured point cloud in the auditing stage; and step 5, processing the point cloud data, identifying key engineering components, performing geographic space matching and fusion on identification results and BIM model component point cloud, calculating and comparing geometric feature differences of the key components, and completing doubtful point detection. By introducing an advanced three-dimensional point cloud and machine learning technology, an efficient, accurate and intelligent construction project engineering management auditing doubtful point extraction method is provided, and powerful technical support is provided for engineering management and auditing work.
Owner:QINGDAO INST OF SURVEYING & MAPPING SURVEY +1

Pipeline inner wall defect visualization system based on polarized light

The invention relates to the technical field of defect visualization, in particular to a pipeline inner wall defect visualization system based on polarized light, which comprises an instruction for executing a control algorithm, realizing movement and advancing of a pipeline robot in a pipeline, judging the posture direction of the robot, and acquiring the movement speed of a motor. The shape of the pipeline is automatically adjusted according to the diameter and shape changes of the pipeline, real-time communication, detection data transmission and control instruction receiving are conducted through a communication system and a pipeline robot and an operator, image data are analyzed through an image processing algorithm, and defects and problems of the inner wall of the pipeline are determined. And a plurality of images are synthesized into a complete pipeline inner wall image, so that a more comprehensive and clearer detection result is provided. According to the invention, the precision and flexibility of the motion control module are obviously improved, the robot can realize accurate forward, backward and turning operations in a complex pipeline, and the posture, position and speed data of the robot are collected and processed in real time, so that the detection precision and reliability of the robot in a complex environment are greatly improved.
Owner:TANGSHAN DATU TECHNOLOGY CO LTD

Surface cleaning identification method for titanium alloy bar rolling

A surface cleaning identification method for titanium alloy bar rolling relates to the technical field of image identification, and comprises the following steps: graying a global image of the surface of a titanium alloy bar to generate a grayscale image, and carrying out texture feature analysis on the grayscale image to obtain a global noise index of the grayscale image; based on the global noise index, obtaining a noise difference coefficient in a neighborhood range of each pixel point, and performing adaptive filtering on the grayscale image according to the noise difference coefficient to obtain a denoised grayscale image; performing gray change coefficient analysis on the denoised gray image, dividing the gray image into an abnormal sliding window or a normal sliding window, and performing local feature merging and erosion operation on each abnormal sliding window in the denoised gray image; and obtaining the stain type corresponding to the abnormal sliding window which completes local feature combination and erosion operation. According to the method, the efficiency and the accuracy of surface cleaning identification of titanium alloy bar rolling are remarkably improved.
Owner:TIPRO INT CO LTD

Pipeline ultrasonic guided wave detection system

The invention relates to a pipeline ultrasonic guided wave detection system which comprises a plurality of detection units distributed in the circumferential direction of a pipeline, a tightening assembly is hinged between the head detection unit and the tail detection unit, a connecting assembly is hinged between the other adjacent detection units, each detection unit comprises a frame and a probe detachably fixed in the frame, and two supports are arranged on the two sides of the frame respectively. A guide rod is arranged in the support, a roller is mounted on the guide rod through a wheel carrier, a first spring is arranged between the wheel carrier and the support, the probe comprises a shell, and a bottom-layer insulating spacer, an annular permanent magnet, an upper-layer insulating spacer and a disc-shaped electromagnetic coil which are fixed in the shell, a rectangular hole is formed in the bottom wall of the shell, and strip-shaped stop blocks are arranged on the two sides of the rectangular hole respectively; the bottom insulation spacer is connected with a coupling patch through a flexible deformable body, the disc-shaped electromagnetic coil is connected with an industrial interface extending out of the shell, the flexible deformable body is made of silica gel, and the coupling patch is made of ferrocobalt. The device has the advantages of being simple in structure, convenient to operate and control, high in reliability and good in adaptability.
Owner:BEIJING GAS GRP

Unmanned aerial vehicle insulator inspection system based on multi-light fusion and method thereof

The invention belongs to the technical field of unmanned aerial vehicle inspection, and particularly relates to an unmanned aerial vehicle insulator inspection system and method based on multi-light fusion. Comprising an unmanned aerial vehicle platform and a ground control station. The unmanned aerial vehicle platform is used for carrying inspection equipment and inspecting the insulator according to a preset path; comprising an unmanned aerial vehicle body, a multi-light fusion sensor module, a data processing module, a control module and a communication module, the multi-light fusion sensor module integrates a visible light sensor, an infrared sensor and an ultraviolet sensor and is used for acquiring visible light image information, infrared thermal image information and ultraviolet image information of the insulator, potential faults can be found in the early stage through the three-light fusion technology, and important data support is provided for preventive maintenance; through integration of data of different wavelengths, insulator fault diagnosis under the three-light fusion technology reduces the possibility of misjudgment of insulator faults, and high detection reliability and high efficiency can be maintained under various environmental conditions.
Owner:HAIBEI POWER SUPPLY COMPANY STATE GRID QINGHAI ELECTRIC POWER +1

Visual inspection system for saw blade tooth profile defects based on deep learning model

The invention discloses a saw blade tooth profile defect visual inspection system based on a deep learning model, and relates to the technical field of saw blade tooth profile defect detection.The saw blade tooth profile defect visual inspection system comprises a light source capable of providing a plurality of different specific wavelengths, and a first visual inspection device shoots a saw blade and generates a digital image; pixel information in the scanning image is subjected to edge detection, texture analysis and morphological operation, and then corresponding characteristic values are extracted; and the second visual detection device is used for receiving the light of different specific wavelengths reflected from the surface of the saw blade in a certain length range, and analyzing and generating reflection spectrum data. The method comprises the following steps: comparing a feature value extracted by a first visual detection device with a set threshold range to preliminarily identify an obvious tooth profile defect area, and taking a comparison result of the feature value and the set threshold as a starting condition for carrying out second accurate detection or not; and the secondary visual detection device performs more accurate detection on the area with the preliminarily detected potential defects, and deep defect features are identified.
Owner:MEIZHOU BAY VOCATIONAL & TECH COLLEGE

Insulating part defect identification method based on synthetic aperture ultrasonic imaging technology

The invention provides an insulating part defect identification method based on a synthetic aperture ultrasonic imaging technology, which belongs to the technical field of ultrasonic defect identification, and comprises the following steps: step 01, setting parameters of an ultrasonic transducer to enable the ultrasonic transducer to emit ultrasonic waves, and attaching the ultrasonic transducer to the surface of a detected insulating part; 02, connecting the ultrasonic sensor with an acquisition card, and acquiring real-time echo data by using acquisition software; step 03, importing the data into data processing software for data processing, and performing defect imaging by applying an imaging algorithm; and step 04, performing defect analysis and positioning on the formed ultrasonic image. According to the method, the accuracy, reliability and practicability of defect detection of the insulating part are remarkably improved, and more effective technical support is provided for quality control in the industrial field. Due to the automatic and intelligent characteristics of the system, the detection efficiency is greatly improved, the uncertainty caused by human factors is reduced, and the system has remarkable practical value and popularization significance.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID NINGXIA ELECTRIC POWER COMPANY +2

Food pesticide residue safety detection and analysis method based on machine learning

The invention relates to the technical field of food detection, and discloses a food pesticide residue safety detection analysis method based on machine learning, which comprises the steps of food sample collection, extract pretreatment, two-dimensional liquid chromatography-high resolution mass spectrometry combined technology analysis, mass spectrum acquisition, mass spectrum numerical data conversion, data correction and machine learning model establishment. The method comprises the following steps: identifying and classifying pesticide residue components, extracting a pretreatment extract, analyzing a to-be-detected sample, acquiring a mass spectrum, converting the mass spectrum into to-be-detected mass spectrum numerical data, correcting the data, inputting a model, identifying and classifying pesticide residues, quantitatively analyzing, comparing food safety standards, judging conformity and generating a detection report. The invention aims to improve the accuracy, sensitivity and efficiency of pesticide residue detection. Meanwhile, through technical correction and optimization, the problems of environmental interference, data deviation and the like faced by an existing method are effectively solved.
Owner:HEZE INST OF FOOD & DRUG INSPECTION & TESTING

Method and device for detecting short circuit of solid-state battery

The invention belongs to the field of battery manufacturing and detection, and discloses a detection method and device for solid-state battery short circuit, and the method comprises the steps: setting the ranges of a first current and a second current; testing the charge-discharge performance of the solid-state battery by using the first current and the second current in sequence; setting a numerical range of a time interval of data sampling, and sampling the voltage of the solid-state battery at equal time intervals in the process of testing the charge-discharge performance of the solid-state battery; calculating charge and discharge characteristic parameters of the solid-state battery according to a voltage sampling result, and drawing a curve of the voltage of the solid-state battery along with time change; obtaining a charge-discharge characteristic parameter qualified threshold value of the solid-state battery, and judging whether the charge-discharge characteristic parameter of the to-be-detected solid-state battery is within the range of the charge-discharge characteristic parameter qualified threshold value of the solid-state battery; if yes, judging that the to-be-detected solid-state battery is normal, and if not, judging that the to-be-detected solid-state battery is short-circuited. The method does not depend on specific temperature condition testing.
Owner:QINGDAO RUIJIE INTELLIGENT INSTR

Pole piece thickness detection device

The invention relates to the technical field of powder forming intelligent detection, and provides a pole piece thickness detection device which comprises a large bottom plate, a pole piece turnover mechanism, a positioning mechanism, a thickness measuring mechanism and a turnover waiting structure. A positioning mechanism, a thickness measuring mechanism and a turnover material waiting structure are sequentially and fixedly connected to the upper surface of the large bottom plate in the length direction, and the thickness measuring mechanism is located between the positioning mechanism and the turnover material waiting structure; the pole piece turnover mechanism is arranged on the right front portion of the turnover waiting structure and fixedly connected to the upper surface of the large bottom plate. Thickness detection is automatically carried out on multi-point positions in the circumferential and diameter directions of the pole piece by adopting the correlation laser displacement sensor; and meanwhile, the mechanism automatically performs dust removal treatment on the test bench, so that the detection efficiency, the detection precision and the detection result reliability can be effectively improved.
Owner:贵州轻工职业大学

Alignment compensation method and system for edge microcrack detection, medium and product

The invention discloses an alignment compensation method and system for edge microcrack detection, a medium and a product, and relates to the technical field of data processing. The method comprises the following steps: sending a first shooting instruction to a position camera to obtain an initial position image of a display panel; determining a movement compensation amount according to the initial position image and a standard detection position of the panel detection platform; the movement compensation amount is sent to a transfer mechanism, so that the transfer mechanism transfers the display panel from the panel bearing platform to a panel detection platform; sending a second shooting instruction to an alignment camera to obtain an alignment detection image of the display panel; judging whether the display panel is aligned with the standard detection position or not according to the alignment detection image and the standard detection position; if not, an alignment adjustment instruction is sent to the transfer mechanism, so that the transfer mechanism adjusts the display panel to be aligned with the standard detection position. According to the invention, the accuracy and efficiency of alignment are improved, and the accuracy and efficiency of display panel edge microcrack detection are improved.
Owner:BEIJING C&W ELECTRONICS GRP

Distributed fluorescence temperature measurement method based on 45-degree inclined grating

The invention discloses a distributed fluorescence temperature measurement method based on 45-degree inclined gratings, and relates to the field of temperature monitoring under high-temperature conditions of engine turbine blades and the like. 45-degree inclined grating strings are designed and manufactured, the outer sides of the 45-degree inclined gratings are coated with fluorescent materials, and the fluorescent materials are made to emit light through ultraviolet pulse excitation light; the fluorescence returns to the optical fiber through the 45-degree inclined grating, the fluorescence lifetime is measured, temperature monitoring is achieved according to the relation between the fluorescence lifetime and the temperature, the detection position is calculated through the pulse light return time, and temperature distribution of different positions is obtained. According to the distributed fluorescence temperature measurement method based on the 45-degree inclined grating, the measurement precision and the signal processing capacity are improved through a time correlation single photon counting method, the grating can be inscribed on a sapphire optical fiber, and the method is suitable for temperature monitoring in the high-temperature field of engine turbine blades and the like; and meanwhile, the device has a multi-point temperature measurement effect with high precision and strong high-temperature adaptability, and is of great significance to high-temperature environment monitoring.
Owner:XIAN XINYUAN YUTONG ELECTRONIC TECHNOLOGY CO LTD

Impurity detection system for high-purity gas and detection control method thereof

The invention relates to an impurity detection system for high-purity gas and a detection control method thereof, and the impurity detection system for the high-purity gas comprises a detection path selection module, a busbar sample introduction module, a chromatography pretreatment module and a moisture detection pretreatment module, the detection path selection module is connected with confluence path units contained in the busbar sample introduction module, the chromatography pretreatment module comprises a plurality of chromatography pretreatment units, the confluence path units are respectively connected with the corresponding chromatography pretreatment units, each confluence path unit is connected with the moisture detection pretreatment module, and the moisture detection pretreatment module is connected with the detection path selection module. The detection path selection module is used for acquiring storage information in a high-purity gas storage tank, and performing corresponding chromatographic analysis steps and / or moisture detection analysis steps on the high-purity gas according to the storage information; the opportunity and parameters of gas entering the detection equipment are automatically adjusted according to the storage states of different steel cylinders, so that the accuracy of a detection result is improved.
Owner:WUHAN IRON & STEEL GRP GAS CO LTD

Juice filling detection system and detection method

The invention relates to the technical field of filling detection, in particular to a fruit juice filling detection system and method.The fruit juice filling detection method comprises the steps that a container image is obtained through a filling module, a preset amount of fruit juice is filled according to the container image, an audio signal in the filling process is obtained, a conveying module conveys a container, and a vibration signal in the container conveying process is obtained; the cover sealing module performs cover sealing action on the container and obtains a stress value of the mechanical arm in the cover sealing process, the filling detection unit judges whether the container filling process is abnormal or not according to the combination of the audio signal and the vibration signal, and the cover sealing detection unit judges whether the container cover sealing process is abnormal or not according to the stress value. According to the invention, the filling process and the capping process are respectively detected, and various problems in the juice filling process are identified, so that the detection accuracy of juice filling is improved.
Owner:TIANJIN CHENG BAO FRESH ORANGE JUICE CO LTD

Flexible pressure sensor and preparation method thereof

The invention relates to a flexible pressure sensor and a preparation method thereof. The preparation method of the flexible pressure sensor comprises the steps of providing a flexible conductive substrate, etching one surface of the flexible conductive substrate by adopting first laser to form a first microstructure with the same height, and then etching the side wall of the first microstructure by adopting second laser to form a hierarchical microstructure with at least one annular groove, a first flexible substrate is obtained; providing a second flexible substrate, wherein the second flexible substrate comprises a second flexible substrate and an electrode arranged on one surface of the second flexible substrate; and arranging a second flexible substrate on the first flexible substrate in a laminated manner, and enabling an electrode to be in contact with the hierarchical microstructure, thereby obtaining the flexible pressure sensor. The flexible pressure sensor prepared by the preparation method not only can maintain high sensitivity, but also has a wide detection range, and can maintain a good linear relation of output signals.
Owner:钱塘科技创新中心

Shaft damage and leakage monitoring system and method for geological sequestration of carbon dioxide

The invention relates to the technical field of environment monitoring, in particular to a carbon dioxide geological sequestration shaft damage and leakage monitoring system and method.The system comprises a shaft, a probe, an optical fiber temperature sensor and an optical fiber strain sensor, the probe comprises an open circular ring, and a groove is formed in the upper end face of the circular ring; the optical fiber sensor is embedded into the groove; the shaft is sleeved with a plurality of annular probes at intervals. Resistivity probes can be arranged around a shaft in a 360-degree omnibearing mode, detailed information of stratums around the shaft can be monitored through resistivity, the distributed optical fiber sensors provide meter-level even centimeter-level spatial resolution, carbon dioxide leakage or migration in any direction can be captured in an omnibearing mode, the detection sensitivity and reliability of the system are improved, and the detection cost is reduced. And meanwhile, the advantage of continuous real-time monitoring of the optical fiber sensor is used as a triggering mechanism to dynamically adjust the resistivity scanning frequency, so that timely detection and response to shaft damage are realized.
Owner:SHANDONG UNIV

Surface defect segmentation model based on improved YOLOv8-seg chip and training method and application thereof

The invention discloses an improved YOLOv8-seg-based chip surface defect segmentation model and a training method and application thereof, a network of an improved YOLOv8-seg segmentation detection model is built, a Backbone module comprises a multi-layer ShuffleNetV2 network structure, a picture is subjected to multiple convolution processing, and three effective feature layers are extracted; the Neck module adopts a ConcatSDI network structure and an EMA attention mechanism network structure, the ConcatSDI network structure is used for carrying out multi-level feature fusion on an effective feature layer output by the Backbone module to obtain a feature map, and the EMA attention mechanism network structure is used for carrying out feature weighting on the feature map; the head module is a segmentation head and outputs final feature information based on an output result of the Neck module; and after the network structure of the improved YOLOv8-seg segmentation detection model is constructed, training, verification and testing are carried out. According to the method, the improved yov8-seg segmentation detection model is used for accurately segmenting and detecting the surface defects of the chip, and particularly, the detection precision can still be ensured when the method faces complex backgrounds and low-contrast defects.
Owner:JIANGSU UNIV

Intelligent operation and maintenance system for low-voltage plant station switch cabinet

The invention discloses a low-voltage plant station switch cabinet intelligent operation and maintenance system, and relates to the technical field of switch cabinet operation and maintenance. The low-voltage plant station switch cabinet intelligent operation and maintenance system comprises a data acquisition module; an alarm information pushing module; a remote monitoring and control module; and a switch equipment detection module. According to the invention, the on-off state data and pile head temperature data of the low-voltage plant station switch cabinet are obtained, then the on-off abnormal data of the low-voltage plant station switch cabinet in the preset time period are obtained, sound and light alarm is carried out, terminal display is carried out, and switch equipment detection is carried out on the switch equipment in the preset period so as to obtain the loss parameter. And finally, the triggering condition of the circuit breaker of the switch equipment in the switch equipment detection process is monitored in real time, and current protection tripping is carried out, so that the real-time performance of obtaining the maintenance suggestions in the switch equipment detection is improved, and the problem of low real-time performance of obtaining the maintenance suggestions of the switch equipment in the operation and maintenance process of a low-voltage plant station switch cabinet in the prior art is solved.
Owner:JIANGSU GUODIAN NANZI POWER AUTOMATION CO LTD

Intelligent system applied to food detection

The invention relates to the field of detection, in particular to an intelligent system applied to food detection, which is provided with a conveying detection mechanism comprising a conveying belt and a grabbing mechanical arm, a detection module comprising an X-ray scanning unit, and a food analyzer comprising a food classification unit and a shake analysis unit, scanning images in the shaking process of the packaged food to be detected are obtained, contour features in the scanning images are extracted, then specific features are recognized, the category of the packaged food to be detected is judged in combination with the contour area of the specific features, and non-specific features in adjacent scanning image frames are determined; judging whether the packaged food meets the standard or not based on the contour area ratio of the non-specific features to the specific features, identifying fragment features based on the difference of the contour features in the scanned images, determining the aggregation region of the fragment features in each scanned image, and judging whether the packaged food meets the standard or not according to the area of the maximum aggregation region. And the detection reliability and the detection accuracy of the to-be-detected packaged food are improved.
Owner:GUANGXI ZHUANG AUTONOMOUS REGION INST OF PROD QUALITY INSPECTION