32results about How to "Meet the needs of online testing" patented technology

The invention relates to a leakage detection and location method and a system thereof based on infrared imaging technology, belonging to the detection technology field. The leakage detection and location system comprises a control device, an infrared imagery device, a cooling device, a sensing unit, an air charging system and a display device. Gas with certain pressure is cooled by the cooling device to be used as test medium, each value is driven by the control device to implement aeration completion timing control on a measured object, and the system state is detected by the sensing unit, a infrared picture of the measured object is collected by the infrared imagery device and then transmitted to the control device to undergoing a series of image processing operations for analysis, leakage amount calculation and leakage point location, the test results is showed on the display device. The invention has high detection precision, high-efficiency for leak point locating, strong anti-interference ability and can take non-contact automatic measurement.

The invention relates to a brightness correction and color classification-based fruit surface defect detection method and system. The method includes the following steps that: a R component image in an RGB image of fruit to be detected is extracted, brightness correction is performed on the R component image, so that the brightness of the R component image can be uniform; HSI transform is performed on the RGB image, so that an H value in the HSI transform corresponding to each pixel in the RGB image is obtained, the H values are compared with the H values of preset colors, so that the color of each pixel can be judged; and the color of each pixel is compared with a preset threshed value corresponding to the color, so that judgment can be performed, a defective region to be confirmed is obtained from the R component image which has been subjected to the brightness correction, the gray values of all pixels except the defective region to be confirmed in the R component image are zeroed, and based on further judgment, the gray values of recognized fruit stem/calyx regions in the defective region to be confirmed are zeroed, and finally, a defective region of the surface of the fruit can be obtained. With the method and the system of the invention adopted, the accuracy of fruit defect detection can be improved.

The invention discloses a rail fastener anomaly detection system based on binocular vision and laser speckle, which is composed of a laser speckle projector, a camera, a laser displacement sensor, a wheel encoder, an RFID detector and an industrial computer. The speckle projector and the camera constitute a binocular stereo vision speckle imaging system, which is used for three-dimensional measurement of the fastener; the laser displacement sensor is used to measure the height of the fastener installation support, which is used to control the camera imaging, wheel encoder and The RFID detector is used for mileage counting, the industrial computer completes the image acquisition and processing, and the method based on binocular vision stereo matching is used to detect whether the fastener is abnormal. The device uses a laser speckle light source to artificially increase the mottled texture on the surface of the fastener, which can improve the matching accuracy of image blocks and accurately reconstruct the three-dimensional shape of the fastener, thereby effectively detecting various abnormalities of different types of fasteners.

The invention relates to an FPC gold finger surface defect detection system and method based on an AOI technology. The system comprises an X-Y-Z multi-axis motion platform and a camera. A central processor carries out motion control and positioning on the platform through a motion control card. The camera carries out digital image acquisition. The central processor carries out preprocessing on theacquired image data. RIO region processing is carried out on a preprocessed image. Feature extraction is carried out on the image data, and image recognition is carried out. According to the FPC goldfinger surface defect detection system and method based on the AOI technology, which are provided by the invention, through an multi-axis operation control device and an image acquisition device, theautomatic optical inspection technology (AOI) is adopted to acquire the surface state of FPC by optical means; based on empirical mode analysis (EMD) and an HU invariant moment feature fusion method,feature extraction is carried out; the classification problems of small sample deficiency and difficult defect identifying are effectively solved; the detection efficiency is improved; and the detection cost is reduced.

The invention relates to a flotation dosing abnormity detection method based on NSST morphological characteristics and depth KELM. The method comprises the following steps: firstly, acquiring a bubble image on the surface of a flotation tank in real time, and decomposing the image NSST to obtain a low-frequency sub-band image and a multi-scale high-frequency sub-band; secondly, binarizing the low-frequency image to extract bubble bright spots, calculating the number, the area, the standard deviation and the ellipticity of the bright spots, and calculating the fractal dimension, the mean value and the variance of high-frequency sub-band coefficients of all scales to form multi-scale morphological characteristics of the bubble image; then, on the basis of the KELM algorithm, a deep KELM is constructed by referring to a deep learning idea, quantum calculation is introduced into optimization of a genetic algorithm and used for optimizing parameters of the deep KELM, and an adaptive deep KELM is constructed; and finally, establishing a flotation dosing abnormity detection model through the multi-scale morphological characteristics and the self-adaptive depth KELM. The average recognition rate and the operation efficiency are obviously higher than those of an existing detection method, the requirement for flotation production on-line detection is better met, and a foundation is laid for follow-up dosing automatic control.

The invention relates to a refractory brick inside quality online detection device comprising a hardware system and a software system. The refractory brick inside quality online detection device is characterized in that the hardware system adopts a modular structure comprising a main processing module, a voice acquisition module, a PC serial communication module, an auxiliary external module and a knock control module; a main processing chip of the DSP main processing module is a 5509A chip which is used for managing an external memory space through an internally and externally arranged external memory interface, the external memory space is divided into CE0-CE3, and each space is provided with a chip selection use signal/CEn. The software system provides a method for detecting and diagnosing inside defects of a refractory brick by utilizing a refractory brick knock acoustical signal and develops corresponding software. The invention solves the problem that the refractory brick inside quality detection device is outmoded, ensures that a refractory brick inside defect detection device is stable and rapid to run, simple to operate and complete in function and can completely meet the requirement of refractory brick inside quality online detection, thereby being applied to refractory brick production plants for improving the production quality and the efficiency.

The invention discloses a method for judging storage period of tea by a hyperspectral image technique. The method comprises the following steps of establishing a qualitative analysis model by combining the hyperspectral image technique and a support vector machine algorithm, so as to quickly and accurately judge the storage period of the tea. The method has the characteristics that the analysis speed is quick, the efficiency is high, the cost is low, the testing reproductivity is good, the pretreatment of the sample is not needed, and the online non-destructive testing can be conveniently performed.

The invention relates to an automatic online testing system for a millimeter wave packaging antenna. The automatic online testing system comprises a small shielding box, a radio frequency transceivingmodule, a transceiving antenna probe, a probe support, a to-be-tested antenna interface board and an upper computer, wherein the transceiving antenna probe, the probe support and the to-be-tested antenna interface board are arranged in the small shielding box, the radio frequency transceiving module is connected with the transceiving antenna probe, the o-be-tested antenna interface board and theupper computer, and the transceiving antenna probe is installed on the probe support. A to-be-tested antenna is installed on the to-be-tested antenna interface board during testing. The transceiving antenna probe and the to-be-tested antenna radiate a specific frequency signal generated by the radio frequency transceiving module to a free space in the small shielding box at the same time and receive a feedback signal, and the upper computer collects antenna information of the transceiving antenna probe and the to-be-tested antenna so as to test the performance of the to-be-tested antenna. Compared with the systems in the prior art, the system has the advantages that the test result can be obtained quickly, the cost and the space are saved, and the system can be used on a production line ona large scale.

The invention discloses a sample rack managing and conveying device and a biochemical immune assembly line. The sample rack managing and conveying device comprises a mounting structure, a sample rack management structure, a sample rack carrying mechanism, an information reading structure and a sample rack relay conveying system. The sample rack relay conveying system comprises a bearing piece; a sample frame rail transfer mechanism provided with a rail transfer rail and a guide rail; and a sample rack conveying mechanism provided with a first conveying mechanism and a second conveying mechanism. According to the invention, the samplerack carrying mechanism carries the sample racks into the orbital transfer track, the orbital transfer track pushes the sample racks to the first conveying mechanism, and the sample racks are conveyed downwards through the first conveying mechanism in a relay manner; and the second conveying mechanism convey the returned sample racks to the orbital transfer track or the guide track, so that relay conveying and recycling of the sample racks between different detection instruments are achieved, the online detection efficiency is improved, the online detection requirement of high-throughput samples in clinic is effectively met, and the waiting time of patients is shortened.

The invention discloses a Stockwell transform based epilepsy electroencephalogram detection device. The device comprises an electroencephalogram amplifier, a data acquisition card and a computer. An electroencephalogram signal preprocessing module, an electroencephalogram signal segmentation module, a Stockwell transform feature extraction module, a classification module and an after-processing module are arranged in the computer. Feature extraction of time-varying unstable epilepsy electroencephalogram signals is realized by means of Stockwell transform, and epileptic seizures in the electroencephalogram signals are detected through the computer. The device is effective in detection of epilepsy electroencephalogram signals and suitable for online electroencephalogram classification detection.

The present invention relates to the detecting technology of water content in textile, and is especially one new type of sizing moisture regaining detecting system. The sizing moisture regain detecting system includes microwave emitting device and microwave receiving device without contact with the sizing to be detected, data acquiring card to acquire electric signal and convert into digital signal fed to the computer, and computer to calculate the dielectric loss value and the sizing moisture regain. The present invention performs on-line no-contact detection and obtains precise measurement result.

The invention discloses a worm gear type cam profile detector, which includes a box body, a transmission unit and a control unit, and the transmission unit includes a worm wheel, a worm, a first bearing, a second bearing, a third bearing, a first The transmission shaft, the second transmission shaft, the gear shaft, the spur gear, the fixture, the fourth bearing, the first bevel gear and the second bevel gear; the control unit includes a distance sensor, a circular grating and a control module. The rotation of the transmission unit drives the rotation of the measured cam on the fixture, and the rotation information of the measured cam is collected to the control module through the distance sensor and the circular grating. This profile detector is small in size, low in cost, fast in detection speed, high in measurement accuracy and good in practicability, and can meet the needs of on-line detection in production lines.

The invention belongs to the related technical field of a nondestructive testing technology, and discloses a magnetic focusing sensor for simultaneous detection of multiple defects and a detection system. The sensor comprises a permanent magnet, a magnetic guiding core and a sensing element, the permanent magnet is an annular magnet, a notch is formed in the lower end of the annular magnet, and the magnetic guiding core is arranged on a connecting line of the circle center of the annular magnet and the notch and used for guiding a magnetic field gathered in the center of the annular magnet to the magnetic guiding core. The magnetic guiding core is of a multi-layer sheet-shaped structure, a detection probe is arranged at the bottom of each layer of sheet-shaped structure, the detection probes are used for detecting surface appearance defects of a magnetic material to be detected, and the sensing elements are arranged on the probes of the magnetic guiding core and used for sensing changes of a magnetic field in each detection probe. According to the invention, detection and identification of the micro surface topography of the magnetic material are realized, the resolution ratio, the detection precision and the sensitivity are higher, and the method can adapt to wider processing and manufacturing environments and working conditions.