47results about How to "Convenient re-examination" patented technology

The invention discloses a tunnel inspection image acquisition device and s tunnel inspection system. The tunnel inspection image acquisition device comprises a plurality of CD cameras, a plurality ofauxiliary light sources, and a fixed bracket, wherein the CD cameras and the auxiliary light sources are fixed on the fixed bracket, and fixing positions of the plurality of CCD cameras are arranged on the same circular ring; in a working state, the center of the circular ring is arranged at the circle center of a tunnel so as to ensure that the distances from the plurality of CCD cameras to a tunnel inner lining are identical, and the overall photographic angle of the plurality of CCD cameras cover the range of the tunnel inner lining. According to the tunnel inspection system, the tunnel inspection image acquisition device is arranged on a flaw detection mobile platform and cooperates with a computer, a display, a synchronous encoder and a data collector to perform synchronous photographing, disease identification, real-time stitching and display of the tunnel. The tunnel inspection image acquisition device and the tunnel inspection system have the technical features of wide detection range, fast detection speed and high timeliness.

An intelligent test system for the electrical connector comprises a computer, a test control unit and an adaptor for the electrical connector. The adaptor comprises two retractable casings, one casing is equipped with an insulating core, and the other casing is equipped with a testing needle. The test control unit comprises a test unit for on-and-off resistance microcontroller, a test unit for withstanding voltage microcontroller and a test unit for the insulation resistance microcontroller. A control device of the microcontroller and a control device of the matrix switching and driving are positioned between the test control unit and the computer. The invention is suitable for the precise test of various parameters of various kinds of the electrical connector, has the advantages of complete function, accurate test and high efficiency.

The invention discloses a needle guiding support device, which consists of a guiding support structure and a direction indicating plate. The guiding support structure consists of a base, a universal connecting rod, a connecting plate, a supporting plate, a puncture needle supporting piece, and a sheath, wherein the universal connecting rod is connected with the base and can be bent in any direction; the connecting plate is connected with the universal connecting rod; the supporting plate is movably connected with the connecting plate; the puncture needle supporting piece is arranged on the supporting plate and is used for fixing a puncture needle and guiding; and the sheath is arranged on the connecting plate and sleeved on the universal connecting rod. The direction indicating plate has a graphometer structure and is arranged on the puncture needle supporting piece; a plane where the direction indicating plate is positioned is parallel to a line where the puncture needle is positioned; the center of the circle of the direction indicating plate is movably connected with the puncture needle supporting piece, so that the direction indicating plate can freely swing; an angle scale is marked on the circumference of the direction indicating plate; an indicating scale which corresponds to a symmetry axis is 0 degree, and is a centre-of-gravity position in a vertical plane; and the scale is uniformly arranged from 90 degrees below zero to 90 degrees on an arc on left and right sides of the zero-degree angle respectively. The needle guiding support device has the advantages of convenient operation, simple structure, and low cost.

The invention discloses a part defect detection and positioning method based on deep learning and normal graphs. The method comprises the steps that 1, an original image is collected, and a material surface normal graph is obtained through calculation; 2, meshing is performed on the surface normal graph; 3, normal graphs obtained after division of parts with different defects and normal graphs obtained after division of normal parts are used to train a model; 4, an image of a to-be-detected part is collected, and a material surface normal graph is calculated; 5, meshing is performed on the normal graph of the to-be-detected part; 6, images obtained after division in the step 5 are used as input to perform defect detection according to the trained model obtained in the step 3; and 7, feedback and defect positioning are performed according to the detection result in the step 6 and the division result in the step 5.

The invention discloses a forensic medicine examination automatic identification system based on deep learning. The system is used for examining diatom and comprises a data acquisition module which isused for performing automatic image acquisition and image segmentation on a to-be-examined tissue sample so as to obtain a plurality of electron injection images corresponding to the tissue sample astraining data samples and output the training data samples; a data expansion module which is connected with the data acquisition module and is used for carrying out sample quantity amplification on the input training data samples based on a predetermined sample amplification method; a model iterative training module which is connected with the training data expansion module and is used for carrying out iterative training by adopting a deep learning method based on the training data sample and/or an externally input training sample to form a deep learning model; and a recognition module whichis connected with the model iterative training module and is used for carrying out diatom component inspection on the input electron injection picture based on the deep learning model, so that the full automation of the diatom inspection is realized, and the diatom inspection accuracy is improved.

The invention discloses a tunnel routing inspection method. The method includes the following steps that S1, a flaw detection movement platform enters a tunnel area, the center of a circular ring where a plurality of CCD cameras on the flaw detection movement platform are located is adjusted to be the circle center position of a tunnel, thus the distances between the plurality of CCD cameras and atunnel lining surface are consistent, and then tunnel routing inspection is started; S2, according to the displacement amount of the flaw detection movement platform, synchronous pulse periodic signals are sent at intervals of fixed distance so as to trigger the plurality of CCD cameras and a plurality of auxiliary light sources to work synchronously, and tunnel lining images are shot; S3, the tunnel lining images are collected in real time and are numbered in combination with the synchronous pulse periodic signals; and S4, the numbered tunnel lining images are subjected to image recognitionand trouble spot marking, and meanwhile the tunnel lining images which are already subjected to trouble spot marking are spliced and displayed in real time. The tunnel routing inspection method has the technical characteristics that the detection speed is high, the timeliness is high, the recognition accuracy is high, routing inspection positioning is accurate, and the shot images are clear.

The invention provides a sample analysis device, comprising a substrate, a detection unit, and a working stage. The working stage is provided with a first detection channel and a second detection channel. The invention further provides a sample detection device and a sample detection method. In the embodiment of the present invention, after the submitted sample on one detection channel is detected, a submitted sample on the other detection channel is detected by arranging the first detection channel and the second detection channel which are parallel. If the previous submitted sample does notrequire to be re-examined, the subsequent submitted samples can be continuously detected; and if the previous submitted sample requires to be re-examined, the relative position of the working stage and the detection unit can be adjusted by a displacement device to re-examine the previous submitted sample. Continuous detection of the submitted samples is guaranteed, there is also no need to increase the workload to save and organize the samples waiting for the test results, and the sample requiring to be re-examined is re-examined conveniently and rapidly.

The invention discloses a defect reinspection system and method. The defect reinspection system comprises an AOI detection line body control module LCS1, a reinspection line body control module LCS2,an AOI detection module and a reinspection module. The AOI detection line body control module LCS1 is used for controlling the AOI detection module and receiving an AOI detection result; the reinspection line body control module LCS2 is used for controlling the reinspection module and sending a trigger instruction to the reinspection module; the AOI detection module is used for carrying out defectdetection on the panel and uploading a defect detection result to the line body control module LCS1; the reinspection module is used for obtaining a defect detection result from the AOI detection line body control module LCS1 and carrying out reinspection on the defect detection result. According to the reinspection system, the reinspection module can directly and automatically obtain the AOI detection result, and the working efficiency of reinspection is improved.

The invention discloses a transmission line icing dancing monitoring and early warning device and method. The device comprises a power supply control unit, an upper computer unit, a meteorological data processing unit, an icing model processing unit, a power grid information screening unit, a data integrated processing control unit and a remote early warning unit. According to the invention, a weather information acquisition module in the meteorological data processing unit acquires real-time weather data of the position of a transmission wire, and transmits the data to the icing model processing unit used for calculating an icing model; the icing model processing unit can send a calculation result to a dancing trip risk factor module to calculate the dancing probability when the wire surface is iced; transmission wire icing monitoring do not need a large number of sensors, so that the sensors are prevented from being damaged by bad field weather and other reasons; and wire surface icing monitoring and dancing monitoring are combined, so that an icing dancing monitoring result of the whole transmission line is accurate and reliable.

The invention provides a measurement method capable of accurately controlling caterpillar gate embedded part coplanarity. The measurement method is characterized in that a theodolite is arranged on a set measuring basis control point position, a magnet base is positioned on the work surface of an embedded part to be measured, the root portion of a vernier caliper is tightly attached to the measuring work surface of the embedded part, scales of the vernier caliper face to the ocular visible position of the theodolite or a total station, the scale line of the well placed vernier caliper is sought through an ocular cross line of the theodolite or the total station, the scale position of the vernier caliper corresponding to an ocular of the theodolite or the total station is determined, the number value of the vernier caliper is read, and the vernier caliper reading difference value of all other detection points is the vertical difference value of the embedded part; and reading values of all points of the work surface of another embedded part are measured by repeating the steps, the difference value of two side vernier caliper reading difference values is the difference value of embedded part coplanarity, and the embedded parts are adjusted to reach the preset adjustment position by determining the difference value of the coplanarity and the verticality of the embedded parts.

The invention discloses a high-dynamic imaging detection method and system for textile fabric flaws, and the detection system is combined with a high-dynamic processing method, and a low-cost CMOS image sensor cooperates with an FPGA control logic circuit so a high-dynamic range image (HDR) can be collected in the movement process of textile fabric, thereby effectively solving the defects of scenechange and the like caused by camera shaking during exposure time and long shooting interval of sequence images during cloth inspection (namely flaw detection) and inaccurate flaw detection structure; in addition, the dynamic imaging system carries the low-cost CMOS image sensor so that high-dynamic image acquisition is met, the cloth inspection cost is effectively reduced, and the accuracy is improved.

The invention relates to an enclosed multifunctional integrated system for biotherapy. The system comprises a loading module, a medicine adding module, a sampling module, a culture bag joint module, pipeline switches, and pipelines; the loading module is connected to the culture bag joint module through the pipelines, the pipelines near the loading module and the culture bag joint module are both provided with a pipeline switch; two sides of the pipeline between the two pipeline switches mentioned above are respectively connected to the medicine adding module and the sampling module through pipelines; and the pipelines near the medicine adding module and the sampling module are both provided with a pipeline switch. The structure of the system is smart, the safety is high, the system has multiple functions, which can be assembled freely, the work efficiency is high, the safety of organisms in the system can be guaranteed, the operation time is shortened, the labor strength is reduced, the requirements on operators are lowered, and a safer standard solution is provided for biotherapy.

The invention relates to the technical field of deep learning, and provides a human body skeleton labeling method and device and electronic equipment, and the method comprises the steps: obtaining a to-be-labeled current frame of human body image and corresponding current frame skeleton key point information, image information of the current frame of human body image and skeleton key point information of the current frame are stored as a current frame annotation file, and the skeleton key point information comprises type information and position information of skeleton key points; labeling the current frame of human body image by using the current frame of labeling file to obtain an initial labeling image, and judging whether missing detection or false detection exists in the initial labeling image to obtain a judgment result; and correcting the skeleton key points with leak detection or false detection in the initial annotation image corresponding to the current frame of human body image according to the judgment result to obtain the current frame of annotation image. According to the embodiment of the invention, the human skeleton annotation image can be quickly and accurately obtained.

The invention discloses an assembly production line of a first-aid case. The assembly production line comprises an automatic labeler, a conveying line which passes through a plurality of feeding stations, and a material receiving line; the automatic labeler is correspondingly arranged at the head end of the conveying line; the head end of the material receiving line is correspondingly arranged atthe tail end of the conveying line; a material blocking mechanism and a scanning mechanism I are arranged at the part, corresponding to each feeding station, of the conveying line; the scanning mechanism I comprises two kinds of scanning guns; one kind of scanning gun is used for scanning a two-dimensional code outside the first-aid case; the other kind of scanning gun is used for scanning a two-dimensional code of an object put in the station; a scanning mechanism II is arranged in the material receiving line; and scanning guns which are arranged in the scanning mechanism II are used for scanning the two-dimensional code outside the first-aid case. The working condition of each feeding station is monitored with the adoption of an on-line code scanning mode, and the first-aid case in whichthe objects are put less or more is automatically identified.

The invention provides a civil aviation maintenance work card system based on voiceprint recognition and voice instruction control, which comprises audio acquisition equipment, a noise reduction processing module, a voiceprint recognition module, a service processing module and a voice synthesis module, and is characterized in that the audio acquisition equipment acquires an audio file and transmits the audio file to the noise reduction processing module; wherein the noise reduction processing module performs environment sound filtering and human voice gain processing on a received audio fileand then transmits the audio file to the voiceprint recognition module, the voiceprint recognition module performs fragmentation, peak clipping and feature extraction on the audio file after noise reduction, constructs a voiceprint model according to features, compares the voiceprint model with a sample voiceprint model and returns comparison similarity, the models are transmitted to the service processing module, and the service processing module carries out identity verification according to the comparison similarity. According to the civil aviation maintenance work card system based on voiceprint recognition and voice instruction control, the safety problem of work card operation is solved through the biotechnology, and meanwhile the maintenance process is organized and intelligentizedbased on voice recognition control.

The invention relates to the technical field of detection, in particular to a device and method for detecting the cleanliness and flatness of a flat plate, and the device comprises an image collectiondevice, a relay lens, a beam splitter prism, an objective lens, an objective lens jacket, a power supply device, a dark field lighting device, a coaxial lighting device and a light source control device. The invention provides a device capable of detecting the cleanliness and concave-convex points of flat glass, which can accurately distinguish defect types on a flat plate and is suitable for production detection.

The invention discloses a rear rack assembly in a wind generating set. The rear rack assembly comprises a rear rack welding part and a rear rack accessory. The rear rack seaming comprises a main rackconnecting plate, an upper panel, a lower panel, a left side plate, a right side plate, a generator front support seaming, a generator rear support seaming, a cantilever crane mounting support seaming, a cabin bracket mounting plate, a cabin cabinet mounting bracket, a left side walking channel mounting bracket, a right side walking channel mounting bracket and the like; and the rear rack accessory comprises a generator rotor outgoing cable, a rotor outgoing cable mounting rack, a generator stator outgoing cable, a stator outgoing cable mounting rack, a generator auxiliary junction box outgoing cable mounting rack, a gear box cooling system pipeline and a grid type cable bridge. The rear rack assembly not only is used for supporting key components such as a generator, a cabin control cabinet I, a cabin control cabinet II, a cabin bracket and a walking channel cover plate, but also is used for fixing components such as an outgoing cable and a cable mounting frame, and has the characteristics of simple structure and convenience in mounting.