152results about How to "Avoid missed inspections" patented technology

The invention discloses a turbine blade CT detection device and a detection method thereof. An opening-closing fixture structure is arranged on a fan-beam industrial CT device base; blades are fixed on a fixture so as to be scanned, and the simultaneous scanning for a plurality of blades can be realized; and cracks perpendicular to a scanning sector can be no longer perpendicular to the scanning sector by adjusting the inclination angle of the blades on the fixture. The device can inhibit the influence of dotted noise in CT images on measurement results, is accurate in extraction result to the cracks perpendicular to an X-ray surface, misses no crack detection, is high in measurement precision, adopts a proposal of extracting a crack region by a multi-scale curved-wave transformation method, utilizes the characteristics of curved wave, can adapt to the shape changes of the cracks, and can separate the crack region according to the shapes of the cracks, so as to accurately measure the cracks.

The invention relates to a human face identification-based train on-way ticket check method. The method comprises the basic steps of A, obtaining train running section information; B, acquiring facial images of passengers entering a station, certificate information and ticket information, establishing a passenger facial feature library, performing information matching, and uploading the information to a national railway data center; C, matching the passengers, tickets and the images with the information; D, obtaining compartment real-time images, transmitting the compartment real-time images to a train-mounted unit, and performing real-time image human face detection by the train-mounted unit to judge whether the passengers are qualified to take a train of a current section or not; and E, sending the facial images of the passengers unqualified to take the train of the current section to handheld ticket check terminals of trainmen, performing targeted directional face-to-face ticket check and ticket buying, and uploading and updating ticket buying information to the national railway data center. According to the method, on-way human face automatic identification and running section automatic matching are performed based on the train running information, the passenger ticket information and the facial features, so that train on-way video intelligent ticket check and to-be-checked object automatic identification are realized.

The invention provides a school bus overloading detection and early warning device, comprising a chassis pressure parameter acquisition module, a passenger number information acquisition module, a storage module, a control module, a detection and early warning module, a display module and a communication module, wherein the control module is used for controlling the function realization of the chassis pressure parameter acquisition module, the passenger number information acquisition module, the storage module, the detection and early warning module, the display module and the communication module as a core module; the detection and early warning module performs processing and analysis on information in the storage module and judges whether a school bus is overweighted or not by virtue of chassis pressure parameters and the change of the number of passengers; after the early warning is started, the display module displays early warning information, and the communication module sends out the overloading information. The invention provides a school bus overloading detection and an early warning method.

The invention discloses a Solr-based retrieval method, which comprises the following steps: receiving an information retrieval request, and obtaining retrieval information corresponding to the retrieval request; when the retrieval information is Chinese retrieval information, judging whether the number of characters of the Chinese retrieval information exceeds a preset standard quantity or not; when the number of characters of the Chinese retrieval information does not exceed a preset standard quantity, obtaining an index field corresponding to the Chinese retrieval information in a preset retrieval dictionary; and querying a preset retrieval database, obtaining a target article corresponding to the index field, and outputting the target article as a retrieval result. The invention also discloses a Solr-based retrieval device, equipment and a storage medium. According to the method, the preset retrieval dictionary is constructed by carrying out data analysis on a large amount of text data, and retrieval information is converted into the corresponding index fields through the preset retrieval dictionary in the retrieval process, so that information retrieval is more comprehensive and accurate.

The invention provides a high voltage isolation switch mechanical fault detection device and method. According to the method and the device, correlation coefficients between current data of a to-be-detected high voltage isolation switch and standard waveform are calculated to determine whether the to-be-detected high voltage isolation switch has a mechanical fault and to determine severity of the existing mechanical fault, so fault caused by empirical judgment of a worker can be avoided, moreover, all the current data transmitted by a lower computer can be processed by a host computer, so an operation state of the high voltage isolation switch can be determined, not only can maintenance efficiency be substantially improved, manpower and material cost is saved, but also missing detection can be further avoided.

The invention discloses a differential via hole pair inspection tool for a PCB. The tool comprises a differential signal line search module, a dimension information extraction module, and a dimension storage database, wherein the differential signal line search module is used for receiving identifiers of to-be-inspected differential signal lines inputted by a user; the to-be-inspected differential signal lines are obtained by searching from a preset routing database according to the identifiers, the dimension information extraction module is used for obtaining the dimension information of a pair of differential via holes corresponding to each pair of to-be-inspected differential signal lines by extracting from a PCB board through calculation, the dimension storage database is used for storing the dimension information for subsequent via hole inspection. The differential via hole pair inspection tool for PCB is capable of automatically completing the search of pairs of differential signal lines and acquiring the dimension information of the corresponding differential via hole pairs, and has the advantages of being manpower-saving, high in inspection speed, and high in accuracy, and the situation of missing inspection is avoided as far as possible.

The invention discloses a construction inspection method and device based on a building information model and a terminal. The construction inspection method comprises the steps of obtaining the designinformation of a building information model; generating an inspection task list according to the design information and a preset inspection rule, and sending the inspection task list to an inspectionterminal; receiving an inspection result which is returned by the inspection terminal and corresponds to the inspection task in the inspection task list to enable the inspection personnel or the inspection terminal to perform unified inspection according to the inspection tasks in the inspection task list; and returning an inspection result corresponding to the inspection task in the inspection task list to the terminal for executing the construction inspection method based on the building information model through the inspection terminal to complete inspection of the inspection task in the inspection task list so as to avoid missed inspection.

The invention discloses a routing inspection system and method for a transformer substation, and relates to the field of routing inspection. The method successively comprises the following steps: drawing a transformer substation map; establishing equipment routing inspection frequency; making a routing inspection path; recording equipment information through an IC chip card; fixing the IC chip card to corresponding routing inspection equipment; acquiring the routing inspection path, and holding a routing inspection terminal with a hand to carry out routing inspection according to the routing inspection path; positioning by the routing inspection terminal while scanning the IC chip card; combining target information and the positioning information into routing inspection schedule information by a server; acquiring the routing inspection schedule information by the monitoring terminal from the server; when the monitoring terminal determines an inspection missing condition, transmitting areminding signal to the routing inspection terminal through the server; and receiving the reminding signal and making a reminding action by the routing inspection terminal. The routing inspection frequencies of the routing inspection equipment are analyzed and classified, routing inspection paths of corresponding frequencies are drawn, the routing inspection efficiency is improved, meanwhile, theIC chip card is mounted on the routing inspection equipment, and the condition of routing inspection missing is prevented effectively.

The invention provides a single-sided bilateral multi-angle ultrasonic detection method for heterogeneous structure pattern pipe welds. The single-sided bilateral multi-angle ultrasonic detection method comprises the following steps: establishing a 3D model with two multi-angle ultrasonic probes and a to-be-tested pipeline having flange or elbow welds, and allowing two simulated ultrasonic probesto simulate sector scanning at two sides of the simulated welds; recording the positions of two simulated ultrasonic probes on the simulated to-be-tested pipeline; assembling the two multi-angle ultrasonic probes onto a multi-angle bilateral ultrasonic scanning device; carrying out equidistant linear scanning along the circumference of the to-be-tested pipeline, and collecting detection data of the weld at the same time; and analyzing the weld condition of the to-be-tested pipeline having the flange or elbow welds. According to the invention, through simultaneous transmission of multi-angle ultrasonic waves to welds, only equidistant linear scanning is carried out, so dependence on heterogeneous structure pattern and size is reduced, and the positions and sizes of defects in the welds arequickly identified and calculated; thus, higher detection rate and more visual results of weld defects are achieved, the quality detection of the flange and elbow welds are guaranteed, and work efficiency and defect detection capability are greatly improved.

The invention provides a processing method for question-answer interaction log. The the question-answer interaction log includes a user question and a corresponding seat answer. The processing method includes: executing verbal trick analysis on the question-answer interaction log to determine whether the seat answer has taboo and / or negative feeling or not; utilizing a CRM database to execute business analysis on the question-answer interaction log to judge whether the user question is matched with a business handled by a user or not and to judge whether the seat answer is uniform with extracted CRM data or not; utilizing a question-answer knowledge library to execute question-answer analysis on the question-answer interaction log to determine whether the seat answer is correct or not; marking the question-answer interaction log which does not pass at least one of verbaltrick analysis, business analysis and question-answer analysis for subsequent artificial quality control.

The invention discloses an automatic inspection method and device for a polar electric component in a circuit board. The method comprises the following steps: S1, obtaining an image of a to-be-inspected circuit board; S2, obtaining a preset positioning image template of the to-be-inspected element, performing matching search on the image obtained in the step S1, and positioning to a mounting position of the to-be-inspected element; S3, obtaining a target image of the to-be-inspected element according to the positioned mounting position, obtaining a preset standard image template correspondingto the to-be-inspected element, matching a target image of the to-be-inspected element with the preset standard image template and judging whether the to-be-inspected element is mounted and the polarity mounting state according to a matching result. The device comprises an image obtaining module, an element positioning module and a mounting inspection module. The method and the device in the invention can realize automatic inspection of various polar elements and have the advantages of simple implementation method, low inspection cost, high inspection efficiency and precision, wide range of application and the like.

The invention discloses a vehicle weight determination method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining a tire image of a vehicle, andcarrying out the preprocessing of the tire image; performing image segmentation on the preprocessed tire image, and obtaining the vertical deflection and the radial rigidity of the tire according tothe segmented tire image; calculating the load of the tire according to the vertical deflection and the radial rigidity of the tire; and obtaining the weight of the vehicle according to the load of each tire in the vehicle. According to the technical scheme, the tire image is obtained, the vertical deflection and the radial rigidity are obtained from the tire image, the load of the tire is calculated according to the vertical deflection and the radial rigidity, and the weight of the vehicle is obtained according to the load of each tire in the vehicle, so that the weight of the vehicle is determined automatically in a non-contact mode; therefore, vehicle congestion is avoided, the weight of all the vehicles is determined by acquiring the tire images of all the vehicles, and the convenience, stability and accuracy of vehicle weight determination are improved.

The invention belongs to the technical field of in-vitro detecting, and particularly relates to a creatine kinase isozyme detection reagent kit and a preparation method thereof. The creatine kinase isozyme detection reagent kit comprises a magnetic separation reagent and an enzyme labeled antibody; the magnetic separation reagent comprises magnetic particles, and a first anti-CK-MB monoclonal antibody and a second anti-CK-MB monoclonal antibody are combined with the surfaces of the magnetic particles; the enzyme labeled antibody comprises an enzyme labeled third anti-CK-MB monoclonal antibodyand / or an enzyme labeled fourth anti-CK-MB monoclonal antibody; and the first anti-CK-MB monoclonal antibody, the second anti-CK-MB monoclonal antibody, the third anti-CK-MB monoclonal antibody and the fourth anti-CK-MB monoclonal antibody are specific to different epitopes of creatine kinase isozyme. According to the creatine kinase isozyme detection reagent kit and the preparation method thereof, the surfaces of the magnetic particles in the magnetic separation reagent are combined with the first anti-CK-MB monoclonal antibody and the second anti-CK-MB monoclonal antibody which are specificto the different epitopes of the creatine kinase isozyme, multi-site recognition can be conducted on the CK-MB antigens in a to-be-detected sample, combination between a magnetic bead antibody and theantigens is improved, the detection missing situation can be avoided, the sensitivity is high, and the applicable people range is wide.

The invention relates to the technical field of industrial product surface scratch detection, in particular to a fine scratch detection method and device, electronic equipment and a computer readablestorage medium, and the fine scratch detection method comprises the following steps: convoluting a Laplace operator and a to-be-detected image, and sharpening and enhancing the to-be-detected image toobtain a to-be-detected enhanced image; carrying out mean filtering on the enhanced to-be-detected image to obtain a background image, and carrying out difference processing on the to-be-detected enhanced image and the background image to obtain a to-be-detected scratch image containing a plurality of scratch line segments; extracting a plurality of scratch line segments in the to-be-detected scratch image according to a straight line extraction algorithm to obtain a scratch line segment set composed of starting point coordinates of the plurality of scratch line segments; and generating a binary image by utilizing the coordinates of a plurality of starting points in the scratch line segment set, and performing Hough transform on the binary image to obtain a scratch line segment. Accordingto the embodiment of the invention, fine scratches can be accurately detected by carrying out scratch detection on an image with a relatively large size, so that the situation of missing detection isavoided.

The invention relates to an insulator detection method, device and equipment based on a deep convolutional neural network. The insulator detection method based on the deep convolutional neural networkcomprises the steps: collecting a plurality of original images, carrying out preprocessing on the original images, and constructing a sample training set; constructing a multi-angle candidate regionnetwork structure based on an RPN network, an inclination NMS algorithm and an angle factor; based on the multi-angle candidate region network structure, training the deep convolutional neural networkby using the sample training set to obtain a training model; and recognizing the to-be-recognized image by using the training model, and outputting an insulator image with a target frame if an insulator exists in the to-be-recognized image. Thus, the extraction precision of the insulator information is effectively improved, the situation that missing detection occurs to insulators with complex backgrounds and small targets during detection is avoided, and the situation that the detection effect is poor due to partial overlapping or shielding in insulator images is also avoided.

The embodiment of the invention provides an examination cheating behavior detection method and system. The method comprises the following steps: firstly tracking the sight of an examinee to obtain themovement range of the sight of the examinee, and / or collecting the front region of the examinee to obtain video data; and obtaining a cheating behavior detection result by analyzing the examinee sight movement range and / or video data. The examination behavior of each examinee can be monitored in real time, the cheating behavior of the examinee can be accurately detected, the situation of missinginspection is avoided, the invigilation strength is greatly improved, and the problem that in the prior art, the monitoring and detection effect of a camera is poor is solved.

The invention relates to a full-automatic integrated processing machine of a video graphics array (VGA) interface. The full-automatic integrated processing machine comprises a rack and a power distribution control box, wherein a transmission groove is formed in the rack and is matched with a product, a clamping device, a bolt loading device and a bolt locking device are arranged at a left part of the transmission groove and are matched with one another, an upper bending device and a lower bending device are arranged at a right part of the transmission groove and are matched, detection devices are arranged at a left side of the upper bending device and a right side of the lower bending device, the upper bending device comprises an upper bending air cylinder, an upper bending block is connected with the upper bending air cylinder and is provided with a bending inclined surface inclining at an angle of 45 degrees at an outer side, the lower bending device comprises a lower bending air cylinder, and a lower bending block is connected with the lower bending air cylinder and is provided with a bending inclined surface inclining at an angle of 45 degrees at an inner side. By the full-automatic integrated processing machine, automatic integrated processing is achieved, meanwhile, the accurate bending angle of a terminal can be ensured, detection leakage is prevented, and the processing efficiency is improved.

The invention discloses a system for detecting the paving temperature segregation of an asphalt pavement. The system comprises a temperature sensor group which is arranged on paving equipment and is 10-15cm from the pavement, a distance collection device used for collecting a paving distance and a paving speed, a processing device which is used for receiving temperature information of the pavement collected by the temperature sensor group, receiving paving distance information and paving speed information collected by the distance collection device and performing analysis processing, a display device which is used for displaying analysis processing results for the temperature information, the paving distance information and the paving speed information from the processing device, and a storage device which is used for soring the temperature information, the paving distance information and the paving speed information. The invention further discloses a method for detecting the paving temperature segregation of an asphalt pavement. By adopting the system and the method for detecting the paving temperature segregation of an asphalt pavement, the temperature segregation detection results are accurate.

The invention discloses thiazole orange cyanine dye molecules and application thereof. The dye molecules structurally comprise binding groups, ELISA groups, crosslinking groups and connecting parts. The molecules are applied to cell fluorescence staining and are used for judging the living states of bacteria based on the bacterium esterase activity and used for selectively inhibiting the amplification of bacterium DNA in PCR reaction, so that that the purpose of rapidly and quantitatively detecting living bacteria is achieved. The dye molecules disclosed by the invention are simple in structure, low in preparation cost and high in esterase degradation rate.

The invention provides a method and a device for detecting the target number in a scene. The method comprises the following steps: acquiring a first image of the scene, wherein the first image does not include persons; shooting the scene within a predetermined time bucket to acquire a second image including persons; extracting a foreground image which is the difference zone of the second image and the first image; detecting the second image through a face detection algorithm to obtain at least one face pre-detection zone; when a zone matched with the face pre-detection zone exists in the foreground image, determining the face pre-detection zone as a person target; counting the determined person targets to obtain the target number in the second image. Through the adoption the technical scheme, the target number in the scene can be counted without manual operation, so that the scheme is low in cost; through comparison between the result of the face detection algorithm and the foreground image, the statistical result is high in accuracy.

The invention discloses a CT image detection method and device, a storage medium and an electronic device. The method comprises: acquiring a single-layer to-be-detected two-dimensional image and a single-layer to-be-detected two-dimensional image in multiple layers of two-dimensional images and continuous N layers of two-dimensional images on one side of the single-layer to-be-detected two-dimensional image and / or continuous N layers of two-dimensional images on the other side of the single-layer to-be-detected two-dimensional image as current to-be-detected images; wherein N is an integer greater than or equal to 1, and then generating a region of interest of the to-be-detected CT image by using the neural network model to replace manual detection of the region of interest in the CT image, thereby greatly reducing the workload of medical personnel, improving the detection efficiency, avoiding missing detection and improving the detection accuracy. Moreover, considering that positionssuch as fractures are usually reflected on continuous multi-layer images, a detection result is comprehensively obtained by detecting the multi-layer continuous images and combining upper-layer imagesand lower-layer images, so that the detection accuracy is further improved.

The invention provides a vehicle automatic fire extinguishing system. A temperature sensing cable is arranged in a vehicle engine compartment; a temperature sensing cable is arranged on the inner wall of a vehicle body, and encircles the inner wall of the vehicle body by a circle, fire can be sensed no matter whether the vehicle is self-ignited or other persons perform malevolent arson at any place in the vehicle body, it is not limited to that a certain point in the vehicle body is detected, spontaneous combustion can be detected, arson can also be detected, and the detection missing condition is avoided; and a gas distributing device is arranged and acts on a fire extinguishing agent storing tank under high pressure, a fire extinguishing agent is made to be sprayed out of a forming jetting pipe encircling the inner wall of the vehicle body, and can be jetted to each corner to extinguish a fire, it is avoided that the fire extinguishing agent can be jetted only from a certain point, fire spreading is effectively avoided, the fire is killed in the bud or in the initial stage of the fire, the fire is extinguished in time, and the loss is reduced.

The invention discloses a device for hub detection.The device comprises an objective table and a detection device.The objective table is connected with a first transmission device and a second transmission device.The objective table can horizontally move under the effect of the first transmission device.The second transmission device is connected with a first driving device.The first driving device drives the second transmission device so that a hub on the objective table can rotate in both the horizontal direction and the perpendicular direction.The detection device comprises an X radiation source and an imaging device.The X radiation source and the imaging device are located on the two sides of the hub respectively.The imaging device comprises an optical grating plate and a detector.The surface of the optical grating plate is provided with an adjustable region defined by sliding stop pieces.The optical grating plate is connected with a second driving device.The second driving device can drive the optical grating plate to rotate perpendicularly.According to the device for hub detection, the automation degree and convenience of hub assembling and disassembling are improved, the comprehensive and non-dead-corner detection effect on the hub is achieved, and the using performance of the device for hub detection is enhanced.

The invention discloses an automatic detecting and removing device for preventing product errors and belongs to the field of industrial automatic detection devices. The automatic detecting and removing device for preventing product errors can detect products in a full-automatic manner and comprises a detecting mechanism, a conveying mechanism, a control system and a removing mechanism. The conveying system comprises an installing frame, a driving mechanism and a conveying part. The detecting mechanism comprises a camera and a light source. The camera is in signal communication with the control system. The removing mechanism comprises a cylinder push rod mechanism and a removed product containing table. According to the automatic detecting and removing device for preventing product errors, the camera is used for taking pictures of products to be detected to obtain images; then, image information is extracted through image processing software; and finally the image information is judged so that the purposes of automatically detecting the products can be achieved. Automatic detection for preventing product errors is achieved, detecting efficiency is improved, and the leak detection condition is avoided; and the mismatch condition during product assembly can be effectively avoided.

The invention provides a smoking behavior and calling behavior identification method based on a video stream. The method comprises the following steps: S1, collecting a data set of model training; S2,installing and compiling a caffe framework supporting 3D convolution; S3, building a classification network architecture based on Tiny_darknet-3D deep learning; S4, setting hyper-parameters of the training network model; S5, directly obtaining a monitoring video stream from monitoring equipment of a to-be-monitored scene; S6, sending the video data obtained in the step S5 into a pre-trained modelin the step S3 for 3D convolution processing, and outputting a classification result; and S7, setting a threshold value according to the confidence value of the target, removing the target with a relatively low confidence value, and storing the image. According to the smoking behavior and calling behavior recognition method based on the video stream, the problems that a traditional smoking and calling detection method is prone to causing target missing detection, the false detection rate is high, an original video cannot be directly recognized, and time dimension information is lost are solved.

The invention discloses a smoothness detection device with a thickness detection function for gastroscope lens processing, and relates to the technical field of gastroscope lens processing; the smoothness detection device comprises a workbench, a rotating table and a detection mechanism, a rotating motor is embedded in the middle of the workbench, a rotating shaft is arranged on the upper side ofthe rotating motor, and sound insulation cotton is arranged on the two sides of the rotating motor; the rotating table is fixed above the rotating shaft, a moving mechanism is arranged above the rotating table, a bearing mechanism is installed above the moving mechanism, a gastroscope body is arranged in the middle of the upper portion of the bearing mechanism, an upper frame body is fixed to theouter side of the upper portion of the workbench, and a detection mechanism is installed below the middle of the upper frame body. And display screens are fixed in the two sides of the upper portion of the upper frame body, the detection mechanism comprises an air cylinder, a piston rod, a lifting plate, a distance measuring sensor and an ultrasonic sensor, and the device has the beneficial effectthat by arranging a cleaning brush, the glass window sash can be conveniently and automatically cleaned.

The invention discloses a display panel, a drive method thereof, and a display device. The display device comprises the display panel, and the display panel comprises a pixel unit formed by the crossing of a plurality of rows of scanning lines and a plurality of columns of data lines, wherein each row of scanning lines are connected with one GOA array substrate scanning line drive unit for providing a scanning line drive signal. A switching unit is disposed between each drive unit and a corresponding scanning line, and the corresponding drive unit and scanning line are turned on and off by theswitching unit in an even-odd manner. Through the control of the on / off of an odd switch or an even switch, the display device can detect the defective area of the pixel unit, avoids the occurrence of the missed detection, and can accurately locate the defective specific position.

The invention discloses a motion foreground detection method and device, terminal equipment and a storage medium. The method comprises: obtaining a to-be-detected current video frame; when the current video frame is the first frame of picture, initializing a pre-established first Gaussian mixture model by using the pixel value of each pixel point of the current video frame; otherwise, performing motion vector estimation on the current video frame according to the background frame to obtain a global motion estimator of the current video frame; performing position correction on the first Gaussian mixture model of each pixel point in the current video frame according to the global motion estimator; matching each pixel point of the current video frame with the first Gaussian mixture model of which the position is corrected; and classifying each pixel point in the current video frame into a foreground pixel point and a background pixel point according to a matching result. According to the invention, the problem of missing detection of the motion foreground in a current motion foreground detection method in a dynamic scene can be solved.