21results about How to "Avoid Manual Inspection" patented technology

The invention relates to a high-speed rail traction system motor temperature monitoring device based on an RBF neural network, belongs to the field of intelligent sensing, and solves the problems of low sensor precision and high early warning and false alarm rate. Comprising a plurality of traction motor temperature sensors which are distributed in each motor and used for measuring the temperature of the motor in real time, obtaining the current motor temperature and transmitting the current motor temperature to a microprocessor; the microprocessor performs nonlinear error temperature compensation on the current motor temperature monitored by the sensor by using an RBF neural network based on an improved particle swarm to obtain compensated motor temperature values, judges whether all the compensated temperature values are smaller than a first temperature threshold value or not, and sends a first early warning instruction to the early warning module if not; a speed reduction instruction is sent to a high-speed rail centralized control center, and a signal is sent to the air feeder corresponding to the motor with the compensated temperature value exceeding the preset temperature threshold value for cooling; if any one of all the compensated temperature values is larger than or equal to a second temperature threshold value, a stopping instruction is sent; and the early warning module performs early warning based on the early warning instruction. And accurate temperature monitoring is realized.

The invention discloses a model training method based on deep learning and a transmission tower corrosion detection method, and the method comprises the steps: constructing an original sample image set of a transmission tower, marking the original sample image set according to the corrosion level, and obtaining a first sample image set; preprocessing the first sample image set to obtain a second sample image set; a preset deep learning model is trained according to the second sample image set, a trained deep learning model is obtained, and a network architecture of the deep learning model comprises Faster R-CNN, ResNet, U-Net and ViT; and optimizing the trained deep learning model to obtain a corrosion detection model, and carrying out transmission tower corrosion detection according to the corrosion detection model. Therefore, the image features can be automatically learned, manual intervention is not needed, the method can adapt to the image features under complex backgrounds and different illumination conditions, and the accuracy and robustness of transmission tower corrosion detection are effectively improved.

The invention relates to the technical field of notching machines, and discloses a notching machine with a detection mechanism and a using method thereof, the notching machine comprises a workbench, and a shell is fixedly mounted at the bottom of the workbench. According to the invention, current, motor rotation speed and temperature data in the device can be received through the data receiving module, then the data is analyzed through the data analysis module, and then the rotation speeds of metal, paper and conveyed material cuts are recorded and stored through the parameter library. Then an automatic selection module automatically selects a corresponding rotating speed for a notch motor according to a specific material detected by an infrared detector, then an automatic early warning module can carry out early warning work on potential dangers of the device, and then a remote control module is used for facilitating remote operation of workers, so that the working efficiency is improved. And through cooperative use of the parameter library, the automatic selection module and the remote control module, the rotating speed of the incision can be automatically selected according to materials, so that the quality of the incision and the intelligence of the equipment are improved.

The present invention discloses a vehicle window drop detection method and a vehicle intelligent security inspection system and device, which belong to the field of mixed security inspection of people and vehicles and are applied to a vehicle intelligent security inspection system. The vehicle intelligent security inspection system comprises at least four cameras, and the vehicle intelligent security inspection system is used to perform security inspection on the vehicle. The vehicle comprises four windows, and each of the windows is photographed by one of the cameras. The vehicle window drop detection method comprises: when a license plate on the vehicle is detected in a security inspection area, an image of the side of the vehicle is acquired; based on the image of the side of the vehicle, a window recognition model is established, and the state of the window is determined according to the image of the window and the window recognition model. By detecting the state of the vehicle window when the license plate on the vehicle is detected, manual detection of the vehicle window can be avoided, thereby improving the efficiency of security inspection, thereby shortening the security inspection process and saving police resources.

The invention discloses a corrosion state detection and evaluation system for a floating offshore wind power mooring system. The mooring system is divided into a plurality of areas, and a detection device is arranged in each area. Each detection device is used to collect data of a corrosion state reference object in the corresponding area and transmit it to a field acquisition instrument, a data transfer station and a data analysis center. The corrosion state reference object includes seawater temperature, dissolved oxygen content and seawater flow rate, sacrificial anode protection potential and protection current density. The corrosion state evaluation system performs data preprocessing on the data detected by the detection device. The artificial neural network model corresponding to each area evaluates the corrosion degree of the current area based on the preprocessed data. The influence of the partial corrosion degree on the overall corrosion state is determined by the grey correlation degree, that is, the correlation degree between the sub-area and the entire mooring system to determine the proportion of the evaluation result of the sub-area in the corrosion state evaluation of the mooring system. Thus, the corrosion state detection and evaluation of the floating offshore wind power mooring system is realized.

The invention discloses a circulating tablet bottling machine, which is applied to the technical field of tablet bottling machines, and is characterized by comprising a base and a U-shaped conveying line which is fixedly connected to the base and is used for conveying medicine bottles, the base is fixedly connected with a tablet filling detection assembly used for filling quantitative tablets into a medicine bottle and detecting the surfaces of the tablets in the filling process. The base is further movably connected with at least one medicine bottle clamping and pouring assembly and a tablet removing assembly based on the rotary disc assembly, wherein the tablet removing assembly is used for detecting poured tablets and removing bad tablets. The base is further fixedly connected with a medicine bottle pushing assembly and a tablet recycling assembly, wherein the medicine bottle pushing assembly is used for pushing aside medicine bottles located at the feeding end of the U-shaped conveying line so that empty medicine bottles with tablets poured out can enter the medicine bottle pushing assembly, and the tablet recycling assembly is used for bearing the tablets and feeding the tablets which are detected to be qualified into the tablet filling detection assembly again. The device has the technical effects that automatic detection is realized, and medicine pollution is avoided.

The utility model discloses a nondestructive testing device for a pressure vessel, and relates to the technical field of pressure vessel detection. The device comprises a bottom plate, one end of the upper surface of the bottom plate is fixedly provided with a vertical plate which is vertically arranged, one side of the vertical plate is provided with two transverse plates which are horizontally arranged, a lead screw is jointly and rotatably arranged between the two transverse plates, a connecting plate which is horizontally arranged is inserted into the lead screw in a threaded mode, and the connecting plate is provided with a clamping groove. The end, away from the vertical plate, of the connecting plate is circular and penetrates through the vertical plate, a plurality of annularly-distributed detection probes are arranged on the inner wall of the penetrating position of the connecting plate, and a movable plate is slidably arranged on the upper surface of the bottom plate. When the driving motor drives the screw rod to work, the detection probe can automatically move downwards, manual detection can be avoided, the labor intensity of workers is reduced, and along with downward movement of the detection probe and rotation of the pressure vessel, surface detection of the pressure vessel body is more comprehensive, and the accuracy of measured data is further improved.

The utility model provides a kind of seal detector for ginseng and donkey-hide gelatin aluminium-plastic blister pack, belong to the technical field of pharmaceutical packaging quality detection, including support leg, the top of support leg is fixedly connected with workbench, the top of workbench is provided with conveyor belt, the top of workbench is provided with sorting device, the sorting device includes support frame, the side of workbench is provided with support frame, the side of support frame is provided with motor, the output shaft end of motor is fixedly connected with two-way threaded rod, the circumference of two-way threaded rod is threadedly connected with two-way threaded sleeve, the circumference of two-way threaded sleeve is fixedly connected with connecting plate, the utility model is detected by the sorting device being set in the top of workbench, when detecting that packaging seal is not enough, secondary heat seal is carried out by conveyor belt, avoid the time-consuming and labor-consuming disadvantages that staff still need to manually inspect packaging seal effect, improve work efficiency.

The embodiment of the present application discloses an image-based disease recognition method and device, wherein the method comprises: performing H feature fusions on the N first modal feature images and the M second modal feature images respectively, obtaining H fused modal feature images to be identified, classifying the H fused modal feature images to be identified according to preset disease categories, obtaining probability values ​​corresponding to each disease category in the preset disease categories, and the probability values ​​characterize the possibility of each category of disease in the preset categories. Thus, at least two modal feature images are fused, and the disease category is automatically detected based on the fused modal feature images, avoiding manual detection, and improving the accuracy of image disease category detection, that is, improving the efficiency of disease category detection, while also avoiding manual selection of images and manual annotation of lesions and lesion categories of images.

The invention provides a method for verifying correctness of a design rule check file. The method comprises the following steps: providing a test layout comprising a plurality of terminals; providing a preset DRC file, wherein the file comprises the definition of the electrical connection relation of different terminals in the test layout; providing a program language, applying the program language to a preset DRC file, and performing DRC verification on the test layout to output an electrical network identifier corresponding to each terminal; and judging whether the connection relation established in the preset DRC file is correct or not according to the electrical network identifier. According to the method for verifying the correctness of the design rule check file, the correctness of the connectivity rule in the DRC file is systematically verified, the design problem caused by the wrong connectivity relation of the DRC file is remarkably reduced, the design accuracy is improved from the source, the layout design deviation caused by the wrong connectivity of the DRC file is avoided, and the design efficiency is improved. And the correctness and reliability of the DRC file are ensured.

The application discloses a small wire coil sorting equipment motion precision detection device, method and equipment, and belongs to the technical field of power equipment. The device comprises: an image acquisition module, which is used for acquiring video sequence image information of the sorting process of the sorting equipment; a first vibration detection module, which is used for identifying first vibration information of the wire coil placed on the stack; an analysis module, which is used for analyzing that the sorting equipment has a fault risk in the case that the motion flexibility of the video sequence image information is lower than a set threshold and / or in the case that the first vibration information is higher than a first set vibration intensity; and a fault early warning module, which is used for generating a maintenance signal to perform targeted maintenance in a production gap. The scheme can acquire the video sequence image information and vibration information of the sorting process of the sorting equipment in real time, quickly find abnormal conditions of the sorting equipment, automatically give an early warning when an abnormality occurs, avoid unnecessary losses, and improve production efficiency and stability.

The invention discloses a vehicle window falling detection method and a vehicle intelligent security check system and device, and belongs to the field of man-vehicle mixed security check, the vehicle intelligent security check system comprises at least four cameras, the vehicle intelligent security check system is used for carrying out security check on a vehicle, the vehicle comprises four vehicle windows, and the vehicle windows are connected with the cameras. Each vehicle window is shot by one camera, and the vehicle window falling detection method comprises the steps that when a license plate on a vehicle is detected in a security check area, an image of the side body of the vehicle is acquired; the vehicle window identification model is established based on the image of the side body of the vehicle, the state of the vehicle window is determined according to the image of the vehicle window and the vehicle window identification model, and the state of the vehicle window of the vehicle is detected when the license plate on the vehicle is detected, so that manual detection of the vehicle window of the vehicle can be avoided, the security check efficiency can be improved, and the security check efficiency is improved. Therefore, the security check process is short in time consumption, and police resources can be saved.

The utility model discloses a kind of battery cell processing integrated equipment, belong to battery pack technical field.The equipment includes: frame body, battery cell conveying mechanism and patch film tearing mechanism, the battery cell conveying mechanism is movably connected in the frame body, for conveying battery cell along the first direction and the third direction, the battery cell detection mechanism is connected in the frame body, and along the second direction, located in the side of the battery cell conveying mechanism, for detecting the battery cell;The patch film tearing mechanism is connected in the frame body, and with the battery cell detection mechanism located in the same side of the battery cell conveying mechanism, along the second direction, the patch film tearing mechanism and the battery cell detection mechanism are spaced apart, the patch film tearing mechanism is used to tear off release film on the side of spacer, the spacer is attached on the battery cell, and release film on the other side of the spacer is torn off.

The invention provides a shale gas transmission station carbon emission monitoring method and monitoring system, and relates to the technical field of carbon emission monitoring, an area needing carbon emission monitoring is divided into a plurality of areas in advance, and corresponding monitoring methods are adopted for corresponding areas to measure the concentration value of carbon emission gas. Finally, the concentration values of the carbon emission gas of all the areas are subjected to fusion calculation, the total carbon emission amount of the whole area is calculated, the method is suitable for carbon emission monitoring of the shale gas transmission station, the problems of high inspection cost and large micro-leakage detection difficulty are solved, the carbon-containing gas of the gas transmission station is detected in an intelligent mode, the detection efficiency is improved, and the labor cost is reduced.

The invention discloses a compressive property detection device for tempered glass production, and belongs to the technical field of glass detection. The compressive property detection device for tempered glass production comprises a detection box, a partition plate is fixedly connected to the inner wall of the detection box, a bearing block is fixedly connected to one side of the partition plate, the bearing block is fixedly connected with the detection box, a detection assembly is arranged above the bearing block, and the detection assembly penetrates through the detection box and extends outwards. According to the compressive property detection device for tempered glass production, by arranging the detection assembly, when the compressive property of tempered glass is detected by the device, a residual gear can be automatically controlled to rotate, so that after a movable plate moves upwards by a certain distance, the movable plate moves downwards through the elastic force of a spring, and the compressive property of the tempered glass is detected; the impact piece is arranged on the bearing block, so that the impact piece can detect the compression resistance of the tempered glass on the bearing block, manual detection of workers is avoided, the labor intensity of the workers is reduced, and the detection efficiency of the tempered glass is improved.

An online detection method for a test board, wherein the test board is installed on an automatic test machine and is used to test an integrated circuit based on a signal provided by the automatic test machine. The test board includes multiple signal paths for electrically connecting to the integrated circuit to be tested so as to transmit a test signal to the integrated circuit. The online detection method includes: suspending the ends of the multiple signal paths used to connect to the integrated circuit, detecting whether each of the multiple signal paths has leakage, and determining that the test board is operating abnormally in response to leakage of at least one of the multiple signal paths. The online detection method is performed before testing each batch of integrated circuits.

The embodiments of the present disclosure disclose an image detection method, device, electronic device and computer-readable medium. A specific implementation of the method includes: based on the feature map of the image to be detected, generating a detection frame and label corresponding to the target object in the image to be detected, the label including the position information and category information of the target object; based on the category information, determining whether the image to be detected displays a first object of a first category and a second object of a second category; in response to determining that the image to be detected displays a first object and a second object, based on the position information corresponding to the first object and the second object respectively, determining the overlap rate of the detection frames corresponding to the first object and the second object respectively; based on the overlap rate, generating image detection information of the image to be detected, the image detection information is used to characterize whether the first object is placed on the second object in three-dimensional space. This implementation achieves improved detection efficiency.

The invention discloses a gelatin and protein intelligent package detection workbench and a using method, the gelatin and protein intelligent package detection workbench comprises a conveying workbench, a fixing frame is installed on the outer wall of the conveying workbench, during use, a banister brush is connected with a fixing plate in an inserted mode, a limiting rod is ejected out through the elastic force of a limiting spring to be clamped with the fixing plate, and then an outer package is placed above the conveying workbench; dust on the surface of an outer package is swept away through a banister brush, then the dust is sucked through a dust collector, an adjusting rod and a positioning frame are adjusted in a threaded mode, a baffle is pushed to move, limiting is conducted according to different outer package sizes, outer package deviation is avoided, the outer package is detected through a detector, and when abnormity is detected, a conveying workbench stops conveying, and the conveying workbench is used for conveying the outer package. And the push plate is driven by the air cylinder to push abnormal outer packages into the storage bin for centralized treatment, so that the gelatin and protein outer package detection operation is completed, and the gelatin and protein intelligent package detection workbench and the use method are completed.

According to the through-flow performance detection device and the through-flow performance detection method disclosed by the invention, the through-flow performance of a fan-shaped heat storage piece can be automatically detected by using the through-flow performance detection device, so that the blockage condition of an air preheater is detected, and manual detection is avoided. The through-flow performance detection device comprises a light source (21) and a light signal receiving and processing assembly. The light source (21) is arranged on one side of the mode heat exchanger and used for emitting light signals to the fan-shaped heat storage piece (10) so that the light signals can be transmitted in the ventilation holes of the fan-shaped heat storage piece (10). The optical signal receiving and processing assembly is arranged on the side, opposite to the light source (21), of the mode heat exchanger, directly faces the light source (21) and is used for detecting the intensity of an optical signal penetrating through the fan-shaped heat storage part (10), comparing the intensity of the optical signal with preset conduction optical signal intensity and calculating to obtain the through-flow performance of the fan-shaped heat storage part (10). And obtaining the through-flow performance of the mode heat exchanger.

The utility model discloses a back cover sealing performance detection device for square bottom valve bag production in the technical field of square bottom valve bag production, which comprises a working table, two threaded rods are rotatably connected on the working table, the two threaded rods are in transmission connection, two pressing plates are arranged between the two threaded rods, an inflation mechanism is arranged on the working table, and the inflation mechanism is connected with the two pressing plates. The inflation mechanism is located between the two pressing plates, a rotating column is rotationally connected to the workbench, a fixing frame is installed on the rotating column, a detection mechanism is installed on the fixing frame, a marking mechanism is arranged on the fixing frame, a reduction gearbox is installed on the lower side of the workbench, the rotating column is in transmission connection with the reduction gearbox, and a driving motor is installed on the workbench. The output end of the driving motor is in transmission connection with one of the threaded rods, so that the air tightness of the bag body is effectively detected, the production quality is guaranteed, the air leakage condition of the product in the production process is prevented, and the production quality is further guaranteed.

The invention discloses a spillway accumulation body blockage identification method based on deep learning, and belongs to the technical field of hydraulic engineering safety detection and intelligent operation and maintenance. According to the invention, a possible rock block accumulation condition is simulated through an indoor experiment, and a set of image acquisition system is established to shoot spillway discharge chute blockage caused by rock blocks in different forms. Besides, an improved DeepLabV3 + model is adopted as an image semantic segmentation algorithm, the improved model can meet the detection requirements in efficiency and precision, and a model performance analysis experiment shows the effectiveness of the established method. Furthermore, the trained model is integrated into an open platform, so that the model is promoted to be integrated into the equipment terminal to realize automatic detection. The method provided by the invention is mainly applied to an engineering operation and maintenance stage, and a tedious process of traditional manual inspection is avoided.