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

266results about How to "Accurate focus" patented technology

PCB defect detection method and system based on YOLOv8 network

The invention relates to a PCB defect detection method and system based on a YOLOv8 network, and belongs to the technical field of target detection. Collecting and preprocessing a PCB sample image data set for training a PCB defect detection model; inputting a to-be-detected image into the trained defect detection model to obtain a detection result; the to-be-detected image is generated by collecting and processing image data of the to-be-detected PCB; wherein the defect detection model comprises a trunk network, a neck network and a head network, and the trunk network extracts features through a mobile reverse bottleneck convolution module and a C2f module to generate an intermediate feature map; and the neck network performs splicing fusion on the middle feature map to generate a spliced feature map, the head network performs re-weighting on the spliced feature map through a convolution kernel attention fusion module to generate a third feature map, and then the detection module outputs a detection result. The method not only improves the precision of the defect detection model in detecting the features of the tiny target, but also improves the detection speed and generalization ability, and reduces the calculation cost and complexity at the same time.
Owner:SUZHOU CITY UNIV

Method for evaluating carbon sink increase potential of offshore area

The invention relates to the technical field of environment and ecological engineering, in particular to a method for evaluating the carbon sink increase potential of an offshore area, which comprises the following steps of: S1, acquiring multi-dimensional marine environment data to form a preliminary data set; s2, deeply analyzing the carbon sink increase characteristics and the long-term change trend, and identifying factors influencing the offshore carbon sink pattern; s3, constructing a static relation model between the carbon sink pattern and the factors; s4, constructing a dynamic relation model of the carbon sink pattern; and S5, combining the static relation model with the dynamic relation model, and carrying out comprehensive evaluation so as to determine the carbon sink space bearing capacity of the offshore area. And S6, determining the carbon sink increasing potential of each region based on the space bearing capacity evaluation result obtained in the S5. According to the method, the carbon sink capacity of the offshore area is evaluated by integrating the static model and the dynamic model, and more accurate carbon sink management and prediction can be provided, so that scientific policy making and resource optimization are supported, and the environmental protection effect is enhanced.
Owner:FIRST INSTITUTE OF OCEANOGRAPHY MNR

Rolling bearing fault diagnosis method based on double fusion attention mechanism

The invention discloses a rolling bearing fault diagnosis method based on a double fusion attention mechanism, and the method comprises the steps: collecting a vibration signal, processing the vibration signal to form a two-dimensional time-frequency diagram, and dividing the formed two-dimensional time-frequency diagram into a data set; dual fusion attention based on channel attention and space attention is provided by improving a traditional mixed attention mechanism; constructing a dual fusion attention-multi-scale feature network fault diagnosis model based on dual fusion attention, and training the constructed dual fusion attention-multi-scale feature network fault diagnosis model through a data set; and finally, inputting a rolling bearing signal under a strong noise background into the trained double fusion attention-multi-scale feature network fault diagnosis model to obtain a fault diagnosis result. According to the invention, the problem of low identification accuracy in a complex background in the existing monitoring and diagnosis of the rolling bearing of the machinery is solved.
Owner:XIAN UNIV OF TECH

Scraped car nonferrous metal target detection method based on attention twin network and multi-source image fusion

The invention belongs to the technical field of image processing, and discloses a scraped car nonferrous metal target detection method based on an attention twin network and multi-source image fusion. According to the method, a scraped car nonferrous metal target detection model is built based on an improved yov8 model, a backbone network with a twin network structure is built in the model, an attention mechanism is introduced into the backbone network to form an attention twin network, and meanwhile, multi-source image input of visible light and infrared thermal imaging channels is fused, so that the target detection accuracy is improved. When nonferrous metal in a scraped car mixture is detected, the method can be focused on an area with nonferrous metal features more accurately, and for nonferrous metal parts which are irregular in shape or mixed with other materials, the twin network is focused to improve the recognition precision of a target by learning the unique feature mode of the nonferrous metal parts. The recovery accuracy and efficiency of the scraped car non-ferrous metal broken objects are improved.
Owner:JIANGSU JIAAO SCRAPPED CAR DISMANTLING CO LTD

Point switch part detection method and equipment based on YOLOv8 model and medium

The invention discloses a point switch part detection method and device based on a YOLOv8 model and a medium, and the method comprises the steps: marking a target part in a point switch part image, and generating a target image; the method comprises the following steps: replacing an original backbone network darknet53 of a YOLOv8 model with a Swin transfer network, and introducing a residual attention module into the Swin transfer network; the method comprises the following steps of: constructing an improved YOLOv8 model by combining a spatial pyramid pooling layer on the basis of a Swin transformer network and replacing an original loss function CIoU of the YOLOv8 model with a new loss function Focal-EIoU at the same time; and inputting the target image into the improved YOLOv8 model, and generating a prediction result. And accurate detection of the target part is realized based on the detection result output by the improved YOLOv8 model.
Owner:LANZHOU JIAOTONG UNIV

Underwater image detection system and method based on YOLOv8s model

The invention relates to an underwater image detection system and method based on a YOLOv8s model, and the system comprises an underwater image collection and preprocessing subsystem which is used for collecting underwater image data and carrying out the preprocessing; the target detection subsystem is used for carrying out target detection by adopting an improved YOLOv8s model, and the improved YOLOv8s model is used for obtaining a feature map by adopting a mode of combining a denoising mechanism and a dynamic adjustment receptive field mechanism based on the preprocessed underwater image data, carrying out feature enhancement by adopting a dual attention mechanism based on the feature map, and carrying out target detection by adopting an improved YOLOv8s model; performing feature fusion and detection to obtain a target detection result; the performance monitoring and evaluation subsystem is used for monitoring and evaluating the target detection result; and the detection result display and output subsystem is used for outputting and displaying the target detection result. Compared with the prior art, the method has the advantages of improving the depth and precision of feature extraction, improving the underwater image detection performance and the like.
Owner:SHANGHAI MARITIME UNIVERSITY

Voice noise reduction system in multi-noise environment

The invention discloses a voice noise reduction system in a multi-noise environment, and particularly relates to the technical field of voice noise reduction, which comprises a basic division module for dividing voice data into a plurality of basic voice segments with the same duration; the rationality analysis module judges whether segmentation points of adjacent fragments are reasonable or not, and if the segmentation points are not reasonable, the optimization marking module searches for new segmentation points for optimization; the loop module repeatedly verifies the optimization result until all the voice segments are reasonably segmented; the noise reduction module extracts voice and noise features, and performs noise reduction processing by using a noise reduction strategy selection model; the recombination module recombines the voice segments after noise reduction into complete voice output; according to the invention, the voice signal is divided into a plurality of segments, the most suitable noise reduction algorithm can be matched for each segment according to the noise feature of each segment, and the method can cope with a more complex and unstable noise environment through a dynamically adaptive noise reduction strategy, and guarantees that the voice quality is better improved in various scenes.
Owner:HANGZHOU HUA TING TECH CO LTD

Liver tumor segmentation method based on SCAF-TransUNet

The invention discloses a liver tumor segmentation method based on SCAF-TransUNet, and the method comprises the steps: firstly, segmenting a liver image into semantically related superpixel regions through SLIC superpixel preprocessing, enabling a model to be more accurately focused on a tumor and other key regions, reducing the calculation redundancy, and improving the efficiency and precision of feature extraction; secondly, a CECA module introduced in jump connection replaces a traditional full connection layer through one-dimensional convolution, the attention mechanism between channels is simplified, capture of the channel dependency relation is enhanced, and meanwhile the feature extraction precision is kept; finally, the FPN is added in the decoder, and the fusion capability of the multi-scale features is further enhanced. According to the FPN, feature maps with different resolutions are fused layer by layer, so that the model can effectively combine global semantic information and local detail features before up-sampling, and the processing capacity for complex liver boundaries and small tumors is improved. Finally, the improvements significantly improve the accuracy and robustness of the liver tumor segmentation task.
Owner:SHENYANG UNIVERSITY OF TECHNOLOGY

Pathology image cell segmentation method based on U-Net model

The invention relates to a pathological image cell segmentation method based on a U-Net model, and belongs to the field of deep learning and medical image segmentation. According to the method, an improved U-Net model is adopted, and in the preprocessing stage, original point mark data is converted into a continuous density map. A multi-scale attention module is added in a decoder stage of the network. The module effectively combines multi-scale feature fusion and a soft attention mechanism, global and local features in an image can be comprehensively captured, and the expression capability of key cell features is remarkably enhanced, so that the cell segmentation precision is improved. Besides, a pixel channel fusion module is added between layers of the decoder, and the module further enhances the detail recognition capability of the model by integrating local information and pixel-level attention into a channel attention mechanism. According to the method, the Ki-67 positive cells, the Ki-67 negative cells and the tumor infiltrating lymphocytes in the IHC-dyed pathological image can be effectively segmented.
Owner:KUNMING UNIV OF SCI & TECH

Spaceborne sliding spotlight SAR (Synthetic Aperture Radar) data processing method based on variable sampling initiation

The invention relates to a variable sampling start-based satellite-borne sliding spotlight SAR data processing method, which comprises the following steps of: carrying out distance direction blocking on echo data of variable sampling start, carrying out Fourier transform on sub-block data along the distance direction, multiplying by a phase compensation function, and carrying out sampling start alignment; performing two-step azimuth frequency domain aliasing removal on the sub-block data after sampling initial alignment; performing two-dimensional frequency domain matched filtering on the sub-block data after the azimuth frequency domain aliasing is removed; carrying out resampling on the sub-block data subjected to two-dimensional frequency domain matched filtering; and splicing the resampled sub-block data to obtain an imaging result of the whole imaging scene. According to the method, sampling initial alignment is carried out through a distance frequency domain azimuth time domain phase compensation function, zero padding does not need to be carried out on echo data, and the data processing difficulty is reduced; the focusing quality is improved by eliminating azimuth frequency domain aliasing, two-dimensional frequency domain matched filtering and two-dimensional frequency domain resampling.
Owner:NO 63921 UNIT OF PLA

Multifunctional optical lens testing lens device

The invention relates to the technical field of lens testing, and discloses a multifunctional optical lens testing lens device which comprises a connecting frame. A casing; a lens body; the positioning assembly is used for fixing the position when the lens body is detected; the detection assembly is used for carrying out multidirectional detection on the lens body; the detection assembly comprises an air pressure detection part, an impact detection part and a vibration detection part; and a driving assembly. According to the multifunctional optical lens testing lens device, multi-direction detection of the lens can be realized through the arranged detection assembly, and multi-direction synchronous detection in vibration, impact, air tightness, waterproofness and high-temperature environments is realized, so that each detection is in a linked state, the detection effect of the lens in different high-complexity environments is improved, and the detection efficiency is improved. And the whole detection process is carried out in one device, and single position conversion is not needed, so that a high-intensity environment is provided for the test of the lens, and the stability of the lens is finally detected.
Owner:JILIN JUCHENG ZHIZAO PHOTOELECTRIC TECH CO LTD

Infrared weak and small target detection method and system, electronic equipment and storage medium

The invention provides an infrared weak and small target detection method and system, electronic equipment and a storage medium, and belongs to the technical field of target detection, and the method comprises the steps: improving a YOLOv8 model for the features of an infrared weak and small target image; and performing target detection on the infrared weak and small target image by using the improved YOLOv8 model. According to the invention, a stronger infrared weak and small target detection capability is provided for the YOLOv8 model, and the problem of target detection precision bottleneck of a traditional model in a complex scene is effectively solved.
Owner:CHENGDU UNIV OF INFORMATION TECH

Photoetching machine for automatic switching of high multiplying power and low multiplying power

The utility model relates to a photoetching machine for automatically switching high multiplying power and low multiplying power, and belongs to the technical field of laser direct writing equipment. According to the utility model, by arranging the automatic switching photoetching system, not only can automatic switching of objective lenses with different multiplying powers be realized, but also accurate photoetching, alignment and focusing can be realized, so that pollution to the environment of an optical machine room caused by manual switching of the objective lenses by a user is avoided, and the photoetching process is not influenced; and meanwhile, real-time focusing alignment can be carried out through the focusing system, so that the accuracy of the photoetching process is further improved.
Owner:JIANGSU YSPHOTECH INTERGRATED CIRCUIT EQUIP CO LTD

High squint SAR imaging processing method under Doppler frequency distance time varying

The invention relates to a high squint SAR imaging processing method under Doppler frequency distance time varying. The method comprises the following steps: firstly, carrying out linear walking correction and distance compression according to a squint angle; then distance partitioning and azimuth upsampling are carried out according to the pulse repetition frequency, the instantaneous Doppler bandwidth and the Doppler frequency time-varying quantity along with the distance, azimuth spectrum ambiguity caused by the change of the Doppler center frequency along with the slope distance is eliminated through azimuth spectrum extension, and sub-block splicing is carried out after upsampling of all sub-blocks is completed; carrying out azimuth space-variant resampling in a two-dimensional frequency domain, and eliminating azimuth space-variant in a range gate; then consistent compression and stot interpolation are carried out, and two-dimensional accurate focusing is completed; and finally, correcting image distance position time shift caused by linear walking correction, and intercepting an effective imaging area to obtain a focused SAR image. According to the method, the Doppler spectrum fuzzy problem caused by Doppler frequency distance time variation can be effectively eliminated, so that effective application of a traditional large squint algorithm is ensured, and a correctly focused SAR image is obtained.
Owner:XIAN INSTITUE OF SPACE RADIO TECH

Temperature detection device and temperature detection system for heat source

The utility model relates to a temperature detection device and a temperature detection system of a heat source. The device for detecting the temperature of the heat source comprises: a moving stage; the thermal infrared imager and the camera module are arranged on the movable objective table, the light inlet surface of the thermal infrared imager and the light inlet surface of the camera module face the heat source, and the distance between the thermal infrared imager and the heat source is the same as that between the camera module and the heat source; the driving module is in driving connection with the movable objective table so as to drive the movable objective table to move towards or away from the heat source; the controller is respectively connected with the thermal infrared imager, the camera module and the driving module; by adopting the device, the objective table can be driven by the driving module to adjust the position of the heat source, the thermal infrared imager is assisted by the camera module to focus the heat source, and the image of the heat source is shot to obtain the temperature of the heat source, so that accurate focusing of the thermal infrared imager can be realized without setting a reference object, accurate temperature measurement of the heat source is realized, and the working efficiency is improved. The problem of low heat source temperature detection accuracy is effectively solved.
Owner:CHINA TOBACCO GUANGDONG IND

Secondary reflection receiver concentrating solar heat collection system and design method

The invention relates to the technical field of solar photo-thermal utilization, in particular to a secondary reflection center receiver concentrating solar heat collection system and a design method thereof. The system is composed of a heliostat field composed of a plurality of heliostats which are symmetrically or approximately symmetrically arranged, an inclined plane secondary reflector installed on a high tower and a receiver which is obliquely installed close to the ground. Each heliostat is accurately controlled through a tracking system, and sunlight is reflected and focused to a common focus located at the high position of the right south of a heliostat field. Afterwards, the light rays are further reflected by the secondary reflector and guided to the receiver, and efficient light energy collection and heat energy conversion are achieved. Through accurate tracking and focusing of the heliostat and the guiding effect of the secondary reflector, the system can efficiently gather sunlight to the receiver, and the light energy collection efficiency is improved. The heliostat field is arranged symmetrically or approximately symmetrically, so that the heliostat field is attractive, shadow shielding can be effectively reduced, and the overall condensation effect is improved.
Owner:UNIV OF SCI & TECH OF CHINA

Three-dimensional laser post-ionization-secondary neutron particle mass spectrometer

The invention discloses a three-dimensional laser post-ionization-secondary neutron particle mass spectrometer which comprises a vacuum pool, a sample introduction system, a primary ion emission system, a three-dimensional laser post-ionization system, an ion optical system, a time-of-flight mass spectrometer, an observation system and a computer control system. By adjusting the wavelength, the frequency and the energy value of the laser, resonance between the energy of laser photons and the electron energy level of target molecules can be realized to realize selective ionization of substances, and the method has extremely high element, nuclide and molecule selectivity, can provide the sensitivity of an instrument, and can be used for mass spectrometry. The device can be applied to single-cell imaging analysis test of lipid, metabolites, small-molecule drugs and part of elements with the molecular weight smaller than 1000 Da, the problems of space metabolome small-molecule metabolite test and ultrahigh spatial resolution imaging are solved, and the device can be independently used as an SIMS when laser post-ionization is not used.
Owner:SHANGHAICHEMLABINSTRUMENTCO LTD

Image recognition method based on bionic vision and fluctuation enhancement

The invention belongs to the technical field of image recognition, and particularly relates to an image recognition method based on bionic vision and fluctuation enhancement, and the method comprises the steps: building a bionic vision network model based on a multi-scale Gabor filter bank and a similarity measurement-based adaptive enhancement mechanism; establishing a pre-training module based on self-supervised learning, and pre-training the bionic vision network model; establishing a visual dynamic attention module, adding the visual dynamic attention module into the bionic visual network model, performing fluctuation enhancement and attention weighting on output features of the bionic visual network model, and fusing feature representations after fluctuation enhancement and attention weighting; combining supervision comparison loss, balance logarithm loss and focus loss to form a comprehensive loss function, and training the bionic vision network model; and performing image recognition by using the trained bionic visual network model. According to the method, the accuracy and robustness of image recognition and the adaptability to complex scenes are remarkably improved.
Owner:SHANDONG TONGGUANG ELECTRONICS CO LTD

High-squint two-dimensional space-variant motion compensation SAR imaging method based on actual trajectory

The invention relates to a high-squint two-dimensional space-variant motion compensation SAR imaging method based on an actual trajectory, and the method comprises the steps: obtaining echo data s0 (tr, eta) according to a pre-constructed nonlinear trajectory geometric model of a carrier platform of a high-squint SAR imaging system; performing range pulse pressure processing on the echo data s0 (tr, eta) to obtain a range frequency domain echo signal s1 (fr, eta) after range pulse pressure; performing non-space-variant phase compensation on the distance frequency domain echo signal s1 (fr, eta) after the distance pulse compression to obtain a compensated signal s2 (fr, eta); performing range space-variant correction on the compensated signal s2 (fr, eta) to obtain a corrected range frequency domain echo signal s7 (fr, eta); and azimuth space-variant correction is carried out on the corrected distance frequency domain echo signal s7 (fr, eta) to obtain a corrected azimuth echo signal # imgabs0 #, and the corrected azimuth echo signal # imgabs1 # is converted into an SAR image through two-dimensional Fourier transform. According to the scheme, the space-variant of the envelope and the phase in the azimuth direction is eliminated, the motion error of the azimuth space-variant is corrected, more accurate imaging focusing is achieved, and high precision and efficiency are achieved.
Owner:XIDIAN UNIV

Method and system for evaluating dynamic and thermal stability of power supply cable

The invention relates to the technical field, in particular to an evaluation system and evaluation method for dynamic thermal stability of a power supply cable, and the method comprises the steps: determining a short-circuit detection point of the power supply cable based on the state of the power supply cable; determining the maximum loss point of the buried power supply cable based on the soil thermal conductivity of the buried power supply cable in a preset time period and the buried depth change rate of the power supply cable in the preset time period, and determining the maximum loss point of the buried power supply cable based on the dust accumulation thickness of the exposed power supply cable and whether the completely exposed power supply cable has cracks or not. Determining a maximum loss point of the exposed laid power supply cable; and performing a short circuit stability verification test on the short circuit detection point of the power supply cable, and determining whether the dynamic thermal stability of the power supply cable is qualified based on whether the short circuit detection point of the power supply cable is damaged or deformed after the test. According to the invention, the accuracy of short-circuit detection point analysis is improved, so that the energy waste is reduced, and the energy utilization efficiency is improved.
Owner:HUBEI ELECTRIC POWER CO JINGZHOU POWER SUPPLY CO +1

Welding device and method for saxophone processing

The invention provides a welding device and method for saxophone machining, and relates to the technical field of saxophone machining. The welding device comprises a driving mechanism, a laser welding mechanism, a supporting mechanism, a smoke discharging mechanism, a control mechanism and a protection mechanism; the laser welding mechanism is mounted on the driving mechanism; the supporting mechanism is installed on the top of the driving mechanism and used for installing a welding tool. The smoke discharging mechanism is installed on the rear side of the driving mechanism and used for sucking smoke generated during welding. The control mechanism is mounted on the driving mechanism; the protection mechanism is mounted on the front side of the driving mechanism; the distance between the laser welding head and the saxophone is automatically adjusted, it is guaranteed that the saxophone is located at the accurate focal length when different positions of the saxophone are welded, and the welding quality of the saxophone is improved; the saxophone laser welding device solves the problems that due to the fact that a laser welding head is usually fixedly installed, when different positions of a saxophone are welded, the focal length is prone to being inaccurate, and the welding quality of the saxophone is reduced.
Owner:BUFFY MUSICAL INSTRUMENTS (JIASHAN) CO LTD

Optical system and optical apparatus including the same

The invention discloses an optical system and optical equipment comprising the optical system.The optical system comprises a lens barrel, a lens set and a spacing element set, the lens set and the spacing element set are arranged in the lens barrel, and the lens set sequentially comprises a first lens, a first quarter-wave plate, a reflective polarization element and a second lens from the first side to the second side along the optical axis, the first lens has positive focal power, and the second lens has positive focal power; and an optical element group consisting of the first quarter-wave plate, the reflective polarizing element and the second lens has positive focal power. The spacing element group comprises a first spacing element which is arranged between the first lens and the second lens and abuts against the second side face of the first lens. The optical system satisfies the following conditions: 0.05 lt; d < 1s >-d < 0s > / C < 1lt >; d1s is the maximum inner diameter of the first side face of the first spacing element in the direction perpendicular to the optical axis, d0s is the maximum inner diameter of the first side end face of the lens barrel in the direction perpendicular to the optical axis, and CT1 is the center thickness of the first lens on the optical axis.
Owner:ZHEJIANG SUNNY OPTICAL CO LTD

Performance enhancement method for automatic driving system based on expert hybrid architecture

The invention belongs to the technical field of software engineering, particularly relates to an automatic driving system performance enhancement method based on an expert hybrid architecture, and aims to solve the core problems that an end-to-end automatic driving system is confronted with semantic fuzziness to cause unreliable decision, multi-task interference hinders optimization planning, too long reasoning delay increases driving risks and the like. According to the method, an ExpertAD framework is provided, task key features are amplified through a perception adapter (PA), and the relevance of scene context understanding is guaranteed; related driving tasks are dynamically activated through a sparse expert mixture (MoSE), and task interference is minimized; and in combination with a customized training loss function, collaborative optimization of planning effectiveness and reasoning efficiency is realized. Experiments show that compared with an existing method, the method has the advantages that the average collision rate is reduced by 20%, the reasoning delay is reduced by 25%, higher multi-skill planning capacity is achieved in rare scenes (such as accident handling and first-aid vehicle avoiding), and good generalization is achieved for unseen urban environments.
Owner:FUDAN UNIVERSITY

Automatic focusing method and device, storage medium and electronic equipment

The invention provides an automatic focusing method and device, a storage medium and electronic equipment. The method comprises the steps of determining a current object distance based on a current angle and a current height of a camera; determining object distance related parameters in a zoom curve template of the camera based on the current object distance so as to determine a target zoom curve at the current angle; and performing automatic focusing based on the target zoom curve. The current object distance can be quickly determined according to the current angle of the camera, then the target zoom curve corresponding to the current object distance is constructed, the zoom motor and the zoom motor are controlled according to the target zoom curve, and focusing is quickly and accurately completed.
Owner:CHENGDU POWER VIEW SCIENCE & TECHNOLOGY CO LTD

Composite material laser welding equipment and welding method

The invention discloses composite material laser welding equipment and a welding method, and belongs to the field of laser printing, the composite material laser welding equipment comprises a base plate, a wire feeding mechanism, a rotary shearing mechanism, a rolling mechanism and a laser heating mechanism are installed on the base plate, the laser heating mechanism comprises a first dovetail groove sliding table and a second dovetail groove sliding table, and the second dovetail groove sliding table is vertically and fixedly installed on the base plate; the first dovetail groove sliding table is located below the second dovetail groove sliding table, a first connecting plate is fixedly arranged on a carriage of the second dovetail groove sliding table, the first dovetail groove sliding table is fixedly installed on a second connecting plate in an obliquely downward mode, and the end, close to the rotary shearing mechanism, of the second connecting plate is hinged to the first connecting plate through a first connecting rod. And the other end of the second connecting plate is connected with the first connecting plate through a telescopic adjusting structure, a laser head is fixedly arranged on a dragging plate at the bottom of the first dovetail groove sliding table, the angle, height and focusing position of a laser beam can be controlled, and the welding requirements of composite materials of different shapes and sizes are met.
Owner:HANGZHOU XINJIN ADDITIVE TECH CO LTD

Laser cutting equipment for machining cutting die and cutting die

The invention relates to the technical field of cutting die laser cutting, in particular to laser cutting equipment for machining a cutting die and the cutting die, the laser cutting equipment for machining the cutting die comprises a shell, a cutting positioning mechanism is installed in the shell, the cutting positioning mechanism comprises an illuminating lamp, the illuminating lamp is fixedly installed in an inner cavity of the shell, and a mounting groove is formed in the shell. Two supporting plates are fixedly mounted in the mounting groove, the first electric track is fixedly mounted at the tops of the two supporting plates, a first sliding block is slidably mounted in the first electric track, and a second sliding block is slidably mounted on the surface of the second electric track. Through the arrangement of the cutting mechanism, the surface of a material can be ground in time in the laser cutting process, impurities, rust and uneven parts on the surface of the material can be removed through grinding, a laser beam can be more accurately focused on the surface of the material, the cutting edge is more tidy, and the machining requirement for higher precision is met.
Owner:YUE WOHING LASER MOULP SHENZHEN

Flight shooting detection system of camera

The invention discloses a flying shooting detection system for a camera, and particularly relates to the technical field of flying shooting detection. The system comprises an image acquisition and preprocessing module used for optimizing ambient light and image quality, and an image processing and analysis module used for carrying out feature recognition and deconstruction on an image by using an advanced algorithm. The data processing intelligent analysis module is used for comprehensively processing and analyzing multi-source data; and the system integration intelligent control module is used for realizing automatic and intelligent control. The self-adaptive system control module is designed to dynamically adjust system parameters according to real-time data, the intelligent interaction interface module provides a visual user interface, remote operation and monitoring are achieved through the remote monitoring and control module, and the automatic calibration and maintenance module ensures that the system is stable and reliable; the system can provide high-quality image data under various environmental conditions, the detection efficiency and accuracy are improved, meanwhile, automatic operation is achieved, manual intervention is reduced, and the working efficiency and safety are improved.
Owner:B&D AUTOMATION (SHENZHEN) TECH CO LTD

Millimeter wave radar and camera combined multi-target deblurring monitoring method and system

The invention discloses a millimeter-wave radar and camera combined multi-target deblurring monitoring method and system, and relates to the technical field of target tracking, and the method comprises the steps: erecting a millimeter-wave radar and a camera on the same vertical plane for monitoring; a checkerboard is used for recording the corresponding focusing time of the camera under different distances, and the function relation between the target distance and the focusing time under different focal length segments is obtained; distance, speed and angle information of multiple targets is obtained according to millimeter wave radar detection, tracks of the multiple targets are obtained, a multi-target tracking algorithm is used for conducting unified prediction and management on the tracks, and a track list is obtained; circularly selecting targets in different periods, and selecting an unfocused fuzzy target in the current period for monitoring; determining a corresponding focal length section according to the distance of the fuzzy target, finally calculating the focusing time according to the function relation, and adjusting the camera to the corresponding focal length, so that the imaging of the current fuzzy target is clear. According to the invention, accurate focusing of a plurality of targets in different distance intervals is realized.
Owner:BEIHANG UNIV

Laser cutting equipment for metal pipe fitting production

The invention relates to the technical field of laser cutting devices, in particular to laser cutting equipment for metal pipe fitting production. Comprising a first fixed shell; the double-shaft motor is fixedly connected to the first fixing shell; the multi-stage telescopic rod is rotationally connected to the first fixing shell, a blind hole is formed in the telescopic end of the multi-stage telescopic rod, and a second fixing shell is slidably connected into the blind hole in the telescopic end of the multi-stage telescopic rod; the supporting piece is fixedly connected to the second fixing shell; the rotating shaft is rotationally connected to the supporting piece, and the first connecting rod is provided with a laser cutter; and the plugging block is connected to the second fixing shell in a sliding manner. In the process of fixing the device and the corrugated pipe, the relative positions of the telescopic end of the multi-stage telescopic rod, the second fixing shell and the plugging block are changed, so that the distance between the laser cutter and the inner wall of the corrugated pipe is changed, a laser beam can be correctly focused on a cutting surface, additional measurement is not needed, and the working efficiency is improved. And the cutting efficiency of the metal pipe fitting is improved.
Owner:HEBEI XINFANGSHENG PIPELINE EQUIP CO LTD

Intelligent robot for flower and fruit thinning of grapes and using method

The invention relates to the field of agricultural equipment, in particular to an intelligent robot for flower and fruit thinning of grapes and a using method.The intelligent robot comprises a grape trellis structure and a digital display control panel, a moving vehicle is movably arranged on the upper side of the grape trellis structure, a plurality of mechanical arms are arranged on one side of the moving vehicle, and image recognizers are arranged between the mechanical arms; each mechanical arm is provided with a shearing mechanical claw, one side of the moving vehicle is further provided with a lifting adjusting structure used for driving the mechanical arms and the image recognizer to ascend and descend vertically, and the moving vehicle is provided with a horizontal driving mechanism used for driving the lifting adjusting structure to rotate in the horizontal direction to be converted to the two sides of the grape trellis structure. The moving trolley is arranged on the grape trellis structure and matched with the lifting adjusting structure to move the mechanical arm and the image recognizer up and down, the cutting distance can be controlled more accurately through the shearing mechanical claw, long-time adjustment is not needed, in addition, face cutting treatment in the up-down direction is conducted in cooperation with a climbing rope on the grape trellis structure, and the working efficiency is improved. And grid type accurate focusing can be realized.
Owner:NINGXIA INST OF AGRI PROD QUALITY STANDARDS & TESTING TECH (NINGXIA AGRI PROD QUALITY MONITORING CENT)