192results about How to "High-precision detection" patented technology

The invention relates to the technical field of cable maintenance equipment adjustment, in particular to adjusting and conveying equipment applied to pipeline buried cable maintenance and detection equipment, the adjusting and conveying equipment comprises a first conveying frame, a second conveying frame and optical detection equipment, and a lateral fixing support is fixedly assembled between the first conveying frame and the second conveying frame. According to the adjusting and conveying equipment applied to the pipeline buried cable maintenance and detection equipment, an unmanned operation mode is adopted to drive the equipment in a pipeline, and a worker does not need to enter the pipeline, so that the maintenance difficulty and cost are greatly reduced; the maintenance and detection equipment is controlled to translate in the pipeline in an unmanned operation mode, so that the detection and conveying efficiency can be greatly improved; the first conveying frame and the second conveying frame on the two sides are fixedly connected through the lateral fixing support, and the structural strength and stability of the whole conveying equipment can be greatly improved.

The invention discloses an underwater acoustic intelligent spectrum sensing method fusing multi-modal data and application, and belongs to the technical field of ocean Internet of Things. The method comprises the following steps: firstly, constructing an underwater wireless sensor network model, obtaining a multi-modal database of underwater acoustic signals, and obtaining picture data in a frequency domain through wavelet transform after a system obtains time sequence data of the underwater acoustic signals; secondly, extracting high-quality features of the time series data through an unsupervised learning denoising auto-encoder; and finally, a Mu-YOLO perceptron of a parallel double BackBone fusion multi-modal technology is constructed, and one BackBone takes DSC module depth separable convolution as a main part to capture key time characteristics. And the other BackBone captures key spatial features by taking CSPDarknet as a main part, and realizes high-precision spectrum sensing by fusing diversified and multi-layer features of multi-modal data.

The invention belongs to but is not limited to the technical field of PCBA defect detection, and discloses a PCBA AI defect detection item demand response method and system, which adopts multi-scale long-range fusion, context information, super-resolution and block detection to improve a target detection algorithm, and performs detection and identification of a tiny target. Identifying the fine granularity of the target by adopting a contextual information and depth feature matching method; 3D point cloud and X-ray perspective are adopted, a multi-sensor fusion detection frame is used, and invisible defect detection is carried out. According to the method, AI technologies such as deep learning are utilized, the detection precision of small defects on the PCBA board is effectively improved, and missing detection and false detection are reduced. The AI technology can automatically identify and learn defect features, and efficiency and accuracy are significantly improved. The AI model can optimize the self algorithm through continuous learning, so that the detection system can adapt to different PCBA boards and production environments, and the universality and flexibility of the detection system are enhanced.

The utility model discloses a detection device capable of multidirectional clamping detection, which belongs to the technical field of annular object detection and comprises a workbench, a support column arranged at the bottom of the workbench, a control panel, a support and a center table arranged at the top of the workbench, a defect box and a finished product box respectively arranged on two sides of the support. A detector is arranged on the support, a motor is arranged in the center table, and a main bevel gear is arranged at the output end of the motor. According to the detection device capable of multi-directional clamping detection, a motor is started through a control panel, so that a main bevel gear rotates, two first lead screws and two second lead screws synchronously rotate, the first lead screws and the second lead screws rotate to drive an extension rod to slide in a main rod, and therefore multi-directional clamping of an annular product is achieved; the movement of the annular product in the detection process is avoided, and the rubber pads on the clamping plates effectively avoid the deformation of the annular product due to excessive stress, so that the subsequent accurate detection is facilitated.

The present invention discloses a vehicle collision detection method based on vision, an intelligent terminal and a storage medium, the method comprising: detecting vehicles in a traffic monitoring video, framing the vehicles in the traffic monitoring video by a rectangular frame, and outputting the vehicle rectangular frame and the vehicle number; tracking the detected vehicles, judging whether the vehicle rectangular frames between the vehicles overlap, and extracting the acceleration, trajectory and direction change of the vehicles; when the vehicle rectangular frames between the vehicles overlap, obtaining an abnormality index according to the extracted acceleration, trajectory and direction change of the vehicles, judging whether the abnormality index is greater than a preset threshold; when the abnormality index is greater than the preset threshold, it is judged as a vehicle collision accident. The present invention comprehensively considers the three factors of abnormal acceleration, abnormal trajectory and abnormal direction of the vehicle to achieve the purpose of vehicle collision accident detection, and can quickly and accurately detect vehicle collision accidents in the scene.

The invention discloses a navigation radar guided photoelectric unmanned ship horizontal plane target detection and positioning method, which comprises the following steps: carrying out zero calibration on a pose measurement device, a navigation radar and a photoelectric device which are deployed on an unmanned ship, and establishing an unmanned ship body coordinate system; obtaining the pose data of the unmanned ship based on the pose measurement equipment; adjusting the pitch angle of the photoelectric equipment based on the unmanned ship rolling data or adjusting the azimuth angle of the photoelectric equipment based on the unmanned ship pitching data, so that the sea level is located in the middle of the picture of the photoelectric equipment; the optoelectronic device receives the orientation of the to-be-tracked target detected by the navigation radar, the navigation radar guides the optoelectronic device to adjust the azimuth angle, and a photoelectric target detection module of the optoelectronic device detects the to-be-tracked target; the photoelectric device locks a to-be-tracked target, and the distance between the unmanned ship and the to-be-tracked target is measured through laser ranging; and determining the longitude and latitude of the to-be-tracked target based on the distance and the unmanned ship pose data. According to the method, the detection accuracy of the unmanned ship on surrounding targets is improved.

The invention discloses a self-adaptive crack identification and quantification method for the periphery of an open stope. The method comprises an image preprocessing step and a crack identification step. According to the method, aiming at the complexity of an open stope environment, a Gaussian pyramid is adopted to carry out multi-scale analysis on an image, and gray scale equalization is realized through gamma transformation so as to adapt to crack identification requirements under different illumination conditions; according to the crack recognition part, an improved difference entropy is used for optimizing a local threshold segmentation algorithm, high-efficiency and high-precision detection of the stope crack is achieved, the segmentation threshold can be dynamically determined according to gray level distribution of an image local area, and the accuracy and robustness of crack recognition are effectively improved; according to the method, the automation level of crack detection is greatly improved, powerful technical support is provided for safety management and risk early warning of the open stope, and the method has important practical application value and wide market prospects.

The invention belongs to the technical field of computer vision, and particularly discloses a monocular 3D object detection method for realizing depth enhancement based on a visual basic model, electronic equipment and a readable storage medium, and the method comprises the steps: S1, building a data set: employing a monocular camera to collect a pavement scene, and obtaining an RGB image in the pavement scene; s2, image preprocessing: preprocessing the RGB image for subsequent feature extraction and depth estimation; s3, performing feature extraction by adopting a dual-backbone network: performing visual semantic feature extraction on the preprocessed RGB image by using DINOv2; performing depth feature extraction on the preprocessed RGB image by using a DPT head; s4, generation of depth perception query points: inputting the visual semantic features and the depth features into a DETR network to generate the depth perception query points; and S5, target detection output: using an MLP-based detection head to obtain information of the category, the size, the center point position, the depth, the 3D size and the direction of the object.

The invention relates to the technical field of urinary tract infection detection, and discloses a phage-based rapid and accurate urinary tract infection detection method, which comprises the following steps: S1, constructing a CRISPR / Cas9 system; s2, constructing a homologous recombinant plasmid; s3, constructing three plasmids BL21; s4, constructing, screening, verifying and reporting a phage T4:: Nluc; according to the detection method, a CRISPR / Cas9 system is combined with a homologous recombination technology, so that the efficiency of bacteriophage gene editing is remarkably improved, based on the report bacteriophage T4:: Nluc, rapid, sensitive, specific, accurate, simple and convenient detection on clinical urinary tract infection escherichia coli is realized, and the method can be used for detecting an escherichia coli urinary tract infection sample which is not pretreated, and has a wide application prospect. The kit shows excellent detection timeliness and specificity, is a powerful tool for identifying clinical urinary tract infection escherichia coli, and provides a new technical path for timely and accurate diagnosis and effective treatment of clinical urinary tract infection.

A fissure occurrence parameter extraction method based on a borehole image relates to the technical field of geological resources and geological engineering, and mainly comprises the following steps: collecting and importing an original borehole image of a drilling area, enhancing and denoising the original borehole image, binarizing the image through dynamic area division, and obtaining a fissure occurrence parameter extraction result; detecting the edge of the fracture structural plane by using a Canny operator for carrying out adaptive threshold selection based on a borehole image gradient histogram, carrying out sine curve fitting on the fracture structural plane, and extracting fracture occurrence parameters on a fitted fracture sine curve; based on the engineering drilling image, the rock mass structural surface can be automatically identified, occurrence parameters can be extracted, previous manual intervention and operation are replaced, and the efficiency of analyzing geological conditions and underground water migration conditions in geological engineering is improved.

The invention provides an efficient power plant equipment maintenance robot, and relates to the technical field of power plant equipment maintenance. The efficient power plant equipment maintenance robot comprises a boiler, a control panel, a frame and four first wall-climbing hubs, the four first wall-climbing hubs are arranged at the upper end and the lower end of the rear end of the two side walls of the frame correspondingly, the four first wall-climbing hubs are arranged at the center of the front end face of the boiler, and the control panel is arranged at the position, close to the front portion, of the upper end of the interior of the frame. A base plate is fixedly connected to the rear portion of the center in the frame, a collecting structure is arranged at the front portion of the lower end of the base plate, a storage battery module is arranged in the frame at the upper end of the base plate, a support is arranged at the rear end of the storage battery module, and a sweeping structure is arranged at the upper portion of the rear end in the support. Dust on the boiler is cleaned through the cleaning structure, the thickness and cracks of the side wall of the boiler are detected through the ultrasonic thickness gauge and the eddy current flaw detector, detection is more accurate and rapid, and therefore the detection efficiency is improved.

The present invention relates to a device and method for three-dimensional detection of surface defects of large-aperture curved optical elements, belonging to the field of three-dimensional detection of surface defects of optical elements. The device includes a mobile platform, a 3D line spectrum confocal sensor, a calibration head, an industrial camera, a telecentric lens, a ring light source, a point light source, and a camera axis fine-tuning device, etc. The method includes the following steps: positioning and focusing the element to be tested; scanning the 3D line spectrum confocal sensor to obtain the defect position and three-dimensional information of the defect; switching to a two-dimensional defect detection module to obtain two-dimensional information of surface defects; and comprehensively analyzing the two-dimensional information and the three-dimensional information to obtain the three-dimensional detection results of each defect on the surface of the element to be tested. The present invention realizes rapid positioning and high-precision three-dimensional detection of surface defects of large-aperture curved optical elements by carrying two defect detection modules on a mobile platform.

The invention discloses a sugarcane smut dual-mode sensing platform and application thereof, and relates to the technical field of biological detection and chemical analysis. The sensing platform comprises a three-chain DNA (Deoxyribose Nucleic Acid) and a CdTe QDs-NH2-F chain, the triplex DNA is a double strand consisting of an MB-A chain and an FAM-B chain; the MB-A chain is an A chain connected with magnetic beads; the FAM-B chain is a B chain which modifies a fluorophore and can form a hairpin structure; the CdTe QDs-NH2-F chain is an F chain which is aminated and is connected with the cadmium telluride quantum dots; a part of base sequence of the chain A is complementary to a base sequence of a sugarcane smut pathogenic bacterium gene; the base sequence of the chain F is complementary to the partial base sequence of the chain A, and the partial base sequence of the chain F is the same as the partial base sequence of the sugarcane smut pathogenic bacterium gene and the partial base sequence of the chain B. The sensing platform can sensitively amplify and efficiently amplify the genes of the pathogenic bacteria of the sugarcane smut, and can respectively obtain independent detection results of a photoelectrochemical detection mode and a fluorescence detection mode, so that the sensitivity and the accuracy of the detection results are improved.

The invention belongs to the technical field of laser positioning emission, and particularly relates to a laser positioning emission method based on YOLO and micro-motion target detection, and the method comprises the steps: S1, obtaining target image data, and recognizing a target graphic anchor frame through a YOLO target detection model; s2, identifying a micro-motion target in the image data acquired by the camera by using a micro-motion target detection algorithm, and obtaining the coordinates of the anchor frame of the target to be detected; s3, integrating the number of the target image anchor frames obtained by the micro-motion target detection algorithm and the number of the target image anchor frames of the YOLO target detection model, and completing the first identification of the to-be-detected target; and S4, establishing a world coordinate system transformation model and a self-adaptive anchor frame zooming model, completing the second identification of the to-be-detected target, and controlling the laser positioning transmitting device. According to the method, machine learning, traditional image processing and hardware control are combined, high-precision target detection and intelligent laser control can be achieved, the automation degree is high, and expandability is large.

Provided are a combined machining device, a control method for the combined machining device, and a program for executing the control method. A method for controlling a combined machining device for performing cutting and friction stir welding includes: acquiring tool information indicating which of a cutting tool and a friction stir welding tool is a plurality of tools attachable to the combined machining device; acquiring a command indicating an execution tool called by a machining program executed by the combined machining device among the plurality of tools; if the execution tool is determined to be a tool for cutting processing based on the tool information and the command, the position correction of the execution tool based on the temperature detected from a temperature sensor provided in the combined processing device is enabled during the cutting processing; and if it is determined that the execution tool is a tool for friction stir welding based on the tool information and the command, determining a load applied to the execution tool during friction stir welding, and enabling position correction of the execution tool based on the load.

The invention relates to the technical field of generator excitation systems, in particular to a PT fuse slow melting judgment method based on phase-splitting comparison, a medium and electronic equipment. The PT fuse slow melting detection comprises the following steps: comparing a PT signal three-phase voltage amplitude accessed by an online operation control channel with a PT signal three-phase voltage amplitude accessed by a standby control channel one by one; and if any phase voltage deviation reaches a phase voltage deviation threshold value and the duration exceeds a preset duration, judging that the PT with a relatively low phase voltage amplitude has a fuse slow-melting fault, and triggering a PT fuse slow-melting alarm. The method is more sensitive to the single-phase PT fuse slow-melting fault of the excitation system, the fault can be rapidly and accurately detected when the PT fuse slow-melting fault of the excitation system occurs, and measures can be conveniently and timely taken for treatment.

The invention provides a simulation method and device for detecting interface pressure of a cable joint through harmonic waves and a medium. The method comprises the following steps: modeling a simulation geometric model for the cable intermediate joint, and setting an ultrasonic excitation source; modeling through a nonlinear spring damper to obtain a cable joint pressure model; and performing nonlinear ultrasonic detection cable joint interface pressure simulation on the cable joint pressure model to obtain a spectrogram at each point probe. According to the invention, on a cable joint model, modeling is carried out through a nonlinear spring damper, nonlinear interaction at a cable intermediate joint interface is simulated, a nonlinear harmonic detection principle is utilized, and the change of harmonic characteristics when the interface pressure changes is deeply explored, so that the relationship between the two is established; the states of the cable intermediate joint under various interface pressures are accurately simulated, the interface pressure of the cable intermediate joint is fully considered, and simulation analysis is performed on the interface pressure detection of the cable joint by establishing a new interface nonlinear model.

[Problem] To achieve a structure capable of detecting a piston contact point and a clutch contact point. In order to solve the problem, a phase (theta) related to the rotation direction of a drive cam (34) when the output torque (T) or the current value (A) of a shift motor (66) starts to increase at an increase rate equal to or greater than a first threshold value when an electric friction engagement device (7) is switched from a connection mode to a disconnection mode is detected as a piston contact point (theta p). And detects, as a clutch contact point ([theta] f), a phase ([theta]) related to the rotation direction of the drive cam (34) when the increase rate is equal to or less than a second threshold value.

The utility model relates to the technical field of air conditioners, particularly provides a bed-mounted air conditioner, and aims to solve the problem that the detection effect of a refrigerant detector in the bed-mounted air conditioner in the prior art is not ideal. In order to achieve the purpose, the bed-mounted air conditioner comprises a bed-mounted machine shell, a first air inlet and a second air inlet, and the side, in the second direction, of the bed-mounted machine shell is provided with a side air inlet; the heat exchanger is arranged in the bed machine shell; the liquid inlet and outlet pipe is arranged in the bed machine shell, located on one side of the heat exchanger in the second direction and located between the side air inlet and the heat exchanger; and the refrigerant detector is arranged on the heat exchanger. According to the utility model, the refrigerant detector is arranged behind the liquid inlet and outlet pipe, airflow enters the bed machine shell from the side air inlet along the second direction, flows through the liquid inlet and outlet pipe and then flows to the heat exchanger, and the refrigerant detector is arranged on the heat exchanger, so that whether a refrigerant leaks or not can be detected in time, and early warning can be carried out in time; and the detection correctness of the refrigerant detector is improved.

This disclosure describes a substrate processing apparatus and a substrate processing method capable of detecting the position of a notch on a substrate with high precision. The substrate processing apparatus includes: a rotation holding unit configured to rotate the substrate while holding it with the notch; an imaging unit configured to capture images of the substrate held in the rotation holding unit; and a control unit. The control unit is configured to perform the following processes: a first process, controlling the imaging unit to capture multiple images of the entire substrate from the same imaging position while changing the imaging conditions during a period when the substrate held in the rotation holding unit is stationary, thereby acquiring multiple image images including the entire substrate; a second process, setting processing areas in different regions for each of the multiple image images according to the imaging conditions; and a third process, performing image processing on the processing areas of each of the multiple image images to detect the position of the notch on the substrate.

This invention relates to the field of track slab measurement, and discloses a portable track slab flatness measuring device and method. The device includes a track base, a track web at the upper end of the track base, and a track head at the upper end of the track web. Two sets of splicing clamping assemblies are provided on both sides of the upper end of the track head. One set of splicing clamping assemblies has a connecting plate at its upper end, and a laser detector at its upper end. The other set of splicing clamping assemblies has a connecting plate at its upper end, and a laser emitter at its upper end. Both sets of splicing clamping assemblies have electric wheels at their bottoms. The track base, track web, and track head are integrally formed. In this invention, the splicing clamping assemblies adopt a symmetrical clamping structure, eliminating the need to push them in from the end face of the track slab. They can be directly clamped and fixed at any position on the track head, solving the problem of limited installation position in existing devices. This facilitates accurate detection of local defects in the track slab and significantly improves detection flexibility.

The utility model relates to the technical field of container lifting, in particular to a container lifting appliance for detecting the direction of a container door, which comprises a lifting appliance body for lifting a container, the container is provided with a first side plate and a second side plate, the first side plate is provided with the container door, and corner castings are respectively arranged at four corners above the container; a lock head corresponding to the corner casting is rotationally connected to the lifting appliance body, a driving assembly for driving the lock head to rotate is arranged on the lifting appliance body, first detection rods are slidably connected to the two ends, corresponding to the length direction of the container, of the lifting appliance body correspondingly, and the distance between the first detection rods is larger than the distance between the first side plate and the second side plate. The first detection rods are in transmission connection with first sensors. The orientation of the box door is detected through whether the first detection rod and the second side plate are pressed or not, the box door orientation detection device has the advantages of being simple and direct in structure and accurate and reliable in detection, and the orientation of the box door can be simply, conveniently and accurately detected.

A circuit backplane detection device and detection method are used to detect the pad group of the circuit backplane, the pad group includes a first pad and a second pad for bonding with an LED chip, the circuit backplane detection device includes an electromagnetic component and an imaging component, the electromagnetic component includes a magnetic induction box and multiple compasses fixed in the magnetic induction box, and the imaging component includes a camera for acquiring images of the compasses. The magnetic induction box is placed on the circuit backplane, and the multiple compasses are arranged in a one-to-one correspondence with the multiple pad groups. When a changing current is passed through the circuit backplane, the image shows that the direction of the compass changes, indicating that the pad group is normal; if the image shows that the direction of the compass remains unchanged, it means that the pad group is damaged. According to the change in the direction of the compass, it can be judged whether the corresponding pad is damaged, thereby realizing the detection of bad points on the circuit backplane before chip bonding, which is conducive to reducing the difficulty of repair and reducing production costs.

The utility model relates to the technical field of mobile phone touch screen detection, and discloses a light transmittance detection device of a mobile phone touch screen, which comprises a transmission band, a detection assembly, a connector, a power line, a first electromagnetic coil and a second electromagnetic coil, the top of the transmission band is provided with the detection assembly, one side of the detection assembly is movably connected with the connector, and the other side of the detection assembly is movably connected with the power line. The first electromagnetic coil and the second electromagnetic coil are symmetrically and fixedly installed on one side of the connector, the power line is fixedly installed on one side of the connector, and the first electromagnetic coil and the second electromagnetic coil are symmetrically and fixedly installed on one side of the connector, and the beneficial effects are that through cooperation among the connector, the power line, the first electromagnetic coil and the second electromagnetic coil, the first electromagnetic coil and the second electromagnetic coil are opposite in magnetic pole and have mutual attraction; according to the light transmittance detection device for the mobile phone touch screen, the connector and the identifier can be fixed, so that the power line is connected more firmly, the power line is prevented from loosening and poor contact due to external influence, the scanning effect of an infrared scanner is prevented from being influenced, and the detection accuracy of the light transmittance detection device for the mobile phone touch screen is improved.

The object detection device for detecting a target (TA) includes: a light source (10); an emission unit (14) that emits illumination light and has an optical phased array (20) that changes the emission direction of the illumination light; an orientation control unit (36) that controls the emission direction of the illumination light to scan a scanning area; a detection unit (40) that determines whether a target exists and measures the orientation of the target; a high reflectivity determination unit (50) that determines whether the target is a high reflectivity; a high reflectivity measurement unit (52) that estimates the size of the high reflectivity; and a threshold setting unit (54) that sets a detection determination threshold. The threshold setting unit sets the detection determination threshold for orientations other than the specified orientation based on the light received from the high reflectivity when the emission direction is set to an orientation other than the specified orientation, the size of the high reflectivity, the distribution of the emission intensity of the emission unit when emitting the illumination light, and the distribution of the light sensitivity of the reflected light of the detection unit.

The invention relates to a detection system. The detection system includes a robot arm, a laser sensor, and a control device. The robot arm includes a base, a multi-joint arm connected to the base, and a capacitance-type proximity sensor provided on the multi-joint arm and detecting an interfering object. The laser sensors are provided at positions facing each other with respect to the base, and emit laser light in a direction substantially parallel to a mounting surface of the robot arm to detect an interfering object. The control device stops or decelerates the operation of the robot arm on the basis of the detection result of the interfering object obtained by at least one of the capacitive proximity sensor and the laser sensor. The beneficial effect is that the interference object approaching the mechanical arm can be detected in a high-precision and large-range manner.

The present disclosure relates to an information processing device, an information processing method, and a computer-readable medium recording an information processing program. The information processing device of the present disclosure includes: a detection unit that detects an observed value related to a change in the acceleration of a vehicle caused by a driving operation; an inertial measurement unit that detects an actual value of the acceleration of the vehicle; and an inference unit that determines that the vehicle has collided when the difference between the actual value of the acceleration of the vehicle detected by the inertial measurement unit and the inferred value of the acceleration of the vehicle calculated based on the observed value, i.e., the acceleration difference, is greater than a predetermined threshold.

The invention relates to the technical field of composite material detection, in particular to a composite material structure surface defect detection method. The rapid composite material structure surface defect detection method is obtained by adopting a hyperspectral imaging technology, so that the data acquisition and processing speed is high, and the identification precision is high. According to the method, the position and the type of the surface defect of the defective composite can be quickly and accurately detected, and the defect can be classified and judged on the basis, so that the influence of human subjective factors on defect judgment is greatly reduced, meanwhile, the data of the defect position can be directly obtained, secondary metering work is not needed, and the working efficiency is improved. According to the invention, the image dimension and the spectrum dimension of the hyperspectral imaging system are simultaneously utilized to detect the fabric defects, so that the result is more intuitive and accurate.

The present invention relates to the technical field of integrated circuits, and provides a power converter and a control method thereof, wherein the power converter comprises a power switch tube and an inductor, and a control circuit, and the power switch tube at least comprises: a first power switch tube connected between the aforementioned inductor and the output end of the power converter, a second power switch tube connected in parallel at both ends of the first power switch tube, and a third power switch tube located between the connection node of the aforementioned inductor and the first power switch tube and the ground, wherein the power converter operates in a negative half cycle, and before the output current decreases to zero, the control circuit controls the on-off state of the power switch tube connected between the aforementioned connection node and the output end of the power converter according to a control signal generated by sampling the output of the power converter and a duty cycle adjustment signal generated by logical control of the switch control signal. This can improve the detection accuracy of the output power and improve the efficiency of the power converter.