1846 results about "Identification device" patented technology

The invention discloses an extreme sea condition parameter identification system based on deep learning, and relates to the technical field of ship navigation auxiliary equipment, in particular to a self-adaptive sea condition identification device which is used for acquiring image data and inertial measurement data of a current sea condition; the wave field visual depth estimation module is used for extracting visible light image features and infrared image features of a wave area from image data of the current sea condition, fusing the extracted visible light image features and infrared image features, using an encoder-decoder architecture and fusing an energy function to obtain a pixel-level wave height field, and outputting the pixel-level wave height field. The three-dimensional reconstruction of the wave surface is realized; the multi-modal data fusion module uses a filter dynamic model and a cost function to eliminate space-time asynchronous errors between inertial measurement data and visual perception data, performs multi-modal data fusion, and outputs wave field real-time parameterization information. According to the invention, the sea condition parameter real-time high-precision identification capability of the autonomous unmanned ship or the offshore carrying platform can be improved.

The invention provides a boiler welding seam full-automatic detection system and method based on machine vision and an ultrasonic phased array, and relates to the technical field of boiler detection.The system comprises a six-axis mechanical arm unit, a multi-degree-of-freedom boiler fixing platform unit and a welding seam type recognition device; the boiler is arranged on the multi-degree-of-freedom boiler fixing platform unit and used for driving the boiler to do vertical motion, inclined motion and rotary motion, the six-axis mechanical arm unit is arranged on one side of the multi-degree-of-freedom boiler fixing platform unit, the welding seam type recognition device is arranged at the tail end of the six-axis mechanical arm unit, and the welding seam type recognition device is arranged on the other side of the multi-degree-of-freedom boiler fixing platform unit. And the six-axis mechanical arm unit is used for driving the welding seam type identification device to move and identifying a circular seam and a longitudinal seam of the boiler. According to the invention, full-process automation of boiler welding seam detection is realized, the detection efficiency and the defect detection rate are improved, the safety risk of manual detection is eliminated, and the detection quality consistency and the industry standardization level are remarkably improved.

To provide a new technique for enhancing interest.SOLUTION: The game apparatus includes an acquirer configured to acquire character string information relating to acquisition of a game element, a specifier configured to specify the game element from the character string information, a display controller configured to display one or more pieces of character string information acquired by the acquirer on a display in a selectable state, and a controller configured to control, based on selection of any one of the one or more pieces of character string information, the game element specified from the selected character string information to be in an acquisition state in the game.SELECTED DRAWING: Figure 8

The invention discloses a quantitative recognition device for the number and size of bubbles at a rotating impeller of a multiphase pump. The quantitative recognition device comprises a two-phase flow experiment system, the multiphase pump, a high-speed camera, a light source and the like. The preprocessing and data analysis system and the deep learning system are arranged in the computer; the two-phase flow experiment system and the image acquisition system are electrically connected with the computer through lines. The invention further discloses a quantitative recognition method for the number and size of the bubbles at the rotating impeller of the multiphase pump. According to the method, the problems of low blistering recognition precision, low efficiency and large error caused by the existing manual measurement method are solved, and a reference method is provided for exploring the influence of gas distribution at the impeller in the multiphase pump on pump operation and optimizing design of the multiphase pump.

The invention discloses a train number, train container number and train type recognition device, which relates to the technical field of train recognition and comprises an edge disturbance sensing module, a fusion feature analysis module, a structure guide reconstruction module, a path evaluation recognition module and a dynamic path regulation and control module. And the structure guide reconstruction module is used for carrying out channel reordering and space adaptive amplification on the image based on the determined morphological fusion features, enhancing character structure coherence and boundary closure by utilizing a fusion feature guide reconstruction network, and extracting real container number character structure features from the image. According to the invention, by introducing multi-scale disturbance perception, morphological fusion feature analysis, structure guide reconstruction and dynamic path regulation and control mechanisms, accurate extraction and stable identification of a real character structure in a complex corrosion interference environment are realized, and the accuracy and robustness of container number identification are improved.

This invention discloses a boom identification method, a processor, a boom identification device, and a computer-readable storage medium. The boom identification method includes: obtaining the output current I of the Nth boom segment. N2 The Xth arm receives the output current I from the (X+1)th arm. (X+1)2 As the input current I of the Xth arm segment X1 and the input current I X1 The process is performed to obtain the output current I of the Xth arm segment. X2 For the output current I 12 The process involves processing to obtain identification parameters for each boom segment. Based on these parameters, the current boom segment type and connection relationship are determined, and the correctness of these parameters is then assessed. The boom identification method, processor, device, and computer-readable storage medium of this invention can identify both the boom segment type and the connection sequence of each segment, ensuring that the correct boom segment type is used and connected in the correct order. This reduces safety accidents caused by boom segment identification errors, thereby minimizing casualties and property damage.

Provided are a position identification method, a position identification device, and a position identification program capable of identifying, from a change in an obtained diffraction image, the position of a structure that becomes a cause of damage such as a crack in a sample in a single-crystal state. This position identification method for identifying the position of a target structure in a sample comprises: a step for vertically irradiating the surface of a sample S1 in a single-crystal state with white X-rays R10; a step for acquiring a diffraction image generated by irradiation; and a step for moving the position of irradiation on the surface of the sample S1. With the method, a parallel position of the target structure is identified on the basis of diffraction images acquired by repeatedly performing the series of steps from the vertical irradiation to the movement.

The invention relates to the technical field of steel wire rope damage detection, and discloses a steel wire rope surface damage recognition device which comprises a steel wire rope and an electromagnetic detector, supporting frames are fixedly connected to the two sides of the electromagnetic detector, guide rollers are arranged in the supporting frames, and a supporting cylinder is arranged on the side, opposite to the electromagnetic detector, of one guide roller. The side end of the steel wire rope sequentially passes through the middle of the supporting cylinder, the bottom of the guide roller and the middle of the electromagnetic detector to be detected, a cleaning mechanism is arranged in the supporting cylinder, and the cleaning mechanism comprises a cleaning cylinder. The technical means that the electromagnetic detector, the guide roller, the supporting cylinder and the cleaning mechanism are matched is adopted, the defect that in the prior art, a steel wire rope used in a mine for a long time is corroded by water vapor and then is rusted to cover the surface of the steel wire rope is overcome, and magnetic field signals, sensitivity and signal accuracy are improved through detection after cleaning; and the detection data is more accurate.

A down feather type identification device relates to the field of down feather detection equipment and comprises a base, a transverse moving mechanism, a longitudinal moving mechanism, a down feather mounting mechanism and a microscopic imaging mechanism, and a light source is arranged on the base; the down feather mounting mechanism moves back and forth through the transverse moving mechanism and the longitudinal moving mechanism and comprises a base plate, a transparent plate, a mounting groove and a sealing cover. And the microscopic imaging mechanism is arranged above the down feather mounting mechanism and is opposite to the light source so as to observe the down feathers in the mounting groove. The to-be-identified down and feathers are placed in the mounting grooves and then covered with the sealing covers, the different down and feathers are aligned with the light source through back-and-forth movement and then observed through the microscopic imaging mechanism, the accuracy of the detection result is improved, experimental data can be conveniently reserved for subsequent verification, and due to the fact that the mounting grooves are isolated from one another, the accuracy of the detection result is improved. Therefore, multi-type and multi-batch down feather identification can be carried out at the same time without causing confusion, and the detection efficiency is improved.

The utility model belongs to the technical field of monitoring equipment, and relates to a defect monitoring and identifying device which comprises a workbench (1), a mounting column (2) arranged on one side of the workbench (1), and a camera (3), a lens (4), an annular light source (5) and a light shielding plate (6) which are coaxially arranged from top to bottom, a light through hole (61) is formed in the light shielding plate (6), a first connecting structure (7) is arranged on the mounting column (2) in a sliding manner, and a second connecting structure (8) is arranged on the first connecting structure (7). The annular light source (5) is rotationally connected with the first connecting structure (7); a second connecting structure (8) is arranged below the first connecting structure (7), the second connecting structure (8) is in sliding fit with the mounting column (2), and the shading plate (6) is fixedly connected with the second connecting structure (8). The defect monitoring and identifying device disclosed by the utility model can effectively inhibit stray light and improve the detection precision.

The invention relates to a modular Coriolis flow meter (1) for determining a process variable of a flowable medium, comprising: a measuring tube module (M1), the invention relates to a device for measuring a medium, comprising: a measuring tube (3a, 3b), in particular a metal, for conducting the medium, a main exciter assembly (23) arranged on the measuring tube (3a, 3b), a main sensor assembly (24a, 24b) arranged on the measuring tube (3a, 3b), and a measuring tube module identifier (28) having identification information; -a carrier module (M2) comprising: a container (11) in which the carrier module (M2) is arranged; measuring tube module (M1) can be arranged in a mechanically fixed manner in a first installation position or a second installation position in a releasable connection and can also be released again, or measuring tube module (M1) can be arranged in a mechanically fixed manner in a first installation position or a second installation position in a releasable connection and can also be released again the second mounting position is different from the first mounting position; an electronics chamber (30) in which evaluation electronics (ME) for determining a process variable are arranged; a secondary exciter assembly (13) that supplements the primary exciter assembly (23); and a secondary sensor assembly (14) that supplements the primary sensor assembly (24); an installation position identification device (19) configured to identify the measuring tube module identifier (28) in order to determine the identification information and to ascertain the current installation position on the basis thereof, the evaluation electronics (ME) being configured to determine the process variable depending on the identified current installation position.

The invention discloses a fault symptom rapid identification method, a fault symptom rapid identification device, a fault symptom rapid identification device and a computer readable storage medium for a converter transformer valve side external construction frequency resonance test, and the method comprises the steps: firstly, carrying out the real-time synchronous collection of multi-dimensional parameters, such as voltage, current, local discharge amount and waveform distortion; on the basis, a multi-parameter comprehensive criterion system is established, and fault type priorities are configured, so that accurate classification and identification of different types of fault symptoms are realized; a preset linkage disposal operation sequence is automatically triggered according to an identification result, and an automatic closed loop from monitoring and early warning to active protection is formed; and finally, through whole-process data recording and report generation, the traceable management of the fault information is perfected. According to the whole scheme, multi-source information fusion and intelligent decision control are combined, and systematic technical support is provided for early warning and quick response of faults in the test process.

The invention relates to a method for identifying a living being by means of a data processing arrangement, comprising the steps of: determining, taking into consideration a second data set comprising a genetic fingerprint of the living being, a hash value by means of a hashing device, and generating, taking into consideration the hash value, a unique identity marking by means of an identification device. The present invention further relates to a corresponding data processing arrangement and a corresponding computer program product.

The invention provides an electrical equipment defect identification method and device based on pose fusion, the method is applied to an identification device comprising a data processing module, a model construction module and a defect identification module, and the method specifically comprises the following steps: obtaining historical image data and corresponding defect information, and aligning pose data with the historical image data according to a shooting timestamp; performing perspective distortion correction and deblurring processing on the historical image data according to the corresponding pose data to obtain a corresponding equipment area image, and training a YOLO model in combination with the corresponding pose data and defect information to obtain a power equipment defect identification model; and constructing a recognition sample according to the currently collected image data and pose data of the power equipment, and inputting the recognition sample into the power equipment defect recognition model to obtain a defect recognition result of the power equipment. According to the method, the pose data can be fused into the pre-training data preprocessing stage and the training stage of the model, the method can adapt to defect identification of power equipment in different pose scenes, and the accuracy is guaranteed.

The utility model discloses intelligent identification equipment for defective rate of fasteners, which relates to the technical field of fastener detection and comprises a rack, a material taking mechanism is mounted on the upper surface of the rack, a base is connected to the edge, close to the rear side, of the bottom of the rack, a belt conveyor is mounted on the front side of the rack, and a conveying plate is connected to the surface of the belt conveyor. A pushing plate is connected to the upper surface of the conveying plate, a workpiece is movably placed between the conveying plate and the rack, a support is connected to the bottom of the rack, and a laser distance measuring sensor is installed on the upper surface of the support. Through the arrangement of the material taking mechanism, the ejection block and the laser distance measuring sensor, defective products of workpieces can be intelligently recognized, and after the defective products are detected, the defective products are automatically removed and collected; by arranging the supporting block screw holes and the screw rods, the distance between the conveying plate and the rack, namely the distance of conveying channels, can be adjusted, the device can be suitable for detection of workpieces of different specifications, and the application range of the device is enlarged.

The utility model discloses an on-line thickness measurement identification device for laser welding materials, which relates to the technical field of laser ranging and comprises a conveying line, fixing frames are fixedly mounted on two sides of the conveying line, adjusting columns are symmetrically mounted on the surfaces of the fixing frames, a vertical positioning rod is mounted on the adjusting column on one side, and a vertical lead screw is mounted on the adjusting column on the other side. The periphery of the lead screw is in threaded connection with an adjusting frame, the side, away from the lead screw, of the adjusting frame is slidably connected with the periphery of the positioning rod, and air cylinders are symmetrically installed at the bottom of the adjusting frame and connected with laser sensors. According to the device, the laser sensor is adopted to automatically measure the thickness of the plate, traditional manual measurement is replaced, the measurement precision and the measurement efficiency are effectively improved, the plate is compacted and flattened in cooperation with the pressing wheel, the influence of plate warping on the measurement precision is eliminated, and the measurement precision is improved.

The invention relates to the technical field of intelligent display, in particular to an intelligent identification method and system based on energy-saving control, and the method comprises the following steps: S1, collecting external environment parameters through a low-power-consumption sensor disposed in an intelligent identification device, the environment parameters comprising environment illumination intensity, a human body or object approach signal and equipment electric quantity information, and transmitting the environment illumination intensity to an intelligent identification device; the data of the environmental parameters are judged; the system can automatically adjust the display brightness and the refresh frequency according to the environment illumination, the target distance and the electric quantity, refresh according to the demand by combining the content priority, and automatically switch the working state and the dormant state according to the human body approaching, the timed task or the remote instruction; in the aspects of communication and energy management, the communication period and power consumption are adjusted in real time, energy self-balancing is achieved, and the service life of equipment is prolonged; in addition, the system periodically analyzes historical operation data and self-learns and optimizes control parameters, so that energy consumption is continuously reduced in long-term operation, display efficiency is improved, and performance stability is kept.

An abnormal irregularity cause identifying device includes a process data acquisition unit that reads, from a storage device storing process data, the pieces of process data, an abnormality determination unit that calculates an abnormality degree representing an extent of an irregularity of process data of the pieces of process data read by the process data acquisition unit, and a cause diagnosis unit that obtains accuracy of a cause of the irregularity based on a proportion of process data having the abnormality degree calculated by the abnormality determination unit satisfying a predetermined criterion to the plurality of types of pieces of process data, by using causal relation information defining a combination between the cause and the irregularity, which appears as an influence resulting from the cause, of each of the plurality of types of pieces of process data.

The present disclosure discloses a product recognition apparatus and method, in which the apparatus includes: a vision sensor configured to obtain and transmit image information of a product to an arithmetic processing unit; the arithmetic processing unit configured to deal the image information of the product based on an image recognition model, to obtain and transmit category information of the product to a data transceiver; and the data transceiver configured to transmit the category information of the product to a backend server of a seller, so that the backend server of the seller makes a settlement based on the category information of the product and preset price information of different categories of products. By adopting the product recognition apparatus, it is possible to quickly recognize the categories of various products, increase efficiency and accuracy of the cashing, and improve the user experiences.

A system for tracing a Group of Members (GoM) of an animal population throughout a process including moving the GoM between a plurality of Physically Separate Locations (PSLs), the system comprising a processing circuitry configured to: obtain a plurality of sets of identifiers of the GoM, each obtained by readings of Identification Devices (IDs), wherein (a) each ID of the IDs is attached to, and uniquely identifies, a respective member of the GoM, (b) the identifiers in each of the sets are read (i) at a respective given PSL of the PSLs, (ii) by a respective given ID reader of a plurality of ID readers; (c) one or more partial sets of the sets do not include one or more respective missing identifiers of at least one member of the GoM; and add the missing identifiers to the respective partial sets along with a confidence score.

The invention relates to the technical field of smart home, and discloses an identity recognition method, which comprises the following steps: preprocessing original data acquired by a low-resolution radar and an inertial measurement unit, and respectively generating a radar state vector and an inertial measurement state vector; performing matching degree calculation on the radar state vector and the inertial measurement state vector with a pre-constructed identity vector library; when the matching degree calculation result meets a preset cross-modal feature fusion condition, carrying out fusion processing on the radar data features and the inertial measurement data features; and performing user identity recognition based on fusion features obtained through fusion processing. According to the scheme, the accuracy of identity recognition is guaranteed, the strict requirements of a family scene for light weight and low cost are met, and stable and accurate multi-target identity recognition can be achieved in a dynamic family environment by fully utilizing low-resolution radar characteristics. The invention further discloses an identity recognition device and a computer readable storage medium.

The invention discloses an intelligent switching control electrician practical training identification device, which belongs to the technical field of electrical detection and comprises a practical training platform, an operation panel, an electrical carrier plate and a built-in PLC (Programmable Logic Controller), the system integrates power input, a first conversion unit composed of a first isolation transformer and a first contactor, a second conversion unit composed of a second isolation transformer and a second contactor, a control unit, a data storage module, an operation input unit, a feedback unit and a load output unit. A dual-safety interlocking structure combining software interlocking and contactor hardware interlocking is realized through a PLC, and two paths of power outputs cannot be switched on at the same time. The device has the functions of intelligent mode switching, real-time voltage monitoring, fusing and sudden stop dual protection, operation state feedback and practical training data storage, meets industrial-grade and safety-grade practical training requirements, is compact in structure and high in safety, supports closed-loop control and data tracing, and is suitable for modern electrician skill training and intelligent examination and identification.

The invention discloses a YOLOv8-based rail transit construction site multi-category engineering vehicle recognition device, method and equipment and a medium, and the device comprises an image obtaining module which is configured to obtain a visible light image and an infrared image of a rail transit construction site; the multi-modal feature enhancement module is configured to respectively extract texture structure features of the visible light image and temperature distribution features of the infrared image, align dual-modal features by using a spatial transformation network, and realize dual-modal feature weighted fusion through a dual-channel attention mechanism; the component-level dynamic attention mechanism module is configured to perform component-level enhancement and optimization on the bimodal features after weight fusion and output an enhanced fusion feature map; and the time sequence correlation loss function module is configured to realize target classification and bounding box prediction, output a target position distribution prediction result after time sequence correlation optimization through a target motion model in combination with a continuous frame detection result, and complete engineering vehicle identification of the rail transit construction site.

An intelligent standard-emulsion-explosive charging robot suitable for underground engineering. The charging robot comprises a blast hole identification device (1), an air blowing and pushing device (2), a robotic arm (3), an air compressor (4), a detonator device (5) and a charging device (6), wherein the blast hole identification device comprises an industrial camera (7) and a fill light (8); the air blowing and pushing device comprises the air compressor, an air blowing and pushing tube (10) and servo electric motors (11-1, 11-2); the detonator device comprises a detonator compartment (15), a servo electric motor (16), a coupling (17), a robotic gripper (19), a steering gear (20) and a ball screw (21); and the charging device comprises a driving device and an explosive compartment (24). The intelligent charging robot has a compact structure and a high degree of automation, and can simultaneously push a plurality of emulsion explosives in a single operation, thereby reducing the labor intensity and improving the tunnel construction efficiency.

The invention discloses a notch edge recognition system, a notch edge recognition method and a notch edge recognition device of a wafer edge finder. The notch edge recognition system, the notch edge recognition method and the notch edge recognition device of the wafer edge finder are based on a control program written by an stm32f407 chip. The method comprises the following steps: motion control of a single motor, a three-axis motor linkage motion control algorithm, innovative design of an ad acquisition circuit, hardware design of motion and acquisition cooperation, a linkage algorithm of motion and acquisition cooperation, a filtering algorithm after data acquisition, and an algorithm of finding a gap through data are combined. The notch edge identification system, identification method and identification device of the wafer edge finder provided by the invention have the advantages of accurately identifying the cut edge and the notch, comprehensively improving the precision, stability and reliability of wafer edge finding, and providing better technical support for wafer processing and the like.

A memory device includes a stacked memory, a plurality of conductive vias, and a memory controller. The stacked memory includes a plurality of memory chips. Each memory chip includes at least one memory cell array, a chip identification device, and a signal path switch. The chip identification device is coupled to the at least one memory cell array. The signal path switch is coupled to the chip identification device. The conductive vias penetrate through the stacked memory. The memory controller is coupled to the stacked memory.

A nicotine delivery device (200) for generating a mist containing nicotine for inhalation by a user. The device comprises a mist generator device (201) and a driver device (202). The driver device (202) is configured to drive the mist generator device (201) at an optimum frequency to maximise the efficiency of mist generation by the mist generator device (201).

The application provides a fingerprint identification device with small thickness and low cost and an electronic terminal. The fingerprint identification device comprises an optical film and an image sensor arranged along a first direction and at a first distance. The optical film comprises a first area and a second area with different light transmittances, and the first area and the second area form a first pattern. When the optical film receives light reflected from a first object, the optical film converts the light into an optical image with the first pattern and transmits the optical image to the image sensor. The image sensor is configured to receive an optical signal in the optical image and convert the optical signal into an electrical signal, and the electrical signal is used to construct an image of a surface of the first object reflecting the light. In an embodiment of the application, an electronic terminal comprising the aforementioned fingerprint identification device is provided.

The invention discloses an intelligent recognition device for power distribution network equipment, and relates to the technical field of intelligent power grid equipment manufacturing, the intelligent recognition device comprises an operation table, and the surface of the operation table is provided with a visual detection mechanism, a trimming mechanism, a feeding mechanism and a feeding supporting assembly; the visual detection mechanism comprises an n-shaped fixing frame fixed to the middle of the operation table, and a limiting installation groove is formed in the inner top wall of the n-shaped fixing frame. The visual detection mechanism is arranged, an industrial camera is located over the limiting tray and cooperates with the rotary supporting pipe to drive a workpiece to rotate, details on the surface of a silicon steel sheet can be captured in all directions, the quality of the workpiece is intelligently recognized, the detection precision is improved, an annular limiting protruding block on the limiting tray is inserted into a silicon steel sheet through hole, and the stability of the workpiece is enhanced; the precision is prevented from being influenced by displacement during detection or trimming; the trimming mechanism adjusts the position of a polishing block through a bidirectional threaded rod, it is ensured that the trimming size is accurate, and the detection and machining precision is guaranteed.