43results about How to "Reduce detection accuracy" patented technology

The invention relates to the technical field of current transformers, in particular to a current transformer for suppressing electromagnetic interference by adopting a high-frequency magnetic ring method. A housing; the number of the ports is two, and the two ports are fixedly connected and penetrate through the shell. The coil is fixedly connected to the interior of the shell; the number of the main magnetic rings is two, and the two main magnetic rings are fixedly connected to the interior of the shell and distributed on the two sides of the coil respectively; the fixing frame is fixedly connected to the interior of the shell, the fixing frame is in sliding connection with a plurality of sliding frames, each sliding frame is fixedly connected with two auxiliary magnetic rings, and the auxiliary magnetic rings are attached to the adjacent main magnetic rings; the stabilizing assembly is arranged in the shell; and the driving assembly is arranged in the shell. By changing the attaching position of the auxiliary magnetic ring and the main magnetic ring, the side, close to an external electric appliance element, of the main magnetic ring is superposed with the auxiliary magnetic ring, the resistance to an external interference magnetic field is improved, and the current detection precision of the device is improved.

The invention discloses a camouflage target detection method based on multi-dimensional polarization information. The method comprises the following steps: 1, acquiring a polarization image data set with pixel-level labels; 2, processing the four original polarization angle images, learning the exclusive weight of the feature of each image through a polarization dynamic attention module, extracting polarization information and structure details at the same time, and fusing the polarization information and the structure details with the original images; and 3, constructing a deep convolutional neural network based on multi-dimensional polarization information, inputting the fused image, and training the deep convolutional network to obtain an accurate camouflage target detection result. Under a reasonable data model condition, scene representation with rich textures and rich edge details is generated by utilizing correlation and difference of group polarization images, so that the problem that the detection effect of a camouflage target is influenced due to the fact that DoLP may be very weak or does not exist under certain illumination conditions can be effectively solved.

The invention relates to an industrial control system anomaly detection method based on protocol field vector similarity, and the method comprises the following specific steps: continuously collecting protocol messages in an industrial control system, and carrying out the protocol analysis of the protocol messages; and training a triplet network prepared in advance by using the training data set to obtain a trained industrial control system anomaly detection model. Protocol messages in the industrial control system are collected in real time, and protocol analysis is carried out on the protocol messages. According to the triplet model training and industrial control anomaly detection method, the collected industrial control protocol data is processed to obtain the stacking vectors, and when the stacking vectors are sorted according to the time sequence, the correlation of the three continuous stacking vectors can just meet the optimization target rule of a triple loss function in a triplet network, so that the triplet model training and industrial control anomaly detection method is designed. The problem that an existing industrial control system anomaly detection method based on unsupervised learning is not high in detection precision is solved, and the industrial control system anomaly detection method based on protocol field vector similarity is provided.

The invention discloses a bonding wire defect detection method based on point cloud. The method comprises the following steps: detecting and positioning integrated circuit image information through a YOLOV8 network; enabling the position detected by the YOLOV8 network to correspond to the point cloud range of the three-dimensional point cloud marking network, and marking the point cloud in the position range as the point cloud of interest; importing the point-of-interest cloud into a bonding wire welding spot extraction network for detection and classification of bonding wires, welding spots and substrates; and carrying out plane fitting on the point cloud of the substrate, and detecting the arch height and span of the bonding wire welding spot. According to the invention, the welding spot bonding wire is directly positioned to a point cloud within a certain range through a two-dimensional positioning and three-dimensional detection technology, so that the detection speed of the welding spot bonding wire is improved; the provided abnormal point elimination network improves the detection precision of the arch height and span of the bonding wire welding spot; a calculation model based on Euclidean is provided, and a space rectangular coordinate system is established; and calculating the arch height information of the bonding wire according to the difference between the vertex center of the bonding wire and the mass center of the welding spot in the Z-axis direction.

The present invention discloses a manual quick positioning clamping mechanism for a high-precision lamp base, comprising a support column, a clamping column is arranged at the upper end of the support column, the clamping column and the support column are connected by a slide rail, a clamping cylinder is arranged at one side of the clamping column, the clamping cylinder and the clamping column are connected by a connecting block, a plurality of long grooves are opened in the connecting block, a wiring harness plug is arranged in the long groove, a connecting column is arranged at the side of the clamping cylinder away from the clamping column, the connecting column and the clamping column are connected by a No. 2 slide rail, a guide column is arranged at the lower end of the connecting column, and a No. 1 travel sensor is arranged at one side of the connecting block; the way of clamping the lamp of the present invention protects the lamp from damage, and at the same time avoids the clamping instability caused by deformation of the lamp, reduces the detection accuracy and working intensity of this workstation, and greatly improves the detection accuracy of the CCD camera of this workstation.

The present application provides a DC-SMKD-based lightweight cattle herd detection method and device. The present application uses deep separable convolution to reduce the model size of the classic model to obtain a student model. The features of each layer output by the student model and the teacher model are subjected to knowledge distillation through SmoothL1Loss, so that the student model learns the multi-layer feature information of the teacher model YOLOv5x, which makes up for the feature loss after the separable convolution, and is conducive to obtaining relatively complete cattle body features in the teacher model, thereby improving the accuracy of cattle herd detection.

The invention provides a vehicle door opening control method, device and equipment, and the method comprises the steps: obtaining a first coordinate of a key point on a to-be-opened vehicle door under a first coordinate system, and obtaining a second coordinate of an obstacle detected by a radar sensor under the first coordinate system; based on the first coordinate of the key point and the second coordinate of the obstacle, determining a first distance between the obstacle and the first straight line and a second distance between the obstacle and the second straight line, and determining a smaller value of the first distance and the second distance as a target distance; based on the first coordinate of the key point and the second coordinate of the obstacle, the target maximum height from the to-be-opened vehicle door to the ground is determined, and the height difference value between the target maximum height and the height of the obstacle is calculated; if the target distance is smaller than a first threshold value, and the height difference value is smaller than a second threshold value, the vehicle door to be opened is braked; otherwise, the to-be-opened vehicle door is allowed to be opened. Through the technical scheme of the invention, the complexity of obstacle detection can be reduced, and the obstacle detection precision is higher.

A motor device (60) includes a stator (200), a rotor (300), a shaft (340), an electric power busbar (261), and a resolver (421). The shaft (340) includes a shaft main body (341) that rotates together with the rotor (300). The electric power busbar (261) is provided at a position away from the shaft main body (341) toward a radially outer side. The electric power busbar (261) extends in an annular shape in a circumferential direction (CD). The resolver (421) is provided on the shaft main body (341) and detects a rotation angle of the shaft main body (341). The resolver (421) is provided at a position away from the electric power busbar (261) toward a radially inner side. The resolver (421) is in a state of entering between the electric power busbar (261) and the shaft main body (341).

The application discloses a structure for realizing high-voltage current detection, which is characterized by the connection of a main input pair and an auxiliary input pair with an output stage NMOS transistor, thereby avoiding the introduction of inherent imbalance due to the current of the detection circuit, reducing the precision of high-voltage current detection, and being beneficial to improving the precision of high-voltage current detection and reducing the number of high-voltage transistors used in the detection circuit.

Provided is a fire detection apparatus that facilitates ensuring detection accuracy of a detection target. A sensor 100 is a fire detection apparatus attached to a ceiling surface 900, and includes an inflow space 400 provided inside the sensor 100, a detection space 300 for detecting a detection target, the detection space 300 being provided at a position on a ceiling surface 900 side of the inflow space 400 on the inside of the sensor 100, a housing section for housing the detection space 300, the housing section being capable of allowing the gas containing the detection target to flow into and out of the detection space 300 through the inflow space 400, and an adjusting portion 15 including a plurality of walls 151 provided in the inflow space 400, the adjusting portion 15 being used to adjust a flow velocity of the detection target flowing into the detection space 300.

The invention provides a roller system space precision detection method and device based on an optical fiber gyroscope. The method comprises the following steps: S1, cleaning dust and rust on the surface of a to-be-detected roller; s2, the gyroscope is placed on the horizontal rigid ground and is started for preheating, so that the operation side of the gyroscope is parallel to the reference roller; s3, enabling the gyroscope device to repeatedly slide along the roller surface within a rated angle range, and executing S4 after a display screen of the gyroscope displays that alignment is completed; s4, measuring direction vectors of intersecting lines of the adjacent planes; s5, performing data credibility evaluation on the direction vector of the intersecting line; if the precision requirement is met, executing S6; and S6, performing right-handed coordinate system-based levelness and parallelism calculation on the direction vector of the intersecting line conforming to the precision. According to the method, the three carried precision gyroscopes can be used for accurately measuring the spatial precision index of the equipment, and a roller system spatial position adjusting scheme is given according to a data processing result, so that the accuracy of the roller system spatial position is ensured.

The invention discloses cotton yarn finished product inspection equipment, and relates to the technical field of cotton yarn finished product inspection, the cotton yarn finished product inspection equipment comprises a detection table, a water tank is fixedly installed at the top of the detection table, and a water inlet pipe fixedly penetrates through the surface of the water tank; and the clamping device comprises a motor, a reciprocating screw rod, an inclined plate, a clamping plate, a fixed cylinder, a roller, a roller I, a fixed frame, a limiting plate, a fixed plate and a connecting block I. According to the cotton yarn finished product inspection equipment, the roller moves to drive the roller I to move, and at the moment, the roller I moves upwards along the surface of the inclined plate; meanwhile, the first rolling wheel moves under the action of the inclined plate to drive the roller to move upwards until the cotton yarn finished product is clamped, automatic clamping of the cotton yarn finished product is achieved, it is avoided that due to improper clamping, the detection precision of the cotton yarn finished product is reduced, meanwhile, the time for workers to fix the cotton yarn finished product is shortened, and the equipment efficiency is improved.

The invention relates to quantitative detection of a semiconductor wet etching solution, in particular to a near-infrared detection method for the content of acid and ammonium acid in an organic system, which comprises the following steps: carrying out uniform formula design on a modeling sample, and calculating the content of acid and ammonium acid in the modeling sample by applying a basic principle of a stoichiometric method through a partial least square method. The method for quantifying the mass fractions of the acid and the acid ammonium in the organic system is formed by associating near infrared spectrum data of a sample with the mass fractions of the acid and the acid ammonium through spectrum pretreatment, analysis waveband selection, determination of optimal modeling parameters such as the optimal number of main factors and a root-mean-square error (RESECV) of cross validation and the like and establishing a model. Compared with a traditional titration method and a gas-phase liquid-phase detection method, the method has the advantages that the time consumption is long (more than 15 minutes) and the precision is poor (more than 0.5%), the interference of similar structures of acid and acid ammonium can be effectively eliminated, and the detection precision is within 0.05%; moreover, the quantity of modeling samples required by the method is only 25-35, so that the modeling workload (the quantity of general near-infrared modeling samples is 100-300) is reduced, and the requirements on accuracy and high efficiency of product content inspection can be met.

The invention discloses a wind driven generator transmission chain vibration detection method based on an echo wall mode microcavity, and relates to the technical field of wind power generation. The wind driven generator transmission chain vibration detection method comprises the following steps: guiding a laser light source into the echo wall mode microcavity based on an optical fiber coupling technology; a vibration response signal at the position of a transmission chain of the wind driven generator is obtained by using the echo wall mode microcavity; and converting the vibration response signal into a digital signal by using a signal processing technology, analyzing and processing the digital signal by combining a digital signal processor, and obtaining vibration information at the position of the transmission chain of the wind driven generator based on a processing result. According to the wind driven generator transmission chain vibration detection method based on the echo wall mode microsphere cavity, the vibration condition of the wind driven generator transmission chain can be detected and analyzed in a high-precision and high-sensitivity mode, and meanwhile the method has the advantages of being capable of resisting interference and adapting to severe environments.

The invention discloses a method and device for testing magnetic hysteresis of an amorphous magnetic core in a magnetic sensor, and belongs to the technical field of amorphous magnetic core magnetic hysteresis testing. The device comprises an upper computer, an acquisition system, a power supply, a current source, a relay, a current line copper rod and a test circuit board; the test circuit board is provided with a clamp and a corresponding magnetic flux gate circuit, an amorphous magnetic core to be tested is connected to the magnetic flux gate circuit through the clamp, and a current line copper rod with the two ends connected with the two ends of a current source penetrates through the amorphous magnetic core. The power supply supplies power to the test circuit board, the acquisition system is used for acquiring an initial offset value output by a zero point of each magnetic flux gate circuit on the test circuit board, and the relay is used for controlling the change direction of the current source. And the acquisition system acquires the offset value of each magnetic flux gate circuit on the test circuit board after the positive change and the negative change of the current source, and hysteresis judgment is carried out through the upper computer according to the change of the offset value. According to the method, the amorphous magnetic core with large zero hysteresis of the sensor can be quickly screened from a production source, and the quality of raw materials is further improved.

The present invention discloses a steel coil edge detection machine based on machine vision, including a movable seat, a support seat is provided at the side end of the movable seat; a storage box is installed on the support seat, a cleaning component is provided inside the storage box, and the cleaning component includes a liquid storage cylinder installed inside the storage box; a driving component is provided inside the storage box, and the special-shaped liquid capsule is squeezed by the movement of the second movable plate, and the liquid inside the special-shaped liquid capsule is transported to the inside of the second pipeline through the pressure valve, and a detection component is connected to the rotating component, and the steel coil edge is detected by the detection component. The steel coil edge detection machine based on machine vision sprays liquid out through the through hole on the rotating rod for cleaning, which reduces the problem of inconvenience in later detection due to more dust on the side end of the steel coil after transportation, and detects the steel coil edge through the detection component. The overall structure is simple, which reduces the problem of increased cost due to complicated structure, and improves the overall practicality.

The invention discloses a light source coupled magnetic domain imaging device and method, and belongs to the technical field of magnetic domain imaging, the device comprises an optical fiber assembly connected in front of a polarizer, and the optical fiber assembly comprises at least two optical fibers; the wavelength division multiplexers are correspondingly connected with the at least two optical fibers respectively; each wavelength division multiplexer is correspondingly connected with a light source assembly, and each light source assembly comprises light sources with at least two colors; the lens assembly is at least arranged on an incident light path of a measured object; light emitted from the at least two optical fibers enters different positions of the lens assembly through the polarizer and reaches an object to be detected, the light emitted from the at least two optical fibers is parallel, light reflected by the object to be detected enters the camera at least through the lens assembly and the polarization analyzer, and the camera is a color camera.

A light detecting device includes: a light detector; a heat exchanger thermally connected to the light detector; a coolant flow channel configured to be connected to the heat exchanger and allow a coolant for cooling the light detector to flow; a pump configured to cause the coolant to flow in the coolant flow channel; and a control unit that controls the pump. The control unit performs control such that a first drive power is supplied to the pump during a detection period in which the light detector performs light detection, and a second drive power is supplied to the pump during a standby period in which the light detector stands by without performing light detection, and the first drive power is smaller than the second drive power.

The invention discloses a cable length detection method, device and equipment and a storage medium, and the method comprises the steps: inputting an initial excitation signal to a to-be-detected cable, so as to obtain an initial impedance spectrogram of the to-be-detected cable; the impedance spectrogram represents the relation between the impedance spectrogram and the impedance of the to-be-detected cable under different frequencies; determining an initial cable length and an initial cable length range according to the initial impedance spectrogram; the initial cable length range comprises a first boundary cable length and a second boundary cable length; determining difference values between the initial cable length and the first boundary cable length and between the initial cable length and the second boundary cable length, and obtaining a first difference value and a second difference value; determining a target excitation signal based on the first difference value and / or the second difference value, so as to determine a target cable length of the to-be-detected cable based on the target excitation signal; it is ensured that the difference value between the target cable length and the target cable length range is within the preset error threshold value, and the accuracy and precision of cable length detection are greatly improved.

The invention relates to a method and device for processing dangerous points along a railway, and the method comprises the steps: obtaining multi-temporal remote sensing image data along the railway, and carrying out the preprocessing of the multi-temporal remote sensing image data; preparing railway line ground feature training sample data with mark information, and marking and preprocessing five types of main ground feature elements; training a deep learning surface feature detection model by using the surface feature training sample data, extracting various surface feature elements along the railway, and converting the surface feature elements into vector data matched with geographic coordinates; dangerous point elements are obtained through change detection, the distance between the change elements and the railway is calculated to divide danger levels, and whether field detection and hidden danger elimination are needed or not is judged. Therefore, the problems that an existing railway line dangerous point detection method is low in detection precision and efficiency, and the detection requirement of large railway line dangerous points cannot be met are solved.

A control device that includes a circuit board, a plurality of heating elements that generate heat that accompanies driving the motor, and a rotation angle sensor that detects a rotation angle of the motor. The circuit board has a power supply input portion to which a driving current of the motor is supplied, a heating element mounting region where the plurality of the heating elements are mounted, and a controller mounting region where the rotation angle sensor is mounted. The power supply input portion, the heating element mounting region, and the controller mounting region are disposed in such an order. The circuit board, as seen from an axial direction of the rotating shaft, protrudes to an outside of a projection region that projects an outer surface of a cylindrical portion of a motor case that surrounds the motor. The power supply input portion is located on a portion out of portions of the circuit board that are on the outside of the projection region.

This utility model relates to the field of infrared imager technology, and specifically discloses an infrared imager for detecting volatile organic compound (VOC) leaks. It includes a detection host, a detection lens, and a support pan-tilt unit. When the device encounters an external impact, the main protective shell, buffer connecting seat, and light-transmitting protective plate form the first line of defense, directly preventing tools, parts, and other external objects from directly contacting the detection lens. This avoids scratching the high-precision optical lens, thereby preventing infrared signal acquisition distortion and ensuring the accuracy of VOC leak detection. If the impact force acts on the front of the light-transmitting protective plate, the two return springs between the light-transmitting protective plate and the main protective shell are compressed synchronously. The elastic deformation of the springs absorbs the impact force, reducing the transmission of the impact force to the buffer connecting seat, the main protective shell, and the inside of the detection host. This protects precision components such as the infrared detector and signal processing module, preventing malfunctions such as decreased detector sensitivity and effectively extending the overall service life of the equipment.

The utility model discloses a wafer processing system and a flower basket frame for loading a flower basket. The wafer processing system comprises a flower basket frame used for loading a flower basket with a wafer, and the flower basket frame is provided with an anti-reverse structure; and the detection piece is used for being matched with the anti-reverse structure to detect the placement direction of the flower basket frame. According to the wafer processing system provided by the utility model, the detection member is arranged, and the basket frame is provided with the anti-reverse mechanism used for cooperating with the detection member, so that the structure is simple, and if the basket frame is placed in a reverse direction, an operator can be rapidly reminded that the placement direction of the basket is wrong. Furthermore, the detection piece comprises a transmitter for transmitting signals and a receiver for receiving the signals, the anti-reversion structure is arranged on a transmission path of the transmitter and the signal receiver, the detection accuracy of the detection piece cannot be reduced along with the increase of time, whether the flower basket is correctly placed or not can be judged only by detecting whether the receiver can receive the signals or not, and the detection accuracy of the flower basket is improved. And the detection accuracy is improved.

The utility model relates to the technical field of hole checking machines, in particular to a hole checking machine for a circuit board, which comprises a rack, a conveying belt is arranged inside the upper part of the rack, and a detection head is arranged on the upper surface of the rack; the adjusting assembly comprises a stand column and an adjusting plate, the stand column is fixedly connected to the upper surface of the rack, the adjusting plate is fixedly connected to the upper surface of the detection head, a positioning plug pin and a positioning assembly penetrate through the position between the stand column and the adjusting plate, and the positioning assembly is located above the conveying belt. According to the utility model, the height of the detection head can be adjusted through arrangement of the adjusting assembly, so that reduction of detection precision caused by large deviation of the distance from the detection head to the circuit board is avoided, and meanwhile, auxiliary limiting can be performed on the circuit board through cooperation with arrangement of the positioning assembly, so that overlarge deviation during placement of the circuit board is avoided; and the detection precision of the circuit board is further improved.

The present invention relates to a sound analysis system, a sound analysis method and a storage medium, which can suppress the decrease in the detection accuracy of sound pressure and perform speech analysis with high accuracy. The sound analysis system comprises: a first and a second sound pressure acquisition unit, each of which is arranged on a device worn by a user, and is respectively arranged at different distances from the user's mouth when the user wears the device, and respectively acquires the sound pressure of the user's voice; a distance estimation unit, which estimates the distance between the first or second sound pressure acquisition unit and the user's mouth based on the sound pressure obtained by the first sound pressure acquisition unit and the sound pressure obtained by the second sound pressure acquisition unit; and a sound pressure correction unit, which calculates the difference between a reference value of the distance between the first or second sound pressure acquisition unit and the user's mouth and the distance estimated by the distance estimation unit, and corrects the sound pressure obtained by at least one of the first and second sound pressure acquisition units based on the difference.

The present invention provides a gas sensor capable of maintaining the detection accuracy of a gas to be measured in a gas to be measured at a high level. A gas sensor (100) for detecting a gas to be measured among a gas to be measured, the gas sensor (100) comprising a sensor element (101) and a control device for controlling the sensor element (101), the control device comprising: a storage unit; the oxygen demand storage unit (43) is used for pre-storing the oxygen demand which should exist in the reference gas chamber (43) when the oxygen concentration in the reference gas in the reference gas chamber (43) is a specified concentration; and a processing unit that performs a regeneration process in which an electric current is passed between a pump electrode (23) disposed at a position different from that in the reference gas chamber (43) and a reference electrode (42) disposed in the reference gas chamber (43), oxygen present in the reference gas chamber (43) is sucked out from the reference gas chamber (43), and thereafter the reference gas chamber (43) is regenerated by the pump electrode (23) and the reference electrode (42). The required amount of oxygen stored in advance in the storage unit is sucked into the reference gas chamber (43).

A row detection system includes: an imaging device mounted to an agricultural machine having one or more wheels, the imaging device being configured to image a ground surface that is traveled by the agricultural machine to acquire time-series images containing at least a portion of the ground surface; and a processing device configured to perform image processing for the time-series images. The processing device is configured to, from the time-series images, select a search region in which to detect at least one of crop rows and ridges, the search region having a size and shape containing at least a portion(s) of the one or more wheels.

The invention discloses conveying equipment for voltage stabilizer machining, and belongs to the technical field of voltage stabilizer machining. Conveying equipment for voltage stabilizer machining comprises a conveyor, a detection box is arranged on the outer side of the conveyor, a partition plate is fixedly connected to the inner wall of the detection box, a motor is fixedly installed in an inner cavity of the detection box, a residual gear is fixedly connected to an output shaft of the motor, and a second large gear is meshed with the outer side of the residual gear; the outer side of the second large gear is fixedly connected with a vertical rod. According to the conveying equipment for machining the pressure stabilizer, by arranging the feeding assembly, when materials needed for machining the pressure stabilizer are placed on a conveyor to be conveyed, an eccentric wheel can be automatically controlled to rotate, and therefore a material pushing plate pushes the materials in an inner cavity of a material storage box to a detection table through a discharging box, so that the materials are conveyed conveniently; therefore, workers do not need to manually place the materials on the conveyor for conveying, and the labor intensity of the workers is reduced.

The application discloses a pry-mounted hydrogen mixing ratio detection device for a gas pipeline, which comprises a sampling pipeline, both ends of the sampling pipeline are used for detachable assembly with the gas pipeline, at least one sampling port is arranged on the sampling pipeline, a hoistable support is provided with a containing position, the sampling pipeline is detachably arranged in the containing position, an analyzer is arranged on the hoistable support and connected with the sampling port, a diffusion pipeline is connected with the analyzer, and the diffusion pipeline is also used for being connected with a diffusion point of the gas pipeline. The pry-mounted device is used for integrating and mounting the sampling pipeline, the analyzer and the diffusion pipeline on the hoistable support, and the pry-mounted device can be hoisted to the gas pipeline as a whole, only the two ends of the sampling pipeline need to be connected with the gas pipeline, and the diffusion pipeline needs to be connected with the diffusion point of the gas pipeline, so that the pipeline is shortened, the viscosity and volume delay of gas flowing in the long pipeline are avoided, the data response period is shorter, the on-site workload and construction time are significantly reduced, and the detection precision can be greatly improved.