68results about How to "Reduce testing labor intensity" patented technology

The invention relates to an online automatic detection method of fabric defects based on machine vision and a device thereof, wherein the clear and integral standard fabric images without the defects of the fabric are shot on a batching and burling machine as a standard image template by utilizing an industrial camera in order to solve the problems of great labor intensity and poor detection quality of the traditional manual detection method; the corresponding characteristic parameters are extracted and stored into a computer; the range of the fabric defect detection characteristic parameters is set according to the requirements of users; the fabric images which are shot in real time are transmitted to the computer to be compared with the standard image template by utilizing the industrial camera and compared with the standard characteristic parameters; if the fabric characteristic parameters are not in conformity with the set requirements, the alarm is started by detection software; the defects are analyzed; and the printing of defects labels is executed. The invention has the advantages of high detection accuracy and high speed; and the labor intensity is greatly reduced.

The invention discloses a machine vision-based method for detecting and sorting polycrystalline silicon solar energy. The method comprises the following steps of: 1) allowing a polycrystalline silicon solar cell to pass through an image acquisition area, and acquiring a corresponding image through a charge coupled device (CCD) camera; 2) performing image preprocessing on the acquired image, wherein the image preprocessing comprises image extraction, gray processing, image noise filtering, image enhancement, edge detection and solar cell positioning; and 3) performing image recognition, comparing the parameters of the polycrystalline silicon solar cell acquired in the step 2) with a template, performing image similarity measurement, performing color classification to sort the colors. The grey level histogram of the polycrystalline silicon solar cell is analyzed and is compared with a standard sample image for calculation to obtain the standard deviation of the histogram distribution, and a classification decision is made through the obtained standard deviation. Through the proving of the experiment proves, the method has the advantages that the detection speed is high and the accuracy is high and the detection requirements can be met.

The invention is the online detection method of the machine vision system to the printing and dyeing color difference. It can solve the big working strength and the bad detection quality of detecting the color difference by human. The invention makes the standard image module of the detecting print-dyeing color difference according to the client sampling cloth, which the RGB value, saturation value and color value are as the standard value of detecting dyeing color difference; it uses the national nine-degree colorimetric card as the standard of dyeing color difference; the RGB value, saturation value and color value are set as the detection parameters and it sets the parameter precision range according to the user need. While the environment light changing, the invention can compensate the light strength of shoot image automatically to determine the production dyeing color difference precisely. The invention meets the practical condition of the user dyeing color difference detection and improves the precision and detection speed of the color difference detection.

The invention discloses an aviation electric connector pin position deviation detection method and belongs to the field of machine vision high-precision detection, for solving the problems of low efficiency and proneness to missed detection existing in manual detection of an electric connector. According to the aviation electric connector pin position deviation detection method, pin template images with different specifications are made; electric connector pin images are obtained; an area of interest with the pin images is reserved, and background interference is filtered; coordinates of optimal matching points are obtained as approximate positions of pins by performing template matching on the electric connector pin images by use of the pin template images; search is carried out by taking the approximate positions of the pins as centers, pin bright spots are sought, calculated mass center positions are taken as position information of the pin centers under an image coordinate system, then after the position information is converted into position information under an actual physical coordinate system, the position information under the actual physical coordinate system is compared to an electric connector contact hole position arrangement standard in a national standard, and whether pin position deviations are within an allowed scope is determined. The method has the advantages of high precision, high automation efficiency and low miss rate.

The invention provides a method for automatically detecting the bending of injector steel needles by using a machine vision system. The method comprises the following steps of: setting transverse bending values of needle points of the steel needles to be detection parameters; setting detection accuracy and qualified ranges of different detection parameters according to requirements of users; starting a camera by using external trigger and control signals to shoot pictures of the steel needles operated on line in real time, and transmitting the shot pictures to a computer for detection; processing the pictures by using the computer by a picture algorithm; extracting the pictures in which the steel needles are bent, and computing the transverse bending values of two bending needles; and judging whether a product is a qualified product or a waste product through the computed transverse bending values, and eliminating the waste product from a specified material outlet through the externaltrigger and control signals. By the method, the injector steel needles can be detected at high accuracy and high speed, and the yield of the product can be effectively ensured.

The invention discloses an automatic detection system for super draught of a navigation vessel. The automatic detection system comprises a measuring head, a measuring head lifting subsystem, a real-time data acquisition device, a data communication interface, a data processing and controlling subsystem and a display and operation panel, wherein the measuring head is connected to a steel wire rope of the measuring head lifting subsystem; the input end of the real-time data acquisition device is connected with the measuring head; the output end of the real-time data acquisition device is connected with the data processing and controlling subsystem through the data communication interface; and the data processing and controlling subsystem is connected with the display and operation panel. According to the automatic detection system, non-contact type automatic detection of (super) draught of the vessel during navigation is realized, the detection efficiency and the detection precision are increased and the detection cost is reduced.

The invention discloses an on-line detection method of a PVC round tube surface flaw based on a machine vision system, comprising the following steps: arranging four industrial cameras on a tuber surface, acquiring video signals and transferring the video signals into a PC computer; carrying out pre-processing; solving an actual area corresponding to each pixel; performing cosine correction on an image to enable the image area approximate to the real curved surface area of a tube; setting time for cameras to shoot regularly, storing shot images in an engineering work space and covering the images shot before, and correcting the images; calculating the amount and areas of heterogeneous pixels in the images; and sending a signal to control a flaw mark executing mechanism to mark near the flaws by the PC computer when the set minimum threshold valve is reached, accumulating the areas and amount of the connected regions of the heterogeneous pixels in the images, clearing and weighting the areas and amount of the connected regions of the heterogeneous pixels in the images in regular time, detecting the surface flaw of the tube so as to obtain the rating of the surface flaw. The invention can automatically detect the tube surface flaw.

The invention relates to the field of automobile parts processing. The invention discloses a seal testing device for an automobile clutch booster. The seal testing device comprises a motherboard and an air cylinder, wherein a connector limiting plate and an air cylinder mounting plate are arranged on the motherboard, an air cylinder is arranged at one side of the air cylinder mounting plate, an output shaft of the air cylinder is connected with a tappet passing through the air cylinder mounting plate, a bearing pedestal provided with a bearing is arranged on the motherboard between the connector limiting plate and the air cylinder mounting plate, a rotary locating plate provided with a through hole is arranged on the bearing pedestal and can rotate on the bearing pedestal, and the rotary locating plate is provided with a positioning pin; an U-shaped hole is opened in the connector limiting plate, and the U-shaped hole in the connector limiting plate corresponds to the through hole of the rotary locating plate and the tappet. When the seal testing device for the automobile clutch booster, disclosed by the invention, is used for seal testing of the clutch booster, a workpiece can rotate easily, so that testers can carry out brushing testing conveniently, therefore labor intensity in testing is reduced, high work efficiency is achieved and testing quality is enhanced.

The invention provides a method for automatically detecting back-stitching of a steel needle of an injector by using a mechanical vision system. The method comprises the following steps of: setting the top height of the steel needle as a detection parameter; setting the detection accuracy and qualified range of different detection parameters according to a user requirement; starting a camera by using an external trigger and control signal to shoot an image of an on-line operating steel needle in real time, and transmitting the shot image to a computer for detection; processing the image by using the computer with an image algorithm, and extracting the image of the top of the steel needle; calculating the top height of the steel needle, and judging whether a product is a qualified product or a rejected product by using the calculated top height of the steel needle; and eliminating the rejected product from an appointed discharge hole by using the external trigger and control signal. The method has the advantages that: the detection accuracy and speed of the back-stitching of the steel needle of the injector are high; and the yield of products can be effectively guaranteed.

The invention provides a method for automatically detecting burrs of injector steel needles by using a machine vision system. The method comprises the following steps of: setting transverse lengths of protruded burrs and sunk burrs of needle point parts of the steel needles to be detection parameters; setting detection accuracy and qualified ranges of different parameters according to requirements of users; starting a camera by using external trigger and control signals to shoot pictures of the steel needles operated on line in real time, and transmitting the shot pictures to a computer for detection; processing the pictures by using the computer by a picture algorithm; extracting the pictures in which the burrs are generated, and computing the dimensions of two burrs; and judging whethera product is a qualified product or a waste product through the computed dimensions of the burrs, and eliminating the waste product from a specified material outlet through the external trigger and control signals. By the method, the burrs of the injector steel needles can be detected at high accuracy and high speed, and the yield of the product can be effectively ensured.

The invention discloses a detection device for a mechanical cam controller; a driving mechanism is used for driving the mechanical cam controller and an encoder to rotate by a coupler; the encoder is used for sending the acquired crankshaft angular velocity information into a control system; a movement monitoring signal generator is used for acquiring crankshaft status signals and sending the signals into the control system; a photoelectric position sensor is used for acquiring the switch position of a cam group and sending the switch position into the control system by a photoelectric signal receiver; and a switch contact is used for sending a switch power-on opening and closing signal into the control system. The control system can be used for processing the signals by an internal computing system, so that the test aim can be achieved. The detection device is suitable for testing the performances and the service life of the mechanical cam controller, can realize multi-parameter measurement, especially the measurement for repeatability precision, and has the characteristics of being accurate in test results, visual, quantitative, small in size and high in efficiency.

The invention provides a method for automatically detecting an abnormal shape of an injector part by using a mechanical vision system. The method comprises the following steps of: pre-shooting an image of a standard part as an abnormal shape standard image, and storing the image into a computer; setting a difference proportion of the abnormal shape standard image as a detection parameter; setting the detection accuracy and qualified range of different detection parameters according to a user requirement; starting a camera by using an external trigger and control signal to shoot the image of the abnormal shape of an on-line operating injector part in real time, and transmitting the shot image to the computer for detection; processing the image by using the computer with an image algorithm, and extracting the image of the abnormal shape of the injector part; calculating an abnormal shape difference value, and judging whether a product is a qualified product or a rejected product by using the calculated abnormal shape difference value; and eliminating the rejected product from an appointed discharge hole by using the external trigger and control signal. The method has the advantages that: the detection accuracy and speed of the abnormal shape of the injector part are high; and the yield of products can be effectively guaranteed.

The invention discloses an automatic detection device for an industrial frequency transformer and a detection control method of the automatic detection device, and relates to the technical field of industrial frequency transformer detection. According to the automatic detection device for the industrial frequency transformer and the detection control method of the automatic detection device, the detection efficiency is high, the industrial frequency transformer is immediately fed into a code printing conveying unit for code printing after being detected, and the intelligent automation degree is high. The automatic detection device comprises a controller, a turning-over conveying unit, the code printing conveying unit, a qualified product container and four detection conveying units. Each of the four detection conveying units comprises a detection connecting mechanism and a detector, wherein the detection connecting mechanism comprises a detection support and a detection anvil which is arranged on the detection support in an up-down moving manner, and the detection anvil can move up and down over a detection area. The four detection conveying units are provided with the four detectors and the four detection anvils in all, and the four detectors are in one-to-one electric connection with the four detection anvils.

The invention discloses a test bed for the braking performance of an automobile/a train. The test bed is characterized in that a signal acquisition part of a sensor is composed of a left detection unit group and a right detection unit group which are formed by linearly arranging a plurality of detection units, and the left detection unit group and the right detection unit group are in symmetric distribution. A braking detection unit comprises a braking sand-adhering plate; the braking sand-adhering plates on the left detection unit group and the right detection unit group are independent, with a distance of 8 mm; each braking detection unit and each weighing detection unit work independently to respectively realize acquisition of braking data and weight data and are independently connected with a signal acquisition processing device; and the signal acquisition processing device is electrically connected with a data processing system. The automobile/train is subjected to multi-axial overall online detection, so that the braking time sequence of the vehicle, the dynamic braking power of the entire vehicle, the poor braking process, the coordinate time and the like of the entire vehicle can be detected in one braking process, therefore, the labor intensity of detection is alleviated, the detection efficiency is improved, and the braking performance of the vehicle can be reflected more truly.

The invention provides a method for automatically detecting a foreign matter of a medical product package by using a machine vision system, which comprises the following steps of: pre-shooting an image of a medical product packaging bag without the foreign matter, identifying various parts in the packaging bag, and numbering the various parts to form a standard library; setting whether a part which does not exist in the standard library exists in the image of the medical product packaging bag as a detection parameter; starting a camera through an external trigger and control signal to shoot the image of the on-line operated packaging bag in real time, transmitting the shot image to a computer for detection, and processing to identify the various parts in the packaging bag by using the computer through an image algorithm and a pattern recognition algorithm; and detecting whether any one part in the packaging bag has a corresponding number in the standard library or not, judging whether the product belongs to a qualified product or a defective product which can be reprocessed, and removing the defective product which can be reprocessed from a specified discharge hole through the external trigger and control signal. By the method, the detection accuracy and speed of the foreign matter of the medical product package are high, and the product yield can be effectively ensured.

The invention provides a method for automatically detecting a missed accessory during automatic assembly of an injector by using a machine visual system. The method comprises the following steps of: pre-shooting an assembly image of a qualified injector product to be used as a standard assembly image and stored in a computer; setting the existence of each accessory in the assembly image of the injector as a detection parameter; starting a camera by using an external trigger and control signal to shoot an image of the missed accessory during automatic assembly of the injector operating on line in real time; transmitting the shot image to the computer for detection; processing the transmitted image by using the computer by an image algorithm, and extracting the image of the missed accessory during automatic assembly of the injector; detecting whether any accessory in the standard assembly image has a corresponding image in the assembly image of the injector; judging whether the product is a qualified product or a degraded product which can be processed again; and removing the degraded product which can be processed again from an appointed discharge outlet by using the external trigger and control signal. By the method, the detection precision and the detection speed of the missed accessory during automatic assembly of the injector are high, and the qualification rate of the product can be effectively ensured.

The invention provides a method for automatically detecting the plugging of injector steel needles based on air pressure. The method comprises the following steps of: connecting a tool strip from the bottom of a needle seat to a pressure pump, and arranging an air pressure valve on a pump air path of the pressure pump; acquiring trigger and control signals, which are synchronous with a productionprocess, of the pressure pump by using a computer, starting the pressure pump by using external trigger and control signals to pump air from the bottom of the needle seat to the steel needles, opening the air pressure valve simultaneously, and transmitting air pressure values of all the steel needles which are detected by a pressure gauge when the air is started to be pumped and after the air is pumped for 0.5 seconds to the computer for detection; and judging whether a steel product is a qualified product or a waste product through the computed change rate of the air pressure generated when the air is pumped within 0.5 seconds, and eliminating the waste product from a specified material outlet through the external trigger and control signals. By the method, the plugging of the steel needles can be detected at high accuracy and high speed, and the yield of the product can be effectively ensured.

The invention provides a detector and a detection method of an elevator overload protection device. The detector comprises a suspension mechanism, a hydraulic mechanism, a baseplate and an adjustable casing group, wherein the suspension mechanism comprises a suspension frame and a lifting belt used to limit the farthest distance of the suspension frame relative to a rope hitch plate; the hydraulic mechanism comprises a hydraulic jack and a pressure detector, the top end of an adjustment screw rod of the hydraulic jack is equipped with a top plate used to press against the suspension frame and make the hydraulic jack apply loads with the suspension frame as supporting during work, and the pressure detector is used to detect the value of loads applied by the hydraulic jack; the baseplate is located under the hydraulic jack and used to transmit the loads applied by the hydraulic jack; and the adjustable casing group is located under the baseplate and comprises a plurality of adjustable casings, one end of each adjustable casing is equipped with a casing used for cup-jointing of a rope hitch rod, and the other end is equipped with an adjustment mechanism which is used to adjust height of the adjustable casing. By applying the detector and the detection method of the elevator overload protection device provided by the invention, efficient and high-precision detection can be realized to the overload protection device through the rational structure and simple and convenient operations.

The invention discloses a spectrophotometric detector for detecting methanal and ammonia in air. The spectrophotometric detector comprises a bottle sleeve, a cylindrical spectrophotometric detecting bottle, a photosensitive sensor and a light emitting diode, wherein the bottle sleeve is composed of a base and a shading cap, and the cylindrical spectrophotometric detecting bottle is arranged in the bottle sleeve; the photosensitive sensor is arranged on the side wall of the base and positioned at one side of the spectrophotometric detecting bottle; the light emitting diode is used for emitting detecting light and gathering the detecting light onto the photosensitive sensor; shading rubberized fabrics are arranged on the light emitting diode and the photosensitive sensor; the light emitting diode is composed of a 412nm light emitting diode and a 630nm light emitting diode. The spectrophotometric detector integrates a phenol reagent method and a diacetone method for detecting methanal and a Nessler reagent method for detecting ammonia and can freely switch the methods as required in use, so that the detection efficiency is greatly improved, and the labor intensity of detection is reduced.