Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

39results about How to "Avoid jagged" patented technology

Binary tree-based SVM (support vector machine) classification method

The invention discloses a binary tree-based SVM (support vector machine) classification method. The binary tree-based SVM classification method comprises the following steps: 1, acquiring signals, namely detecting working state information of an object to be detected in N different working states through a state information detection unit, synchronously transmitting the detected signals to a data processor, and acquiring N groups of working state detection information which corresponds to the N different working states; 2, extracting characteristics; 3, acquiring training samples, namely randomly extracting m detections signals to form training sample sets respectively from the N groups of working state detection information which are subjected to the characteristic extraction; 4, determining classification priority; 5, establishing a plurality of classification models; 6 training a plurality of classification models; and 7, acquiring signals in real time and synchronously classifying. The binary tree-based SVM classification method is reasonable in design, easy to operate, convenient to implement, good in use effect and high in practical value; and optimal parameters of an SVM classifier can be chosen, influence on the classification due to noises and isolated points can be reduced, and classification speed and precision are improved.
Owner:XIAN UNIV OF SCI & TECH

Intelligent steel cord conveyer belt defect identification method and intelligent steel cord conveyer belt defect identification system

The invention discloses an intelligent steel cord conveyer belt defect identification method and an intelligent steel cord conveyer belt defect identification system. The identification method includes the following steps: (1) electromagnetic loading; (2) defect signal acquisition; (3) feature extraction; (4) training sample obtainment; (5) class priority determination; (6) multi-class model establishment; (7) multi-class model training; (8) real-time signal acquisition and synchronous class: electromagnetic detection units are adopted for real-time detection, detected signals are synchronously inputted into a data processor, features are extracted and then sent into established multi-class models, and the defect class of a detected conveyer belt is automatically outputted. The identification system comprises an electromagnetic loader, a plurality of electromagnetic detection units, the data processor and an upper computer, the data processor can automatically output the defect class of the detected conveyer belt, and the upper computer bidirectionally communicates with the data processor. The design of the invention is reasonable, the invention is easy to operate and convenient to put into practice, moreover, the using effect is good, the practical value is high, the reliability of conveyer belt defect detection is enhanced, and the efficiency of defect identification is increased.
Owner:XIAN UNIV OF SCI & TECH

Method for optimizing disaggregated model by adopting genetic algorithm

The invention discloses a method for optimizing a disaggregated model by adopting genetic algorithm. The method comprises the following steps of: 1, acquiring a training sample, wherein the acquiring process includes signal acquisition, characteristic extraction and sample acquisition; 2, selecting kernel function: radial basic function is selected as the kernel function of a disaggregated model needing to be established, and the disaggregated model is a support vector machine model; and 3, determining penalty parameter C and kernel parameter gamma: a genetic algorithm is adopted to optimize the penalty parameter C of the disaggregated model needing to be established and the kernel parameter gamma of the selected radial basic function and the optimization process includes population initialization, calculation on the fitness value of each individual in the initialized population, selection operation, interlace operation and variation operation, calculation on the fitness value of each individual in the offspring, selection operation and judgment on whether the termination condition is met. The method is reasonable in design, simple and convenient in operation, convenient to realize and good in use effect and high in practical value; the classification precision of the obtained disaggregated model is high, the training speed is high and the number of support vectors is less.
Owner:XIAN UNIV OF SCI & TECH

Method and device for deinterlacing

The invention provides a method and device for deinterlacing. The method comprises the following steps: using difference values between pixels, corresponding to the pixel for interpolation, in the previous field and the subsequent field and the pixel values, corresponding to the next pixel for interpolation, in the previous field and the subsequent field, as well as the movement weight value of the previous interpolation pixel to calculate the movement weight value of the pixel for interpolation to calculate the inter-field interpolation and the in-field interpolation of the pixel for interpolation; using the inter-field interpolation, the in-field interpolation and the movement weight value of the pixel for interpolation to calculate the initial pixel value of the pixel for interpolation; calculating the relativity of the current field in multiple directions according to the difference values among the pixel values of the pixels in multiple directions in the current field; selecting multiple pixels in the direction with the maximal relativity and the pixel value of the pixel corresponding to the pixel for interpolation in the previous field for filtering; calculating the compensation pixel value, and calculating the determined pixel value of the pixel for interpolation according to the initial pixel value, the compensation pixel value and the in-field interpolation. The device is used for realizing deinterlacing by adopting the method. The device for deinterlacing is small in amount of calculation, lower in requirement on a hardware device and good in output picture quality.
Owner:APPOTECH

Reworking method for copper-clad plate circuit manufacturing abnormal products and printed circuit board

The invention discloses a reworking method of copper-clad plate circuit manufacturing abnormal products. The reworking method comprises the following steps of acid pickling, film pasting, engineeringdata compensation adjustment, secondary alignment exposure, development, secondary etching, film stripping and inspection. The reworked abnormal product is a copper-clad plate subjected to one-time circuit manufacturing, oxides, oil stains, fingerprints and the like on the surface of the plate are removed in the acid pickling step, and the copper surface of the plate is roughened, so that subsequent copper plating of the copper surface is facilitated. In the step of engineering data compensation adjustment and the step of secondary alignment exposure, it is guaranteed that a short-circuit areacan be etched off through secondary etching, meanwhile, the problems of line negligence, sawteeth, steps and the like after secondary etching can be avoided, and the quality of plate reworking is improved. The invention further discloses a printed circuit board, the printed circuit board is manufactured by adopting the reworking method for manufacturing the abnormal product through the copper-clad plate circuit, recycling of the abnormal product is achieved, and the production cost is reduced.
Owner:广州杰赛电子科技有限公司

Arc welding wire feeding heat conduction mechanism

PendingCN112605501AAvoid jaggedWire offset problem solvingArc welding apparatusReciprocating motionEngineering
The invention provides an arc welding wire feeding heat conduction mechanism which comprises a heat conduction nozzle, a first wire feeding mechanism and a control mechanism. A welding wire is conveyed into the heat conduction nozzle through the first wire feeding mechanism, and the heat conduction nozzle and the first wire feeding mechanism are located on the same straight line so that the welding wire between the heat conduction nozzle and the first wire feeding mechanism can be kept in a straight line state. The control mechanism is connected with the first wire feeding mechanism so as to control the first wire feeding mechanism to do reciprocating motion in the moving direction of the welding wire, when the first wire feeding mechanism gets close to the heat conduction nozzle, the first wire feeding mechanism clamps the welding wire and drives the welding wire to move in the direction of the heat conduction nozzle, and when the first wire feeding mechanism gets far away from the heat conduction nozzle, the first wire feeding mechanism loosens the welding wire. According to the arc welding wire feeding heat conduction mechanism, in the welding wire conveying process, the welding wire can be prevented from being in a sawtooth shape, and the problem of welding wire deviation caused by heat conduction nozzle wear is solved.
Owner:佛山宇仁智能科技有限公司

Intelligent steel cord conveyer belt defect identification method and intelligent steel cord conveyer belt defect identification system

The invention discloses an intelligent steel cord conveyer belt defect identification method and an intelligent steel cord conveyer belt defect identification system. The identification method includes the following steps: (1) electromagnetic loading; (2) defect signal acquisition; (3) feature extraction; (4) training sample obtainment; (5) class priority determination; (6) multi-class model establishment; (7) multi-class model training; (8) real-time signal acquisition and synchronous class: electromagnetic detection units are adopted for real-time detection, detected signals are synchronously inputted into a data processor, features are extracted and then sent into established multi-class models, and the defect class of a detected conveyer belt is automatically outputted. The identification system comprises an electromagnetic loader, a plurality of electromagnetic detection units, the data processor and an upper computer, the data processor can automatically output the defect class of the detected conveyer belt, and the upper computer bidirectionally communicates with the data processor. The design of the invention is reasonable, the invention is easy to operate and convenient to put into practice, moreover, the using effect is good, the practical value is high, the reliability of conveyer belt defect detection is enhanced, and the efficiency of defect identification is increased.
Owner:XIAN UNIV OF SCI & TECH

Method for optimizing disaggregated model by adopting genetic algorithm

The invention discloses a method for optimizing a disaggregated model by adopting genetic algorithm. The method comprises the following steps of: 1, acquiring a training sample, wherein the acquiring process includes signal acquisition, characteristic extraction and sample acquisition; 2, selecting kernel function: radial basic function is selected as the kernel function of a disaggregated model needing to be established, and the disaggregated model is a support vector machine model; and 3, determining penalty parameter C and kernel parameter gamma: a genetic algorithm is adopted to optimize the penalty parameter C of the disaggregated model needing to be established and the kernel parameter gamma of the selected radial basic function and the optimization process includes population initialization, calculation on the fitness value of each individual in the initialized population, selection operation, interlace operation and variation operation, calculation on the fitness value of each individual in the offspring, selection operation and judgment on whether the termination condition is met. The method is reasonable in design, simple and convenient in operation, convenient to realize and good in use effect and high in practical value; the classification precision of the obtained disaggregated model is high, the training speed is high and the number of support vectors is less.
Owner:XIAN UNIV OF SCI & TECH

Piercing device and method for beverage capsules

The invention discloses a piercing device for beverage capsules. The piercing device for beverage capsules comprises a bottom mold and a punch, wherein the bottom mold comprises a capsule positioninggroove and a piercing positioning structure; the capsule positioning groove is an annular inner groove; a side wall of the capsule positioning groove consists of a vertical main positioning plane anda secondary positioning plane of which the top is inclined outwards to form an oblique plane; the main positioning plane is projected out of the secondary positioning plane so that the capsule positioning groove is step-shaped; the piercing positioning structure is arranged in the center of the bottom surface of the capsule positioning groove, and is a hollow cylinder which is projected out of thebottom surface of the capsule positioning groove; the punch comprises a cylindrical head and a tail; the outer diameter of the cylindrical head is smaller than the inner diameter of the piercing positioning structure; the tail is fixedly connected with a piercing power mechanism; and the vertical projection of the punch drops in the piercing positioning structure. The invention further provides apiercing method. A pierced region of a capsule shell pierced on the basis of the piercing device and method is flat and smooth, and thus, the piercing device and method for beverage capsules are suitable for efficient industrial production of an assembly line.
Owner:无锡鼎加弘思饮品科技有限公司

Binary tree-based SVM (support vector machine) classification method

The invention discloses a binary tree-based SVM (support vector machine) classification method. The binary tree-based SVM classification method comprises the following steps: 1, acquiring signals, namely detecting working state information of an object to be detected in N different working states through a state information detection unit, synchronously transmitting the detected signals to a data processor, and acquiring N groups of working state detection information which corresponds to the N different working states; 2, extracting characteristics; 3, acquiring training samples, namely randomly extracting m detections signals to form training sample sets respectively from the N groups of working state detection information which are subjected to the characteristic extraction; 4, determining classification priority; 5, establishing a plurality of classification models; 6 training a plurality of classification models; and 7, acquiring signals in real time and synchronously classifying. The binary tree-based SVM classification method is reasonable in design, easy to operate, convenient to implement, good in use effect and high in practical value; and optimal parameters of an SVM classifier can be chosen, influence on the classification due to noises and isolated points can be reduced, and classification speed and precision are improved.
Owner:XIAN UNIV OF SCI & TECH

Dividing and cutting machine with straight knife dividing and cutting mechanism and using method of dividing and cutting machine

The invention discloses a dividing and cutting machine with a straight knife dividing and cutting mechanism and a using method of the dividing and cutting machine. The dividing and cutting machine comprises a power distribution cabinet, fifteen knife bases and two symmetrical triangular plates, wherein a controller is installed on the inner side wall of the power distribution cabinet, the rear surface of the power distribution cabinet is in threaded connection with a slide carriage box through screws, one side of the slide carriage box is fixedly connected to a material storage roller through a coupler, one side of the slide carriage box is fixedly connected to two connecting rollers through couplers, a straight knife module is designed on the basis of a jaw structure of the knife bases and can be rapidly assembled and disassembled, the jaw structure and a cross beam strip can be accurately buckled, a guide rail groove can be moved in a double-point matching mode through a protruding block in a moving process, the mechanical characteristic of stepped adjustment of a pawl and a ratchet bar is utilized in the moving process, the cutter bases form reverse stroke stepped feeding motion, so that the cutter bases are accurately positioned at each scale of a scale plate in the moving process, and the requirements of accurate moving and positioning are met.
Owner:苏州安嘉卓电子有限公司

A video super-resolution method and device

The embodiment of the invention provides a method and device of the super-resolution of a video. In the method, first, sampling is conducted on an input video sequence, then source image blocks which are determined by every first video frame in the input video sequence, first video frames where the source image blocks belong to, adjacent video frames of the first video frames where the source image blocks belong to, the corresponding video frames in the video sequence after the first video frames are sampled and pixel value entries and structure entries among all image blocks to be compared are used for working out the similar distance between the source image blocks and the image blocks to be compared, wherein the image blocks to be compared are determined in the adjacent vide frames of the corresponding video frames, the image blocks to be compared, which have the smallest similar distance, are the similar image blocks of the source image blocks, at last, all the similar image blocks corresponding to all the source image blocks in every first frame video and the corresponding similar distances are calculated to obtain a target video sequence containing second video frames. The method and device solve the problems that sawtooth happens to an existing method of the super-resolution and the visual effect of the video is poor.
Owner:PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products