408results about How to "Guaranteed matching accuracy" patented technology

The invention discloses a wax injection mold for investment casting of hollow turbine blades and a method for rapidly and accurately manufacturing the wax injection mold. The mold consists of a cavity mold, a mold core and an accessory structure, wherein the cavity mold comprises an upper mold and a lower mold of a combined structure; each mold block forming the cavity mold consists of an external aluminum mold frame, an internal cast zinc alloy inlay and a conformal cooling copper pipe embedded into the inlay; a mold core positioning piece which can be decomposed at a high temperature is arranged on a longitudinal rib of the mold core; and water-soluble core blocks used for forming exhaust openings in the rear edges of the turbine blades are arranged on rear edge ribs of the mold core. The matching precision of the mold core positioning piece and the cavity mold is guaranteed by adopting a cavity mold interior running-in method, and the matching precision of the water-soluble core blocks and the cavity mold is guaranteed by adopting a cavity mold interior adhesion method. The wax injection mold disclosed by the invention is low in manufacturing cost and short in period, and the high wax pattern precision and core positioning precision can be obtained.

The invention relates to the technical field of computers, and provides a target tracking method and device, equipment and a storage medium. The method comprises the steps: calculating the Mahalanobisdistance between each obtained original detection region and each obtained prediction target region; taking the original detection target corresponding to the mahalanobis distance with the minimum value as a basic target to be evaluated; if the number of the to-be-evaluated basic targets is more than one, taking an original detection target in the previous frame of video image corresponding to the prediction tracking target as a to-be-processed target; performing depth feature extraction on each to-be-processed target to obtain a depth feature vector of each to-be-processed target; and matching the depth feature vector of each to-be-processed target in each frame of video image with the depth feature vector of each to-be-processed target in the next frame of video image to obtain a matching result corresponding to each to-be-processed target in each frame of video image, and completing target tracking according to the matching result. The accuracy of target tracking can be improved.

The invention discloses a micro-embedded self-lubricating texture on the surfaces of a gear and a cam and a preparation method thereof. The preparation method comprises the following steps of: performing micro texture processing on the surfaces of the gear and the cam by an Nd: YAG laser processing technology; and embedding a solid lubricant into the micro texture on the surfaces of the gear and the cam by a molding bonding technology of a self-lubricating composite material. The self-lubricating composite material comprises the following formula components in percentage by mass: 15 to 85 percent of polyimide (PI), 0 to 85 percent of polytetrafluoroethylene (PTFE), 10 to 40 percent of MoS2, 0 to 15 percent of WS2, 0 to 16 percent of graphite fluoride, 5 to 15 percent of graphite, 0 to 12 percent of PbO, 0 to 6 percent of antimony trioxide, 0 to 10 percent of CaF2 or BaF2, 0 to 15 percent of hexagonal boron nitride, 0 to 15 percent of nano lubricant and 0 to 5 percent of additive. According to the micro-embedded self-lubricating texture, the self-lubricating texture is subjected to micro embedding on the surfaces of the gear and the cam to ensure that the solid lubricant on the friction surface is stably supplied and uniformly coated, so that the lubrication and anti-wear properties of friction pairs such as the gear and the cam under complicated and harsh operating conditions are improved.

The invention discloses a high-pressure self-oscillation oscillating impulse jet flow nozzle with continuous adjustable cavity length. The high-pressure self-oscillation oscillating impulse jet flow nozzle comprises an inlet nozzle, an adjusting ring, a base and an outlet nozzle, wherein the base is an inner hollow cylinder; the inner cavity of the cylinder is a cylindrical oscillating cavity; the upper end of the inlet nozzle is connected with a high-pressure pipe by external threads arranged on the cylindrical face of the end part of the upper end; the middle of the inlet nozzle is spirally connected with inner ring threads of the adjusting ring by external threads arranged on the outer cylindrical face of the middle; the lower end of the inlet nozzle is spirally screwed into the oscillating cavity of the base; the base is fixedly connected with the adjusting ring and the outlet nozzle respectively by screws, through holes formed in the upper and lower bottom faces of the base, a through hole formed in the adjusting ring and a through hole formed in the outlet nozzle. The high-pressure self-oscillation oscillating impulse jet flow nozzle with the continuous adjustable cavity length has the advantages that aiming at different working pressures, the cavity length of the oscillating cavity can be continuously adjusted by rotating the base, and thus the continuous jet flow is changed into strong impulse jet flow; each part of the nozzle is easily processed, and the replacement is convenient.

The invention discloses a different-source image matching method based on refined feature optimization extraction, which mainly solves the problem of low matching precision in the prior art, and adopts the technical scheme that 1, gradient moduli and directions of an optical image and an SAR image are calculated by adopting different gradient operators respectively; 2, completing region-of-interest calibration by utilizing the specific property of the target in the image; 3, according to the result of the step 1, obtaining edge features of the interested areas of the two images, and obtaininga coarse matching affine transformation matrix between the two images through template matching; 4, obtaining a transformed optical image by using the coarse matching affine transformation matrix, andthen extracting refined features; 5, performing preliminary matching on the refined features, and eliminating singular point interference to obtain a fine matching affine transformation matrix; and 6, obtaining a final affine transformation relation matrix between the optical image and the SAR image according to the results of the steps 3 and 5. The method can achieve the precise registration ofa heterologous image, and can be used for the guidance of an aircraft.

The invention provides a panoramagram generation method which includes the steps that (1) for the same region, a benchmark image and an image to be registered are obtained; (2) pixel characteristic value sequences are generated for the two images respectively; (3) front M pixel points in the two sequences are selected to serve as characteristic points; (4) feature matching is conducted on the two sets of characteristic points, and a matching point pair sequence is obtained; (5) an affine mapping relation is built according to the matching point pair sequence, and a transformed image to be registered is obtained; (6) the shared regions on the two images are fused, and a spherical panoramagram for the same region is obtained; (7) the spherical panoramagram is converted to be an unfolded planar coordinate system from a spherical coordinate system, and a panoramagram is generated. The method is simple in overall procedure, high in speed and capable of generating the panoramagram with high accuracy and small deformation under the conditions that the lens pitch angle is unknown and the rotating angle is unknown and converting the spherical surface of the panoramagram to a plane, and watching is facilitated for users.

The invention discloses a multiple-subarea matching method constraint by a space relation. A plurality of subareas are selected in a matching template as sub-templates, and the sub-templates are separately and simultaneously matched with to-be-matched images. Space position relations among the sub-templates are utilized to realize the accurate matching of the images. The method comprises the following steps: the plurality of subareas are selected in the matching template respectively as the sub-templates; the space relations among the sub-templates are determined; the plurality of sub-templates keep the space position relations unchanged to form combined templates; matching is carried out by utilizing the mobile searching performed by the combined templates on the to-be-matched images, and a plurality of similarity values of the combined templates are obtained; the plurality of similarity values are compared, and a position where a maximum similarity value exists is regarded as an optimum matching position to complete the matching. The method of the invention utilizes the mutual space relations among the plurality of sub-templates to reach the requirements for accuracy and precision of matching. The object identifying performance of the method is substantially improved in real-time performance compared with the conventional large-template gray scale or contour matching algorithms.

The invention relates to a non local stereopair dense matching method based on image gray scale guiding. The non local stereopair dense matching method based on image gray scale guiding includes the steps: performing cost computation: taking an improved HOG operator as a cost measure, computing the cost between homonymous pixels, taking the cost as the means of describing the similarity between the homonymous pixels, and establishing a cost matrix; performing cost accumulation based on image gray scale guiding, and obtaining a stable cost accumulation result; according to a WTA strategy, obtaining an initial disparity image, rejecting a mis-matching point and an occulsion point, and obtaining a refined disparity image; and finally according to the disparity image, generating a dense high-precision three dimensional point cloud. The non local stereopair dense matching method based on image gray scale guiding fully considers the edge gray scale characteristics, has relatively high matching precision on the disparity edge, uses an eight-direction iterative cost accumulation mode so as to increase the matching robustness of a texture lacking area, and can quickly obtain a dense high-precision three dimensional point cloud, thus having great application prospect in the field of aerospace photogrammetry, low altitude photogrammetry and close-range photogrammetry, automatic driving of unmanned vehicle.

The invention discloses an underwater intelligent self-adapted terrain matching method based on terrain information amount and mainly aims to solve the problems that the terrain information amount of an underwater navigation region is not sufficient or not complete so that the error of an aided navigation system is increased and the long-time accurate navigation and positioning requirements of an underwater vehicle cannot be met. The underwater intelligent self-adapted terrain matching method mainly comprises the following steps: calculating different terrain feature parameter values in the navigation region; calculating a terrain information amount aggregative index based on an intelligent method; and carrying out sampling time calculation and a self-adapted terrain matching algorithm based on a terrain information amount aggregative index value. According to the method, the problems that the terrain information amount of the underwater navigation region is not sufficient so that the error of the aided navigation system is increased and the single terrain feature index can cause the incomplete evaluation on the terrain information amount can be effectively improved; the intelligent method is used for comprehensively considering the influence of each index; the sampling time is adjusted by the terrain information amount in a self-adapted manner, the matching range is enlarged and the matching precision is improved.

The invention discloses a matching method for a battery electric vehicle power system. The matching method comprises the following steps: performing initial matching on the selecting parameters of all components of a power system, thereby confirming a matching value of the selecting parameters of all the components; inputting the matching value in an established simulating calculation model, thereby acquiring a simulating calculating value of each performance parameter; if the performance parameter with the simulating calculating value which does not meet the corresponding performance index demand exists, adjusting the corresponding matching value till meeting the demand; acquiring each matching value causing the simulating calculating value to meet the corresponding performance index demand and taking the matching value as a to-be-verified matching value; verifying the to-be-verified matching value on a power system rack, thereby acquiring a verifying value of each performance parameter; if the performance parameter with the verifying value does not meet the corresponding performance index demand exists, adjusting the corresponding to-be-verified matching value till meeting the demand. The matching method has the advantages of shortening the developing period and reducing the development cost.

The invention discloses a rapid image three-dimensional matching method and device. The method includes the following steps that a reference view is over-segmented into a plurality of areas which are not overlapped with one another; the pixel initial matching cost between a pixel i in the reference view and a pixel i' in a target view is calculated; a candidate parallax subset and a support subset at the position of the current pixel i are determined; iterative computation is conducted on the aggregation matching cost of the pixel i, the candidate parallax subset and the support subset are updated and reduced according to the aggregation matching cost, and elements in the candidate parallax subset and elements in the support subset are reduced continuously until the number of candidate parallax in the candidate parallax subset is reduced to a set parallax number; the parallax value corresponding to the maximum matching cost in the candidate parallax subset is selected as a first parallax value of the pixel i. According to the rapid image three-dimensional matching method and device, the matching accuracy is guaranteed, and meanwhile, the algorithm running speed is greatly increased; in addition, a parallax plane fitting method based on the PatchMatch algorithm is used, and therefore the optimal plane parameter estimation value can be converged rapidly.

The present invention provides an aero-engine complete machine residual life prediction method based on gas path performance parameter graphic matching to solve the problem that an aero-engine complete machine residual life is difficult to predict accurately. First, a degradation mode dictionary is constructed by using full-life history degradation data of engines of the same type. Secondly, sensor selection and state parameter dimensionality reduction are performed on data of a to-be-predicted engine. Then, graphic matching is performed on a recession trajectory of the to-be-predicted engine and recession trajectories of reference engines in the degradation dictionary, and life estimation of the to-be-predicted engine and similarity with the reference engines are obtained. Finally, the residual service life of the to-be-predicted engine is obtained via a similarity weighting strategy. According to the method, the residual service life of the aero-engine can be accurately predicted, and life prediction has a great significance for maintenance of the engine.

The invention discloses a grinding machine tool for a dovetail guide rail. The grinding machine tool for the dovetail guide rail comprises a portal frame, a workbench, a machine tool guide rail and a base. A driving assembly frame is transversely fixed to the portal frame and provided with a grinding wheel, two driving mechanisms which are capable of moving transversely and longitudinally are arranged on the left side and the right side of the front face of the driving assembly frame, the grinding wheel can rotate on the driving mechanisms, the driving mode of the workbench is the hydraulic driving mode, the workbench comprises two layers, the bottom face and the side faces of the machine tool guide rail are all fixed to the base, the side faces of the machine tool guide rail are covered with covering plates, the contact faces between the covering plates and the side faces of the U-shaped ends of the base and the contact faces between the covering plates and the machine tool guide rail are provided with lubricating oil grooves, and through lubricating oil grooves are formed in the top of the guide rail face of the machine tool guide rail. After the scheme is adopted, the inclined faces of a V-shaped groove of the dovetail guide rail can be ground fully, the precision of ground products is higher, the driving stability of the workbench of the grinding machine tool can be guaranteed, and the service life of the machine tool is longer.

The invention discloses a local matching method of a three-dimensional model. The method comprises the following steps of: calculating the bending salience of any vertex of the three-dimensional model; generating a sequencing list according to the bending salience and carrying out region growing to form a local vertex set; carrying out secondary surface fitting according to the local vertex set formed by the region growing; identifying a fitting region to be a three-dimensional model local subblock and extracting the features of the three-dimensional model local subblock; carrying out featurecomparison and local matching on the three-dimensional model local subblock; and carrying out overall feature comparison and overall matching on the three-dimensional model. The method disclosed by the invention can be used for matching locals of the three-dimensional model, realizing the local-to-local retrieval and the local-to-overall retrieval of the three-dimensional model and extracting obvious region features of the locals, thereby increasing the matching precision of the method; and shape normalization is not needed any more in a feature extracting process, thereby the stability of feature extraction is guaranteed.

The invention discloses a connecting structure of a panoramic sunroof and a vehicle body. The connecting structure comprises a supporting frame and sunroof glass, wherein the supporting frame is formed by a front beam cover plate, a left supporting plate, a rear top cover and a right supporting plate, the front end of the left supporting plate and the front end of the right supporting plate are connected with the front beam cover plate in an overlap mode, and the rear end of the left supporting plate and the rear end of the right supporting plate and the rear top cover are welded in an overlap joint mode; a main positioning hole and an auxiliary positioning hole are formed in the front beam cover plate, a main positioning pin and an auxiliary positioning pin adhere to the sunroof glass, the main positioning pin is matched with the main positioning hole in the front beam cover plate, the auxiliary positioning pin is matched with the auxiliary positioning hole in the front beam cover plate, and the lower surface of the edge of the sunroof glass directly adheres to the supporting frame through gluing. Not only is the matching precision of installation of the panoramic sunroof ensured, but also the sealability and waterproofness of an installation structure of the sunroof glass are improved.

The invention discloses an automatic member-embedding injection mould. The automatic member-embedding injection mould has the advantages of automatic blanking, accurate positioning, high cooperation precision, and continuous and high efficiency injection moulding process. The automatic member-embedding injection mould comprises an upper die, a lower die, a cylinder and a blanking mechanism; the blanking mechanism comprises a blanking tube, a feeding push block with an accommodation hole is arranged at the lower part of the blanking tube, the feeding push block is positioned in a block pushing groove connected to the feeding push block in a slide mode, a compression extrusion plate is arranged besides the feeding push block, the right side of the compression extrusion plate is contacted to an upper die briquetting in the upper die, a spring is provided at the back of the compression extrusion plate, the spring is in a compaction state while the mould is closed, the blanking mechanism also comprises a feeding push rod driven by the cylinder, the lower end of the feeding push rod just faces to one end of the accommodation hole, a pre-embedding position in the mould cavity is positioned at the lower part of the accommodation hole, and a discharging push rod is provided on the lower die. The automatic member-embedding injection mould has the advantages of automatic feeding and blanking, rapid blanking in place and accurate positioning, the stability is high while injection moulding, and the cooperation precision of the molded product is guaranteed.

The invention relates to an online shaft neck repairing method. The online shaft neck repairing method includes: grinding a worn shaft neck coarsely; welding weld ribs; finishing the weld ribs; machining a bush; mounting the bush and replacing a bearing sequentially on the shaft neck provided with the weld ribs and completing repairing after post processing. By the method, the shaft neck at the cooperative positions of two ends of a shaft and the inner ring of the bearing can be repaired online, repairing time and cost can be favorably saved, and production can be ensured to run smoothly.

The invention discloses an ORB feature extraction and matching method and device. The method comprises the following steps: firstly, converting an original image into a gray level image, performing FAST angular point and HARRIS corner point extraction, centroid calculation and Gaussian blur, and outputting the feature point key information and Gaussian blur images; performing down-sampling on theimage to obtain a plurality of sets of feature point key information and Gaussian blur images; calculating the descriptor information corresponding to the feature point, performing feature matching onthe descriptor information of the two frames of images to obtain the ORB feature matching result; and finally outputting the original image and the ORB feature matching result synchronized with the original image. The problem that a large amount of memory and CPU resources are consumed for identifying the same target image in the prior art is solved. According to the method and the device, the speed for identifying the same target image can be increased, and meanwhile, the real-time performance is guaranteed while the feature extraction and matching accuracy is guaranteed.

The invention discloses an artwork identification method for searching for pictures by using a picture. The method comprises the following steps that S1, when a user inputs a search picture to conducta picture searching request, highly-matched historical pictures are searched for from an experience library, and if the pictures are searched for, search results corresponding to the highly-matched historical pictures and similarities are displayed to the user, otherwise, the second step is started; S2, a Hash algorithm is adopted for conducting gray processing on the search picture to obtain aninformation fingerprint, and rough matching is conducted according to the information fingerprint in a picture library to obtain a first result set; S3, for pictures in the first result set, accordingto stable feature points and sub-picture feature points of the search picture, an SIFT algorithm is adopted for quick matching to obtain a second result set; S4, the SIFT algorithm is adopted for precisely matching pictures in the second result set to obtain final similar pictures, and the pictures are ranked according to the similarities. By means of the method, through rough matching, quick matching and fine matching, on the basis of ensuring the matching precision, the search efficiency is improved.

The invention discloses a processing technology of a robot RV speed reducer needle gear shell, and belongs to the technical field of robot RV speed reducer processing. The processing technology includes the steps that precise casting or forging is carried out on a needle gear shell blank; the needle gear shell blank is clamped after the surface of the needle gear shell blank is machined, and the rotation center of the needle gear shell blank is taken as a positioning reference; the end face of the needle gear shell blank, a bearing position of a roller pin bearing and bearing positions of two main bearings are machined; finish machining is carried out on the inner surface of the roller pin bearing according to the positioning reference; finish machining is carried out on a roller pin groove in line contact with a roller pin of the roller pin bearing according to the positioning reference; inner grooves are simultaneously machined in the bearing positions of the two main bearings in a finish machining mode according to the positioning reference; finish machining is carried out on the outer surface of the needle gear blank. The needle gear shell machined according to the steps improves machining precision and the parallelism degree of the bearing positions of the main bearings, guarantees coaxiality, the position degree and cylindricity of the main bearings after installation, achieves one-time clamping, can meet requirements of multiple process parameters, improves machining precision and installation precision of the needle gear shell, reduces accumulated errors, meets the high-precision requirements, and prolongs service life.

The invention discloses an integrated machining method of a planet carrier of a robot RV reducer, and belongs to the technical field of robot RV reducer machining. The method comprises the steps as follows: forging a first casing and a second casing, and performing hot extrusion on the first casing and the second casing respectively; performing thermal refining; performing tempering; performing finish machining on end surfaces respectively; connecting the first casing with the second casing to be clamped to a clamp, and performing finish machining on inner holes formed in the first casing and the second casing with a center of gyration serving as a locating basis; performing finish machining on outer surface with the locating basis; directly machining inner rings of rolling bearings on the first casing and the second casing; accurately grinding an outer track on each inner ring simultaneously; and performing finish machining bearing positions of three tapered roller bearings on the first casing and the second casing with the location reference, and directly machining outer rings of the tapered roller bearings. With the adoption of the method, the mounting accuracy, the manufacturing accuracy and the transmission accuracy are ensured, the requirement for high accuracy is met, the service life is prolonged, machining and assembling errors and accumulative errors are reduced, the output torque is increased, and the machining cost is effectively reduced.

The invention relates to a butt joint-precise inductor assembly machine. The machine comprises a frame and a power distribution control box; the frame is provided with a conveying device; an iron sheet inserting device, a pressing ring device and an iron core inserting device are arranged above the conveying device in sequence; the conveying device is matched with a positioning device; the positioning device includes a positioning base arranged on a conveying base; the positioning base is provided with a positioning lifting cylinder; the positioning lifting cylinder is provided with a positioning lifting block matched with a positioning lifting slide rod on the positioning base; and the positioning lifting block is provided with a positioning pin matched with a positioning pin sleeve arranged on a conveying carrier. The machine is provided with the positioning device in the conveying device; and through insertion matching between the positioning pin arranged on the positioning lifting block and the positioning pin sleeve arranged on the conveying carrier of the conveying device, the conveying device stops conveying, the inertia influence is eliminated, the butt joint precision between the conveying carrier and each assembly part is improved, and the yield is largely increased.

The invention discloses a message classifying method based on rule information entropy. The message classifying method based on the rule information entropy includes: calculating regular stray attribute subsets on an attribute domain with regular classified messages through preprocessing on classification rules, using a regular attribute weight vector to calculate weighting distance afterwards, and then analyzing subspace straying influence factors of regular weighting neighbor domains, and generating frequent matching subsets for matching messages by comparing the subspace straying influence factors with straying factor threshold value. According to the message classifying method based on the rule information entropy, subsequent message matching had the regular frequent matching subsets with no-straying attributes by being compared with prior message matching, matching efficiency is improved, and simultaneously time expenditure for generating the frequent matching subsets through the preprocessing of the classification rules is smaller than time expenditure for matching a whole data stream, and transmission performance of an algorithm used in the message classifying method is higher than transmission performance of the algorithm before the preprocessing.