64 results about "Abnormal positions" patented technology

The invention discloses an AI substitute inspection method and system based on multi-modal perception, and relates to the technical field of intelligent detection. According to the method, images, audios, environmental parameters and equipment state data of an inspection area are synchronously collected through a multi-modal sensor array, and after space-time alignment preprocessing, multi-modal features are extracted and input into a pre-trained fusion model to generate unified feature representation. The fusion model adopts a Transform architecture to realize cross-modal feature interaction, an anomaly detection algorithm is used to identify and classify anomalies, a confidence coefficient is calculated in combination with an evidence theory, and finally an inspection report containing anomaly positions, types and processing suggestions is generated. According to the invention, the information limitation of single-mode inspection is solved, the detection accuracy and robustness in a complex environment are improved, unmanned inspection in a high-risk scene is realized, the labor cost is reduced, the safety is guaranteed, and the method is suitable for automatic inspection in the fields of industrial equipment, public facilities and the like.

The application relates to the technical field of data monitoring, in particular to a pipeline abnormality monitoring method and device, electronic equipment and a medium. The method comprises the following steps: comparing pressure values of each substation with corresponding preset standard pressure values of each station to determine whether an initial abnormal substation exists; if yes, determining a monitoring range corresponding to the initial abnormal substation according to an initial abnormal position; determining corresponding noise frequency and noise characteristics based on sound monitoring data corresponding to the monitoring range, and determining a first weight value based on the same; determining a predicted influence value according to the noise frequency and the noise characteristics; determining a pressure difference value by comparing the pressure value corresponding to the initial abnormal substation with the corresponding preset standard pressure value, and determining a second weight value according to the predicted influence value and the pressure difference value; determining whether the monitoring range is abnormal according to the first weight value and the second weight value, and if yes, generating warning information based on the monitoring range. The application can discover the existing abnormality of a transportation pipeline in time.

The present application belongs to the technical field of data labeling, and particularly relates to a 3D point cloud data labeling-based acceptance method and device and a storage medium. The method comprises the following steps: S1, standard presetting, in which, based on an acceptance object and an acceptance standard, a size of an element box and a fitting error of the element box are preset in advance; S2, system judgment, in which, according to a comparison between the standard presetting and actual labeling, it is judged whether the size of the element box is correct, whether the fitting of the element box is within the error range, whether the element boxes overlap, and an abnormal position and an abnormal reason are identified; and S3, inspection, in which, according to the abnormal position and the abnormal reason judged by the system, a form that can be viewed visually is used to display, and the abnormal position and the abnormal reason are clicked to inspect. The purpose is to solve the problem of misjudgment and low efficiency in the background art.

A data shaping apparatus includes: an abnormality detection unit configured to detect, as abnormal data, positioning data indicating an abnormal position from a positioning data group based on a movement constraint condition for a moving object, the positioning data group being a collection of positioning data at least indicating a position and a positioning time of the moving object; a first generation unit configured to generate first data from the positioning data group by replacing a position indicated by the abnormal data with a position assumed under a predetermined movement condition; and an output unit configured to output information based on the first data.

The invention discloses a flushing system anomaly detection method, device and system for medical equipment, and belongs to the technical field of medical equipment. The medical equipment is provided with a flushing channel, the method comprises the steps that first detection information and second detection information corresponding to the flushing channel are obtained, the first detection information represents the flushing pressure change condition of the flushing channel within the target duration, and the second detection information comprises at least one of the second detection information and fluid temperature information; the second detection information represents the bubble generation condition in the flushing channel, and the fluid temperature information represents the temperature change condition of fluid in the flushing channel; and according to the first detection information and the second detection information, abnormal alarm information corresponding to the flushing channel is output, and the abnormal alarm information indicates at least one of an abnormal position in the flushing channel and an abnormal state corresponding to the abnormal position. By means of the method, the abnormity in the flushing channel can be accurately detected.

The application relates to the technical field of target detection, and provides an optimization method and device for target detection, which comprises the following steps: inputting a to-be-detected image into a target detection model, so that the target detection model outputs a target category, a target position and a first confidence value for determining the category; inputting the to-be-detected image into an abnormality detection model, so that the abnormality detection model outputs an abnormality position and a second confidence value for determining the abnormality; calculating the IoU of the target position and the abnormality position; if the IoU is greater than or equal to a set value, optimizing the confidence value corresponding to the target category according to the first confidence value and the second confidence value; and outputting a target detection result. The abnormality detection model and the target detection model are combined, the optimization of the confidence value corresponding to the target category in the target detection result is realized, and the simultaneous optimization of the missing and overkill of the target detection result can be realized without changing the confidence value threshold as much as possible.

The invention discloses an abnormity identification method and device for a vehicle test tool, and relates to the technical field of test tool abnormity identification. The method comprises the following steps: in the process of testing a whole vehicle or a vehicle part through a test tool, detecting real-time relative displacement between two corresponding connecting pieces with a relative relationship by using each connecting displacement sensor; for each connection displacement sensor, calculating a reference data fluctuation threshold value corresponding to a specific position according to the historical relative displacement, detected by the connection displacement sensor in a first historical period, of the specific position of the test tool in a normal state; according to the real-time relative displacement detected by each connection displacement sensor and a reference data fluctuation threshold value, whether abnormal fluctuation exists in the real-time relative displacement or not is determined; and under the condition that any real-time relative displacement has abnormal fluctuation, a structure abnormal position is determined, and a structure abnormal alarm is given. According to the embodiment, the position with the abnormal structure in the test tool can be quickly identified and positioned.

The invention relates to the technical field of test evaluation, in particular to a semi-physical simulation system test confidence coefficient online evaluation and guarantee method, which comprises the following steps of: recording asynchronous abnormal events in real time, and generating a local asynchronous event sequence which serves as basic data of subsequent confidence coefficient weakening; calculating a confidence weakening factor of each local confidence unit, reflecting the real influence degree of the asynchronous abnormal event in the local region, and outputting a local confidence evaluation result; according to the method, the overall test credibility is subjected to decreasing type recombination, an overall credibility structure capable of indicating a local abnormal position is formed, the situation that the test is misjudged to pass when asynchronous abnormity exists is avoided, and abnormal positioning information for backtracking and an independent local confidence record are generated. According to the method, the structural decline mode not only improves the response capability of the overall assessment to the chain propagation risk, but also realizes the conversion of credibility calculation from static weighting to dynamic conduction.

The invention belongs to the technical field of substation equipment intelligent inspection and anomaly recognition, and particularly relates to a substation intelligent inspection robot anomaly recognition method and system based on multi-modal fusion and deep learning. The objective of the invention is to solve the problems of single mode limitation, poor working condition adaptability and the like in substation equipment abnormity identification. The method comprises the following steps: synchronously acquiring multi-modal time sequence data through an inspection robot, and embedding a GPS position and a unique ID of equipment to complete scene marking; after preprocessing and time alignment, extracting depth features of each modal; in combination with the working condition parameters, outputting an adaptive weight by a dynamic weight fusion network, and generating a combined multi-modal feature; and through a space-time double-flow deep learning network, synchronously capturing space static characteristics and time dynamic characteristics, identifying an abnormal state, and positioning an abnormal position. The system comprises a data acquisition module, a preprocessing module, a feature extraction module and other core modules, supports online updating of the model, adapts to complex dynamic working conditions of the transformer substation, and improves the inspection efficiency and the anomaly recognition accuracy.

The invention relates to the technical field of experiment monitoring, and provides an experiment monitoring alarm method and device based on a scheduling plan, a computer readable medium and electronic equipment. Experimental information and equipment information are acquired, operation steps and operation duration of each operation step are determined, and a dynamic scheduling scheme of the equipment components is generated; performing an experiment based on the dynamic scheduling scheme, and monitoring the actual time corresponding to each operation step and the actual operation state of each equipment component; when it is detected that the actual time or the actual operation state is abnormal, an alarm identifier is displayed at the associated position of the control interface; and performing indexing based on the alarm identifier to determine an abnormal target component and an abnormal reason from the equipment components. Equipment resource allocation is optimized through a dynamic scheduling scheme, visual positioning of an abnormal position is realized in combination with a control interface association alarm mechanism, experimental monitoring is converted into active early warning from passive response, and the efficiency and accuracy of an experiment and a monitoring process thereof are guaranteed.

The application discloses a device, method and equipment for checking abnormalities of a laid mineral insulated cable, and belongs to the technical field of power facilities. The device comprises: a laying track acquisition module, which is used to acquire a track line of the laid mineral insulated cable; a position of interest determination module, which is used to determine a position of interest according to the track line; and a flaw detection module, which is used to perform nondestructive flaw detection on the position of interest based on a nondestructive flaw detection means to determine whether the position of interest has an abnormality. According to the technical scheme, the position of the mineral insulated cable where damage defects are prone to occur can be checked for abnormalities through the laying track of the mineral insulated cable, maintenance personnel can be helped to timely repair the abnormal position, the insulation of the mineral insulated cable is prevented from being too low and electric breakdown from occurring, the safe operation of a power system is maintained, the service life is prolonged, and the maintenance cost of the mineral insulated cable is reduced.

The invention discloses a reset control method and system of a mushroom mechanical arm based on path planning, relates to the technical field of path planning, and determines the clamping action of the mushroom mechanical arm according to the detection of a clamping path. And according to the clamping action and the corresponding clamping posture parameters, the clamping grade of the mushroom frame by the mushroom mechanical arm is determined, the clamping grade of the mushroom frame by the mushroom mechanical arm is guaranteed, and accurate clamping of the mushroom frame by the mushroom mechanical arm is achieved. Therefore, according to the position variable quantity of the first obstacle and the moving path of the mushroom mechanical arm, reverse reset of the mushroom mechanical arm is triggered; in the reverse reset process of the mushroom mechanical arm, the abnormal posture of the mushroom frame is determined based on the multiple posture parameters of the mushroom frame, and the mushroom mechanical arm is triggered to dynamically and stably control the mushroom frame according to the abnormal posture of the mushroom frame and the corresponding abnormal position, so that the reverse reset accuracy of the mushroom mechanical arm is guaranteed, and the mushroom frame is prevented from being damaged. And the dynamic stability of the mushroom mechanical arm to the mushroom frame is further improved.

The invention provides a valve opening and closing state real-time tracking and abnormality diagnosis method, which comprises the following steps: comparing the impedance growth rate of each branch with increased roughness with a preset flow distribution rated value to obtain the flow contribution variation of each branch, and determining the interference level of each branch according to the flow contribution variation; the abnormal type of the abnormal valve and the flow of the branch to which the abnormal valve belongs are analyzed, the influence weight between the abnormal type and the flow distribution amount is evaluated by combining the interference level, and the accurate coordinate of the abnormal position is determined; the actual flow at the accurate coordinates of the abnormal position is obtained, the floating range between the expected flow and the actual flow is determined, and the tracking judgment boundary value of the opening and closing state of the valve is determined according to the floating range; the roughness change rate and the opening reading which are collected in real time are processed by tracking and judging boundary values of the opening and closing state of the valve, and whether the opening and closing state of the valve is normal or not is evaluated.

This invention discloses a visual positioning method for double-sided printing on cartons, relating to the field of carton printing technology. It addresses the problem that existing methods for verifying the post-printing position of cartons typically rely on manual inspection, which suffers from issues with accuracy and efficiency. This invention includes the following steps: S1: First, determine the inner and outer printing positions of the folded carton and mark the determined printing positions with feature points; S2: Then, verify and correct the marked printing positions. This invention prints customized patterns on the inner and outer sides of the carton before folding, meeting the needs of different customers. Simultaneously, it utilizes a visual positioning method to double-verify the printed patterns on the carton, correcting any abnormal positions, greatly improving the accuracy of the printed patterns. Furthermore, by analyzing the position and quality of the printed patterns, it can determine whether there are any abnormalities in the printing press or the carton clamping and positioning device and provide timely warnings.

The application discloses an image anomaly detection method based on a local perception knowledge distillation network. An anomaly detection network with a feature local perception module and a difficult example perception loss function is constructed. Non-anomalous images are input for training, and real-time test images are input into the trained anomaly detection network to obtain an abnormal image for judging and detecting anomalies. The anomaly detection network includes a structure teacher network and a student network, and a feature local perception operation module is used to obtain a feature corresponding graph containing local information. The student network is trained under a multi-level difficult example perception feature loss, while the teacher network remains unchanged. The feature loss of the two networks is large for abnormal positions. The application can fully perceive context feature information and local spatial information, improve the network's structured feature extraction capability and the role of structured information in the anomaly detection task, enhance the network's ability to perceive small abnormal areas, the network's adaptability to noise and the detection accuracy of abnormal areas, and effectively improve the network's generalization performance.

The invention relates to a tractor abnormal pose detection method and system based on multi-source sensing. The abnormal poses of the tractor mainly comprise slipping, trapping, rollover and the like. The multi-source sensing detection of the slipping and parking postures is mainly judged through a machine vision system and the wheel rotating speed slip rate; multi-source sensing detection of rollover poses is mainly carried out through an inertial measurement unit IMU and a tilt angle sensor. Multi-source sensing is utilized to ensure that the running posture of the tractor is accurately detected during actual field operation, operation according to the normal posture is facilitated, and occurrence of abnormal poses such as vehicle sinking and rollover is prevented, so that the personal safety of a driver is guaranteed, the overall operation efficiency of the tractor is improved, the unmanned level of the whole tractor is improved, and the working efficiency of the tractor is improved. And the tractor is promoted to develop to intelligence in an assisted manner.

The application discloses an application program self-repairing method and device, equipment and storage medium, the method comprises the following steps: acquiring the abnormal information generated by the front-end component, wherein the abnormal information comprises abnormal type information and abnormal position information; reading the target file pointed by the abnormal position information; obtaining the corresponding syntax analysis matcher according to the abnormal type information; analyzing the target file based on the syntax analysis matcher and the abnormal position information to obtain a target abnormal code segment; repairing the target abnormal code segment according to the abnormal type information to obtain a patch file; and repairing the front-end component based on the patch file. The application can automatically locate and correct the abnormality of the front-end component, repair the front-end component in the form of the patch file, does not need manual participation, can be automatically implemented, and does not need to interact with the server, so that the repair speed can be improved, the labor cost and the communication cost can be reduced.

The invention provides a position diagnosis method for wafer bonding abnormity, and relates to the technical field of wafer bonding. The method comprises the following steps of: primarily bonding a first wafer and a second wafer to obtain a first primary bonding structure; the first initial bonding structure is detected, a first abnormal area of the first initial bonding structure is determined, then the relative angle of the first wafer and the second wafer in the first wafer group is changed, detection is carried out again, a second abnormal area is determined, or the first wafer and the second wafer in the second wafer group are bonded and detected at a second relative position; and obtaining a third abnormal region. And finally, judging that the first wafer or the second wafer is abnormal according to the position relationship between the first abnormal region and the second abnormal region or the position relationship between the first abnormal region and the third abnormal region. According to the technical scheme, by changing the relative angle of the first wafer and the second wafer and comparing the positions of the abnormal areas before and after the positions are changed, the abnormal source is accurately bonded, and the troubleshooting efficiency is improved.

This invention discloses a safety assessment system and method for pressure-bearing components based on nonlinear ultrasound, belonging to the field of component safety assessment technology. The invention controls a robotic arm to drive an automatic probe to acquire nonlinear signals; establishes a mapping benchmark library and calibrates the background nonlinear threshold; divides the detection area of ​​the pressure-bearing component under test into a grid, and acquires the original field detection signal corresponding to each grid unit; removes nonlinear interference from each original field detection signal and calculates effective nonlinear parameters; based on the effective nonlinear parameters and the background nonlinear threshold, filters out abnormal candidate regions; for all abnormal candidate regions, inversely calculates the equivalent emission source parameters of the abnormal nonlinear signals; based on the three-dimensional spatial coordinates of the equivalent emission source parameters, determines the abnormal location region and outputs the location characteristics of the abnormal location region; trains a safety assessment model, inputs the location characteristics into the safety assessment model, and calculates the safety assessment result of the pressure-bearing component.

The application discloses a kind of fan blade root bolt monitoring method and monitoring system, comprising the following steps: the blade root corresponding hub cooperation area is fan-shaped partition, monitoring and obtaining the bolt overall load pressure variation value in all the abnormal area, the fan-shaped partition of bolt load abnormality occurs is determined by the load pressure numerical value of load component;Monitoring and obtaining the independent load condition between every two bolts in the fan-shaped partition of bolt load abnormality, and determining the specific position of the bolt that fails according to the difference of the independent load condition.Through the setting of threshold range A and threshold range B, the abnormal position bolt is judged, the corresponding value of observation mark ruler and physical target can be analyzed, which bolt in adjacent bolt occurs abnormality, the blade root is fixed on the bolt fixing part of partition whole fixed, while realizing abnormal load bolt position monitoring function.

The invention discloses a multi-robot abnormal position complementing scheduling method in an industrial scene, and relates to the technical field of industrial robot scheduling, and the scheduling method comprises the following steps: S1, configuring a multi-source sensing unit for each industrial robot, and constructing a multi-dimensional abnormal sensing model to achieve the real-time monitoring and precise recognition of the abnormal state of the robot; s2, designing a layered position covering scheduling framework to generate an initial position covering scheme; s3, an improved self-adaptive scheduling algorithm is adopted to optimize a position complementing scheme; s4, establishing a dynamic adjustment mechanism to realize real-time optimization of the position covering process; s5, state feedback and knowledge base updating are carried out after position complementing is completed; multi-dimensional data such as the running state, the environment and the task progress of the robot are collected through the multi-source sensing unit, feature fusion is achieved through a weighted fusion algorithm, accurate judgment is conducted in combination with an anomaly recognition knowledge base, the anomaly misjudgment rate and the anomaly missed judgment rate are effectively reduced, the anomaly recognition accuracy is effectively improved, and a reliable basis is provided for follow-up position covering scheduling.

The invention discloses an abnormal reason analysis method and device, a medium and a program product, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining an index number and index metadata information corresponding to target index data; determining index transaction position information corresponding to the target index data in an index transaction table according to the index number; replacing template metadata in a preset cue word frame with the index metadata information, and replacing a template index transaction position in the cue word frame with the index transaction position information to obtain a replaced target cue word; and inputting the target cue word into a pre-trained exception reason analysis model to obtain an exception reason analysis report corresponding to the target cue word output by the exception reason analysis model. According to the scheme provided by the invention, the situation that the abnormal reason analysis efficiency is relatively low due to relatively long time consumption caused by dependence on manpower is avoided, so that the abnormal analysis time is shortened, the abnormal reason analysis efficiency is improved, and the abnormal reason analysis accuracy is improved.

The invention relates to the technical field of data analysis, and particularly provides a data exception positioning method and device, a medium, equipment and a product, and the method can comprise the steps: obtaining associated data and a demand document corresponding to exceptional data in a work order; wherein the demand document is used for deducing business logic between the abnormal data and the associated data; the associated data comprises multiple layers of upstream data; performing analog computation on the associated data based on the business logic to obtain verification data; comparing the verification data with the abnormal data, and positioning an abnormal position; wherein the abnormal position is any layer in the multiple layers of upstream data. According to the embodiment of the invention, intelligent traceability of data can be realized, and the precision and efficiency of anomaly positioning are improved.

1. The name of the design product: fan monitoring graphical user interface of electronic equipment. 2. The use of the design product: an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The product carrier is the usual design, and the rear view, left view, right view, top view, and bottom view are omitted. 6. The use of the graphical user interface: for fan anomaly monitoring, abnormal position positioning, abnormal sound recording, analysis and report generation, and wind farm fan management. 7. The human-computer interaction mode of the graphical user interface: the front view is a fan overview list interface, clicking on the "details" of any fan under "fan list" enters the corresponding fan detail interface of change state diagram 1, and sliding down in the change state diagram 1 enters change state diagram 2 and change state diagram 3 in turn to view other information of the fan details.

The application provides a labeling control method, device and equipment and a computer readable storage medium. The labeling control method comprises: obtaining a target image containing a target parcel to be labeled; determining a target labeling point on the target parcel and coordinate information corresponding to the target labeling point according to the target image; setting a movement control parameter corresponding to a preset labeling device according to the coordinate information; and controlling the movement of the preset labeling device according to the movement control parameter, so that the preset labeling device completes the labeling operation on the target parcel. The application uses the image corresponding to the parcel to determine the target labeling point on the parcel and the coordinate information thereof. When the movement control parameter set according to the coordinate information containing the position information of the labeling point is used to control the movement of the labeling device, the labeling device can paste the printed label at the labeling point, avoiding the pasting of the label to other abnormal positions and improving the efficiency of subsequent transfer.

The invention provides a pipeline detection method, device, system and equipment based on an endoscope image and a medium, and the method comprises the steps: obtaining the endoscope image transmitted by an industrial endoscope in real time, calling a preset image recognition model to recognize the image features of the endoscope image, and determining a pipeline abnormality score value according to the image features; when the pipeline abnormity score value meets a preset score threshold value, detection parameters of the industrial endoscope are obtained, and the detection parameters comprise the detection length and the detection angle; determining an abnormal position of the pipeline based on the detection parameters, and marking a preset pipeline model according to the abnormal position to obtain a marked model; and fusing the endoscope image and the mark model to obtain a fusion model, and then carrying out visualization processing on the fusion model. According to the method, the endoscope image of the abnormal position of the pipeline is marked and rendered in the three-dimensional digital twin model, so that the processing efficiency and the detection efficiency of searching and positioning the abnormal position of the pipeline by a technician can be improved, and the maintenance effect of the pipeline is improved.

The invention belongs to the technical field of sensing monitoring, and discloses a sensing optical cable and a sensing monitoring mechanism. The sensing optical cable comprises a sensing fiber core, an outer sheath and a position sensing piece, the outer sheath comprises a coating part and at least two positioning parts, the at least two positioning parts are circumferentially arranged on the outer wall of the coating part at intervals, the coating part coats the sensing fiber core, each positioning part is configured to be attached to a to-be-monitored structure, and the sectional area of each positioning part is decreased from outside to inside; the position sensing member is arranged on the outer sheath. The sectional area of the positioning part is reduced from outside to inside, so that the possibility that the outer sheath interferes with a to-be-monitored structure when the sensing optical cable is installed can be reduced, the influence on the mechanical property of the to-be-monitored structure is reduced, and the change of the to-be-monitored structure can be transmitted to the sensing fiber core as much as possible; and parameter information such as strain and vibration of the to-be-monitored structure can be effectively acquired. When the sensing fiber core senses abnormity, the position sensing piece can rapidly lock the abnormal position, and rapid maintenance and replacement are facilitated.

To provide a belt conveyor stopping device capable of detecting an abnormal part of a belt conveyor and an abnormal part detection system equipped with the same.SOLUTION: A belt conveyor stopping device of the present invention is a device for stopping a belt conveyor in operation, and is equipped with a "towline switch" having a towline and a "detection light" outputting visible light. Among these, the towline switch stops the belt conveyor when the towline is pulled, and the detection light connected to the towline switch outputs visible light when the towline switch stops the belt conveyor.SELECTED DRAWING: Figure 1

The invention discloses an aircraft outer surface anomaly detection method, device and equipment, a medium and a product, and relates to the technical field of line laser contour detection. Acquiring information of a to-be-detected outer surface and a batch outer surface of at least one to-be-detected aircraft; scanning the to-be-detected outer surface based on the batch outer surface information and a threshold parameter, and generating a three-dimensional contour image of the to-be-detected aircraft; performing anomaly identification on the three-dimensional contour image based on the key morphology area to obtain an abnormal position coordinate; and based on the continuous threshold value and the at least two normal position coordinates, determining whether the at least one to-be-detected aircraft is in the same-batch anomaly. By adopting the technical scheme, the abnormal continuity of the outer surface is judged based on the batch outer surface information, the key morphology area and the continuous threshold value, the detection efficiency is improved while the detection precision is guaranteed, the method is suitable for automatic detection in large-scale airplane outer surface production, and the problems of low contour detection practicability and low detection precision are solved. And continuous abnormal conditions cannot be identified.

The invention relates to a control method and device for secondary shaping of a valve seat, and relates to the technical field of fluid control devices.The method comprises the steps that a front image of the valve seat is collected; determining a shadow abnormal position when the shadow abnormal feature exists in the front image of the valve seat; an abnormal position exposure image is collected, and the shadow abnormal position is analyzed to determine an abnormal type; when the sunken feature exists in the abnormal position exposure image, a push plate preset on the first detection station is controlled to push the valve seat and fall into a waste box; when the projection features exist in the abnormal position exposure image, determining the projection contour range of each projection feature, and screening out the maximum contour; when the maximum contour is not smaller than the preset reference contour area, a preset laser polishing method is used for processing; and when the area of the maximum contour is smaller than that of the reference contour, processing is conducted through a preset overturning and grinding method. The method has the effect of improving the product percent of pass and the production efficiency.