CN117152586B - Reducing spring detection method and system for rapid discharging - Google Patents
Reducing spring detection method and system for rapid discharging Download PDFInfo
- Publication number
- CN117152586B CN117152586B CN202311382063.3A CN202311382063A CN117152586B CN 117152586 B CN117152586 B CN 117152586B CN 202311382063 A CN202311382063 A CN 202311382063A CN 117152586 B CN117152586 B CN 117152586B
- Authority
- CN
- China
- Prior art keywords
- spring
- reducing
- diameter
- curve
- variable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 91
- 238000007599 discharging Methods 0.000 title claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 121
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000013461 design Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 16
- 230000001276 controlling effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method and a system for detecting a variable-diameter spring for rapid discharging, and relates to the field of spring detection, wherein the method comprises the following steps: acquiring a reducing spring image set; acquiring edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to acquire an edge point coordinate set; fitting to obtain a spring reducing curve; acquiring a preset variable-diameter curve, and acquiring a preset curve change angle and an actual curve change angle; calculating to obtain the variable diameter change angle difference; inputting the variable diameter change angle difference into the spring discharging detection classifier, analyzing and obtaining the quality grade of the variable diameter spring, and controlling the discharging of the variable diameter spring according to the quality grade of the variable diameter spring. The technical problems of low quality detection accuracy of the reducing spring and poor discharging control effect of the reducing spring in the prior art are solved. The technical effects of improving the quality detection precision and reliability of the reducing spring and improving the discharge control quality of the reducing spring are achieved.
Description
Technical Field
The invention relates to the field of spring detection, in particular to a method and a system for detecting a variable-diameter spring for rapid discharging.
Background
The reducing spring has better deformability and bearing capacity and stronger customizability, and is suitable for a plurality of fields needing elastic support. In the prior art, when the diameter-variable spring is detected, the size, the elastic coefficient and the like of the diameter-variable spring are simply focused, the detection precision of the diameter-variable spring is not high, and when the detection precision is improved, the detection discharge efficiency is lower due to the change of the diameter, so that the technical problems that the quality detection precision of the diameter-variable spring is low and the discharge control effect of the diameter-variable spring is poor exist.
Disclosure of Invention
The application provides a variable-diameter spring detection method and system for rapid discharging. The technical problems of low quality detection accuracy of the reducing spring and poor discharging control effect of the reducing spring in the prior art are solved. The technical effects of improving the quality detection precision and reliability of the reducing spring and improving the discharge control quality of the reducing spring are achieved.
In view of the above, the present application provides a method and a system for detecting a variable diameter spring for rapid discharging.
In a first aspect, the present application provides a method for detecting a reducing spring for rapid discharge, where the method is applied to a reducing spring detection system for rapid discharge, the method includes: constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by acquiring an image of the reducing spring to be detected through a CMOS image sensor; performing convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set to obtain edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set; performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve; acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring, and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point; calculating to obtain a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle; and carrying out quality identification and classification of the reducing spring according to the reducing change angle difference to obtain the quality grade of the reducing spring, and carrying out discharging control on the reducing spring according to the quality grade of the reducing spring.
In a second aspect, the present application also provides a reducing spring detection system for rapid discharge, wherein the system comprises: the image acquisition module is used for constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by performing image acquisition on the reducing spring to be detected through the CMOS image sensor; the edge point coordinate obtaining module is used for carrying out convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set, obtaining edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set; the curve fitting module is used for performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve through fitting; the change angle acquisition module is used for acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point; the angle difference calculation module is used for calculating and obtaining a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle; and the discharging control module is used for carrying out quality identification and classification on the variable-diameter spring according to the variable-diameter change angle difference to obtain the quality grade of the variable-diameter spring, and carrying out discharging control on the variable-diameter spring according to the quality grade of the variable-diameter spring.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
acquiring an image set of the variable-diameter spring by acquiring an image of the variable-diameter spring to be detected; the method comprises the steps of obtaining an edge point coordinate set by carrying out convolution feature extraction and processing on a plurality of reducing spring images in a reducing spring image set; performing curve fitting on the edge point coordinate set to obtain a spring reducing curve; constructing a preset reducing curve according to design data of the reducing spring; calculating a preset curve change angle corresponding to a preset reducing curve, and calculating an actual curve change angle corresponding to a spring reducing curve; obtaining a variable diameter change angle difference according to a preset curve change angle and an actual curve change angle; inputting the variable diameter change angle difference into a spring discharging detection classifier to obtain the quality grade of the variable diameter spring, and controlling the discharging of the variable diameter spring according to the quality grade of the variable diameter spring. According to the embodiment of the application, the image of the reducing spring is acquired, the change angle of the curve formed by the edge points of the spiral body is analyzed, the quality of the reducing spring is analyzed, a more accurate and efficient reducing spring detection means is provided, the discharging efficiency of the reducing spring is ensured, the technical effects of improving the quality detection accuracy and reliability of the reducing spring and the discharging control quality of the reducing spring are achieved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the following description will briefly explain the drawings of the embodiments of the present invention. It is apparent that the figures in the following description relate only to some embodiments of the invention and are not limiting of the invention.
FIG. 1 is a schematic flow chart of a method for detecting a variable diameter spring for rapid discharging according to the present application;
FIG. 2 is a schematic flow chart of acquiring an image set of a reducing spring in a method for detecting a reducing spring for rapid discharging;
fig. 3 is a schematic structural diagram of a reducing spring detection system for rapid discharging according to the present application.
Detailed Description
The application provides a method and a system for detecting a variable-diameter spring for rapid discharging. The technical problems of low quality detection accuracy of the reducing spring and poor discharging control effect of the reducing spring in the prior art are solved. The technical effects of improving the quality detection precision and reliability of the reducing spring and improving the discharge control quality of the reducing spring are achieved.
Example 1
Referring to fig. 1, the present application provides a method for detecting a reducing spring for rapid discharging, wherein the method is applied to a reducing spring detecting system for rapid discharging, and the method specifically includes the following steps:
constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by acquiring an image of the reducing spring to be detected through a CMOS image sensor;
further, as shown in fig. 2, acquiring the image set of the reducing spring further includes:
constructing an area coordinate system in an area for detecting the reducing spring;
constructing a camera coordinate system based on a CMOS image sensor for image acquisition of the reducing spring;
the regional coordinate system and the camera coordinate system are regulated to obtain the coordinate system;
and acquiring images of the reducing spring through the CMOS image sensor to obtain the reducing spring image set.
In the area where the reducing spring is detected, an area coordinate system is constructed, that is, the reducing spring is placed in the detection area, and the area coordinate system is obtained by taking the center point of the area where the reducing spring is fixed, that is, the center point when the reducing spring is fixed for detection, as the origin of coordinates, taking the horizontal direction as the abscissa axis, and taking the vertical direction as the ordinate axis. And then, the area coordinate system and the camera coordinate system of the CMOS image sensor are regulated, namely, the area coordinate system and the camera coordinate system are subjected to coordinate origin unification and coordinate scale unification, and the coordinate system is obtained. And acquiring multiple images of the reducing spring through a CMOS image sensor based on a coordinate system to obtain a reducing spring image set. The detection area may be any area for detecting the variable-diameter spring. The region coordinate system is a coordinate system with the center point of the reducing spring as the origin of coordinates, the horizontal direction as the abscissa axis and the vertical direction as the ordinate axis. The camera coordinate system is a coordinate system carried by the CMOS image sensor. The camera coordinate system is a three-dimensional rectangular coordinate system established by taking the focusing center of the CMOS image sensor as an origin and taking the optical axis as a z axis. The camera coordinate system includes an x-axis, a y-axis, and a z-axis. The x-axis and the y-axis are parallel to the abscissa axis and the ordinate axis of the regional coordinate system, the z-axis is an optical axis, and the optical axis is perpendicular to the plane of the reducing spring. The coordinate system comprises a region coordinate system and a camera coordinate system, wherein the region coordinate system is uniform in coordinate origin and coordinate axis scale. The set of reducing spring images includes a plurality of reducing spring images. Each reducing spring image comprises image data information corresponding to the reducing spring. The reducing spring comprises a plurality of reducing spirals. The method achieves the technical effect of obtaining the image set of the variable-diameter spring and providing data support for calculating the edge point coordinates of a plurality of variable-diameter spirals.
Performing convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set to obtain edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set;
performing data mining on historical data of detection of the reducing springs to obtain a historical reducing spring image set and a plurality of historical edge point coordinate sets of a plurality of edge points of a plurality of reducing spirals;
and the variable diameter spring detection system for rapid discharging is connected, historical detection data of the variable diameter spring are collected, and a historical variable diameter spring image set and a plurality of historical edge point coordinate sets of a plurality of edge points of a plurality of variable diameter screws are obtained. The historical reducing spring image set comprises a plurality of historical image data information corresponding to the historical reducing springs. Each history reducing spring comprises a plurality of reducing spiral bodies, the outer edges of images of the spiral bodies in the reducing springs are edge points, and the vertical line section of each edge point and the axial lead of each reducing spring is the diameter of the reducing spring at the position of the spiral body. Each historical edge point coordinate set comprises a plurality of historical edge point coordinates corresponding to a plurality of edge points of a plurality of reducing spirals of each historical reducing spring.
Constructing a spiral body edge point coordinate recognition channel based on the historical reducing spring image set and the plurality of historical edge point coordinate sets;
constructing an edge point coordinate recognition channel of the spiral body by adopting a convolutional neural network, wherein input data of the edge point coordinate recognition channel is a variable-diameter spring image, and output data is edge point coordinates of the edge points;
and based on the historical reducing spring image set and the plurality of historical edge point coordinate sets, performing supervision training on the edge point coordinate recognition channel by adopting a gradient descent method, and adjusting network parameters to obtain the edge point coordinate recognition channel meeting convergence conditions.
Convolutional neural networks are a class of feedforward neural networks that involve convolutional computations and have a deep structure. The convolutional neural network has characteristic learning capability and can carry out translation invariant classification on input information according to a hierarchical structure of the convolutional neural network. The convolutional neural network comprises an input layer, an implicit layer and an output layer. And taking the convolutional neural network as a basic channel structure of the spiral body edge point coordinate identification channel. The basic channel structure of the spiral body edge point coordinate identification channel comprises an input layer, an hidden layer and an output layer. And then, based on a convolutional neural network, performing supervision training on the historical variable diameter spring image set and the plurality of historical edge point coordinate sets by adopting a gradient descent method, and adjusting network parameters of the basic channel structure until an edge point coordinate recognition channel meeting convergence conditions is obtained. The gradient descent method is a first-order optimization algorithm, and is also commonly called a steepest descent method. In short, the gradient descent method is to continuously and iteratively adjust network parameters of the basic channel structure until the edge point coordinate recognition channel meets the convergence condition. The specific operation steps of the gradient descent method comprise the steps of taking a historical reducing spring image set and a plurality of historical edge point coordinate sets as training sets, randomly selecting one sample data from the training sets each time, calculating loss and gradient corresponding to the sample data, updating network parameters of an edge point coordinate recognition channel according to the loss and gradient corresponding to the sample data, and repeatedly iterating until the edge point coordinate recognition channel meets convergence conditions. The network parameters comprise the number of convolution layers, the convolution kernel size, the convolution step length, the filling layer number and the like of the edge point coordinate identification channel. The convergence condition comprises an output accuracy threshold value of the edge point coordinate recognition channel which is preset and determined by the variable diameter spring detection system for rapid discharging. And the input data of the edge point coordinate recognition channel is a variable-diameter spring image, and the output data is the edge point coordinates of a plurality of edge points. The technical effect of constructing a high-precision edge point coordinate recognition channel by a gradient descent method and improving the quality detection reliability of the reducing spring is achieved.
Inputting a plurality of reducing spring images in the reducing spring image set into the spiral body edge point coordinate recognition channel, and extracting and processing convolution characteristics to obtain a plurality of basic edge point coordinate sets of the plurality of edge points;
and calculating a mean value according to coordinate values of a plurality of coordinate points in the plurality of basic edge point coordinate sets to obtain the edge point coordinate set.
Performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve;
and respectively taking a plurality of reducing spring images in the reducing spring image set as input information, inputting the input information into a spiral body edge point coordinate recognition channel, and carrying out convolution feature extraction and processing on the plurality of reducing spring images through the spiral body edge point coordinate recognition channel to obtain a plurality of basic edge point coordinate sets. Each basic edge point coordinate set comprises a plurality of edge point coordinates corresponding to a plurality of edge points of a plurality of reducing spirals in each reducing spring image. And then, classifying the edge point coordinates corresponding to the same edge point of the same variable-diameter screw in the plurality of basic edge point coordinate sets to obtain a plurality of variable-diameter screw clustering edge point coordinate sets. And respectively carrying out average value calculation on the edge point coordinate sets of the variable diameter screw clustering to obtain a plurality of edge point average value coordinates, and adding the plurality of edge point average value coordinates to the edge point coordinate sets. Each variable-diameter screw body clustering edge point coordinate set comprises a plurality of edge point coordinates corresponding to the same edge point of the same variable-diameter screw body in a plurality of basic edge point coordinate sets. Each edge point mean coordinate comprises an average of a plurality of edge point coordinates within each set of variable diameter screw clustered edge point coordinates. The set of edge point coordinates includes a plurality of edge point mean coordinates.
Further, curve fitting is performed on the edge point coordinate set, namely, a curve fitting coordinate system is built by taking edge points of the variable-diameter screw body as abscissa axes and taking edge point mean coordinates as ordinate axes. And inputting the edge point coordinate set into a curve fitting coordinate system to obtain a spring reducing curve. The curve-fitting coordinate system includes an abscissa axis and an ordinate axis. The abscissa axis is the edge point of the reducing screw, and the ordinate axis is the mean value coordinate of the edge point. The spring reducing curve comprises a plurality of edge points of a plurality of reducing screws and a plurality of edge point mean coordinates corresponding to the edge points. The method has the advantages that convolution characteristic extraction and processing are carried out on a plurality of variable-diameter spring images through the spiral body edge point coordinate recognition channel, an accurate edge point coordinate set is obtained, curve fitting is carried out on the edge point coordinate set, a spring variable-diameter curve is constructed, and data support is provided for the subsequent calculation of variable-diameter change angle difference of the variable-diameter spring.
Acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring, and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point;
fitting and acquiring the preset reducing curve according to the design data of the reducing spring;
taking the edge point of the spiral body with the inner diameter of the reducing spring beginning to change as a detection point, taking the distance between two spiral bodies in the reducing spring as a pre-aiming distance, taking the detection point as an original point, taking the pre-aiming distance as a radius, drawing a circle, and taking the intersection point with the preset reducing curve as a pre-aiming point;
tangent lines of the preset variable-diameter curve are formed at the detection point and the preset aiming point, and an included angle between the two tangent lines is obtained and is used as the change angle of the preset curve;
and obtaining the actual curve change angle according to the spring diameter change curve.
Calculating to obtain a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle;
and connecting the variable diameter spring detection system for rapid discharging, inquiring design data of the current variable diameter spring, such as diameter data in a design drawing, and performing curve fitting on the design data to obtain a preset variable diameter curve. The design data comprise a plurality of edge point design coordinates corresponding to a plurality of edge points of a plurality of reducing spirals of the reducing spring. The manner of curve fitting the design data is the same as that of curve fitting the edge point coordinate set, and for brevity of the description, no further description is given here. The preset reducing curve comprises a plurality of edge points of a plurality of reducing spirals of the reducing spring and a plurality of edge point design coordinates corresponding to the edge points.
Further, calculating a preset variable-diameter curve to obtain a preset curve change angle. Preferably, the process of calculating the preset reducing curve includes: the edge point of the spiral body with the inner diameter of the reducing spring beginning to change is taken as a detection point. The distance between the two spiral bodies in the reducing spring is set as the pre-aiming distance. And drawing a circle by taking the detection point as an origin and taking the pretightening distance as a radius to obtain a pretightening distance circle. And taking the intersection point of the preset aiming distance circle and the preset reducing curve as a preset aiming point. And (3) making tangent lines of a preset reducing curve at the detection point and the preset point, and obtaining the included angle of the two tangent lines as the change angle of the preset curve.
Further, based on the same method, calculating the spring reducing curve, drawing a circle by taking a detection point as an original point and a pre-aiming distance as a radius, taking an intersection point of the spring reducing curve as a pre-aiming point, and then, based on the same method, calculating to obtain an actual curve change angle. And outputting the difference between the preset curve change angle and the actual curve change angle as a variable diameter change angle difference. The process of calculating the spring reducing curve is the same as the process of calculating the preset reducing curve, and for simplicity of the description, the description is omitted here. The technical effects of obtaining accurate variable diameter change angle difference by calculating the preset variable diameter curve and the spring variable diameter curve and improving the quality detection accuracy of the variable diameter spring are achieved.
And carrying out quality identification and classification of the reducing spring according to the reducing change angle difference to obtain the quality grade of the reducing spring, and carrying out discharging control on the reducing spring according to the quality grade of the reducing spring.
Searching and processing detection and discharge data of the reducing spring to obtain a historical reducing change angle difference set and a sample reducing spring quality grade set;
and connecting the variable-diameter spring detection system for rapid discharging, collecting detection discharging data of the variable-diameter spring, and processing and obtaining a plurality of historical detection discharging data based on the method in the previous content. Each historical detection discharge data comprises a historical variable diameter change angle difference and a historical variable diameter spring quality grade, and the historical variable diameter spring quality grade can be detected and given based on specifications such as diameters and the like of variable diameter springs by a person skilled in the art. Then, a plurality of historical diameter change angle differences in the plurality of historical detection discharge data are added to the historical diameter change angle difference set, and a plurality of historical diameter change spring quality grades in the plurality of historical detection discharge data are added to the sample diameter change spring quality grade set. The historical diameter-changing change angle difference set comprises a plurality of historical diameter-changing change angle differences in a plurality of historical detection discharge data. The sample variable diameter spring quality grade set includes a plurality of historical variable diameter spring quality grades in a plurality of historical test discharge data.
Adopting the historical diameter-changing angle difference set and the sample diameter-changing spring quality grade set to construct a spring discharge detection classifier based on a decision tree;
inputting the variable diameter change angle difference into the spring discharging detection classifier for decision classification, and obtaining the variable diameter spring quality grade.
Randomly selecting a plurality of historical diameter change angle differences in the historical diameter change angle difference set, taking the historical diameter change angle differences as a plurality of decision thresholds, constructing a plurality of layers of decision nodes, carrying out decision division on the input diameter change angle differences by each layer of decision nodes according to the decision thresholds, and inputting the decision nodes of an upper layer;
obtaining a plurality of final division results of the multi-layer decision node;
and adopting a plurality of sample reducing spring quality grades in the sample reducing spring quality grade set as decision results of the plurality of final dividing results to obtain the spring discharging detection classifier.
The embodiment of the application constructs the spring discharging detection classifier based on the idea of a decision tree algorithm. And randomly selecting a plurality of historical variable diameter change angle differences in the historical variable diameter change angle difference set to obtain a plurality of decision thresholds. And setting a plurality of decision thresholds as multi-layer decision nodes of the spring discharge detection classifier. And then, connecting the multi-layer decision nodes, and obtaining a plurality of final division results of the division decision of the multi-layer decision nodes. Each final division result includes a section of varying angle difference of varying diameter. And setting a plurality of sample reducing spring quality grades in the sample reducing spring quality grade set as a plurality of decision results. And marking a plurality of final dividing results according to the plurality of decision results to obtain the spring discharging detection classifier. And further, the variable diameter change angle difference is used as input information and is input into a spring discharge detection classifier to obtain the quality grade of the variable diameter spring, and the discharge control of the variable diameter spring is performed according to the quality grade of the variable diameter spring, so that the discharge control adaptability of the variable diameter spring is improved.
The decision thresholds comprise a plurality of historical variable diameter change angle differences which are selected randomly. The multi-layer decision nodes comprise a plurality of decision thresholds, each layer decision node performs decision division on the input variable diameter change angle difference according to the decision thresholds, and the input variable diameter change angle difference is input into the upper layer decision node. The plurality of final division results comprise results obtained by dividing according to a plurality of decision thresholds corresponding to the multi-layer decision nodes. The spring discharging detection classifier comprises a plurality of layers of decision nodes, a plurality of final dividing results and a plurality of decision results.
In summary, the method for detecting the variable-diameter spring for rapid discharging provided by the application has the following technical effects:
1. acquiring an image set of the variable-diameter spring by acquiring an image of the variable-diameter spring to be detected; the method comprises the steps of obtaining an edge point coordinate set by carrying out convolution feature extraction and processing on a plurality of reducing spring images in a reducing spring image set; performing curve fitting on the edge point coordinate set to obtain a spring reducing curve; constructing a preset reducing curve according to design data of the reducing spring; calculating a preset curve change angle corresponding to a preset reducing curve, and calculating an actual curve change angle corresponding to a spring reducing curve; obtaining a variable diameter change angle difference according to a preset curve change angle and an actual curve change angle; inputting the variable diameter change angle difference into a spring discharging detection classifier to obtain the quality grade of the variable diameter spring, and controlling the discharging of the variable diameter spring according to the quality grade of the variable diameter spring. The technical effects of improving the quality detection precision and reliability of the reducing spring and improving the discharge control quality of the reducing spring are achieved.
2. By calculating the preset reducing curve and the spring reducing curve, accurate reducing change angle difference is obtained, and therefore quality detection accuracy of the reducing spring is improved.
Example two
Based on the same inventive concept as the method for detecting a variable diameter spring for rapid discharging in the foregoing embodiment, the present invention further provides a variable diameter spring detection system for rapid discharging, referring to fig. 3, the system includes:
the image acquisition module is used for constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by performing image acquisition on the reducing spring to be detected through the CMOS image sensor;
the edge point coordinate obtaining module is used for carrying out convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set, obtaining edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set;
the curve fitting module is used for performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve through fitting;
the change angle acquisition module is used for acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point;
the angle difference calculation module is used for calculating and obtaining a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle;
and the discharging control module is used for carrying out quality identification and classification on the variable-diameter spring according to the variable-diameter change angle difference to obtain the quality grade of the variable-diameter spring, and carrying out discharging control on the variable-diameter spring according to the quality grade of the variable-diameter spring.
Further, the system further comprises:
the area coordinate system construction module is used for constructing an area coordinate system in an area for detecting the reducing spring;
the camera coordinate system construction module is used for constructing a camera coordinate system based on the CMOS image sensor for acquiring the image of the reducing spring;
the first execution module is used for regulating the region coordinate system and the camera coordinate system to obtain the coordinate system;
the reducing spring image set acquisition module is used for acquiring images of the reducing springs through the CMOS image sensor to acquire the reducing spring image set.
Further, the system further comprises:
the second execution module is used for carrying out data mining on the historical data of the detection of the variable-diameter spring, and acquiring a historical variable-diameter spring image set and a plurality of historical edge point coordinate sets of a plurality of edge points of a plurality of variable-diameter screws;
the third execution module is used for constructing a spiral body edge point coordinate recognition channel based on the historical reducing spring image set and the plurality of historical edge point coordinate sets;
the basic edge point coordinate set obtaining module is used for inputting a plurality of reducing spring images in the reducing spring image set into the spiral body edge point coordinate recognition channel, extracting and processing convolution characteristics, and obtaining a plurality of basic edge point coordinate sets of the plurality of edge points;
and the average value calculation module is used for calculating an average value according to coordinate values of a plurality of coordinate points in the plurality of basic edge point coordinate sets to obtain the edge point coordinate sets.
Further, the system further comprises:
the fourth execution module is used for constructing the spiral body edge point coordinate recognition channel by adopting a convolutional neural network, wherein the input data of the edge point coordinate recognition channel is a variable-diameter spring image, and the output data is the edge point coordinates of the plurality of edge points;
and the monitoring training module is used for monitoring and training the edge point coordinate recognition channel by adopting a gradient descent method based on the historical reducing spring image set and the plurality of historical edge point coordinate sets, and adjusting network parameters to obtain the edge point coordinate recognition channel meeting convergence conditions.
Further, the system further comprises:
the preset reducing curve determining module is used for obtaining the preset reducing curve in a fitting mode according to design data of the reducing spring;
the fifth execution module is used for drawing a circle by taking the edge point of the spiral body with the inner diameter of the reducing spring beginning to change as a detection point, taking the distance between the two spiral bodies in the reducing spring as a pre-aiming distance, taking the detection point as an original point, taking the pre-aiming distance as a radius, and taking the intersection point with the preset reducing curve as a pre-aiming point;
the preset curve change angle calculation module is used for making tangent lines of the preset reducing curve at the detection point and the preset aiming point, and obtaining an included angle of the two tangent lines as the preset curve change angle;
the actual curve change angle obtaining module is used for obtaining the actual curve change angle according to the spring diameter change curve.
Further, the system further comprises:
the data retrieval module is used for retrieving and processing detection and discharge data of the reducing spring and acquiring a historical reducing change angle difference set and a sample reducing spring quality grade set;
the sixth execution module is used for constructing a spring discharge detection classifier based on a decision tree by adopting the historical diameter-changing angle difference set and the sample diameter-changing spring quality grade set;
the variable diameter spring quality grade determining module is used for inputting the variable diameter change angle difference into the spring discharging detection classifier for decision classification, and obtaining the variable diameter spring quality grade.
Further, the system further comprises:
the decision dividing module is used for randomly selecting a plurality of historical diameter change angle differences in the historical diameter change angle difference set, constructing a plurality of layers of decision nodes as a plurality of decision thresholds, carrying out decision division on the input diameter change angle differences by each layer of decision nodes according to the decision thresholds, and inputting the decision nodes at an upper layer;
the final division result acquisition module is used for acquiring a plurality of final division results of the multi-layer decision node;
and the seventh execution module is used for adopting a plurality of sample reducing spring quality grades in the sample reducing spring quality grade set as decision results of the plurality of final dividing results to obtain the spring discharging detection classifier.
The variable diameter spring detection system for rapid discharging provided by the embodiment of the invention can execute the variable diameter spring detection method for rapid discharging provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The application provides a reducing spring detection method for rapid discharging, wherein the method is applied to a reducing spring detection system for rapid discharging, and the method comprises the following steps: acquiring an image set of the variable-diameter spring by acquiring an image of the variable-diameter spring to be detected; the method comprises the steps of obtaining an edge point coordinate set by carrying out convolution feature extraction and processing on a plurality of reducing spring images in a reducing spring image set; performing curve fitting on the edge point coordinate set to obtain a spring reducing curve; constructing a preset reducing curve according to design data of the reducing spring; calculating a preset curve change angle corresponding to a preset reducing curve, and calculating an actual curve change angle corresponding to a spring reducing curve; obtaining a variable diameter change angle difference according to a preset curve change angle and an actual curve change angle; inputting the variable diameter change angle difference into a spring discharging detection classifier to obtain the quality grade of the variable diameter spring, and controlling the discharging of the variable diameter spring according to the quality grade of the variable diameter spring. The technical problems of low quality detection accuracy of the reducing spring and poor discharging control effect of the reducing spring in the prior art are solved. The technical effects of improving the quality detection precision and reliability of the reducing spring and improving the discharge control quality of the reducing spring are achieved.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (8)
1. A method for detecting a variable diameter spring for rapid discharge, the method comprising:
constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by acquiring an image of the reducing spring to be detected through a CMOS image sensor;
performing convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set to obtain edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set;
performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve;
acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring, and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point;
calculating to obtain a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle;
and carrying out quality identification and classification of the reducing spring according to the reducing change angle difference to obtain the quality grade of the reducing spring, and carrying out discharging control on the reducing spring according to the quality grade of the reducing spring.
2. The method according to claim 1, wherein constructing a coordinate system in a region where the variable diameter spring is detected, and performing image acquisition of the variable diameter spring to be detected by the CMOS image sensor, comprises:
constructing an area coordinate system in an area for detecting the reducing spring;
constructing a camera coordinate system based on a CMOS image sensor for image acquisition of the reducing spring;
the regional coordinate system and the camera coordinate system are regulated to obtain the coordinate system;
and acquiring images of the reducing spring through the CMOS image sensor to obtain the reducing spring image set.
3. The method of claim 1, wherein convolving feature extraction and processing of the plurality of reducing spring images in the set of reducing spring images to obtain edge point coordinates of the plurality of reducing spirals in the reducing spring and calculating to obtain a set of edge point coordinates, comprising:
performing data mining on historical data of detection of the reducing springs to obtain a historical reducing spring image set and a plurality of historical edge point coordinate sets of a plurality of edge points of a plurality of reducing spirals;
constructing a spiral body edge point coordinate recognition channel based on the historical reducing spring image set and the plurality of historical edge point coordinate sets;
inputting a plurality of reducing spring images in the reducing spring image set into the spiral body edge point coordinate recognition channel, and extracting and processing convolution characteristics to obtain a plurality of basic edge point coordinate sets of the plurality of edge points;
and calculating a mean value according to coordinate values of a plurality of coordinate points in the plurality of basic edge point coordinate sets to obtain the edge point coordinate set.
4. The method of claim 3, wherein constructing a spiral edge point coordinate recognition channel based on the set of historical reducing spring images and the plurality of sets of historical edge point coordinates comprises:
constructing an edge point coordinate recognition channel of the spiral body by adopting a convolutional neural network, wherein input data of the edge point coordinate recognition channel is a variable-diameter spring image, and output data is edge point coordinates of the edge points;
and based on the historical reducing spring image set and the plurality of historical edge point coordinate sets, performing supervision training on the edge point coordinate recognition channel by adopting a gradient descent method, and adjusting network parameters to obtain the edge point coordinate recognition channel meeting convergence conditions.
5. The method according to claim 1, wherein obtaining a preset reducing curve according to design data of the reducing spring, and obtaining a preset curve change angle and an actual curve change angle of the preset reducing curve and the spring reducing curve at a detection point, comprises:
fitting and acquiring the preset reducing curve according to the design data of the reducing spring;
taking the edge point of the spiral body with the inner diameter of the reducing spring beginning to change as a detection point, taking the distance between two spiral bodies in the reducing spring as a pre-aiming distance, taking the detection point as an original point, taking the pre-aiming distance as a radius, drawing a circle, and taking the intersection point with the preset reducing curve as a pre-aiming point;
tangent lines of the preset variable-diameter curve are formed at the detection point and the preset aiming point, and an included angle between the two tangent lines is obtained and is used as the change angle of the preset curve;
and obtaining the actual curve change angle according to the spring diameter change curve.
6. The method of claim 1, wherein the reducing spring mass identification classification based on the reducing variation angle difference comprises:
searching and processing detection and discharge data of the reducing spring to obtain a historical reducing change angle difference set and a sample reducing spring quality grade set;
adopting the historical diameter-changing angle difference set and the sample diameter-changing spring quality grade set to construct a spring discharge detection classifier based on a decision tree;
inputting the variable diameter change angle difference into the spring discharging detection classifier for decision classification, and obtaining the variable diameter spring quality grade.
7. The method of claim 6, wherein constructing a spring discharge detection classifier based on a decision tree using the set of historical diameter change angle differences and the set of sample diameter change spring quality classes comprises:
randomly selecting a plurality of historical diameter change angle differences in the historical diameter change angle difference set, taking the historical diameter change angle differences as a plurality of decision thresholds, constructing a plurality of layers of decision nodes, carrying out decision division on the input diameter change angle differences by each layer of decision nodes according to the decision thresholds, and inputting the decision nodes of an upper layer;
obtaining a plurality of final division results of the multi-layer decision node;
and adopting a plurality of sample reducing spring quality grades in the sample reducing spring quality grade set as decision results of the plurality of final dividing results to obtain the spring discharging detection classifier.
8. A reducing spring detection system for rapid discharge, characterized in that the system is adapted to perform the method of any one of claims 1 to 7, the system comprising:
the image acquisition module is used for constructing a coordinate system in a region for detecting the reducing spring, and acquiring an image set of the reducing spring by performing image acquisition on the reducing spring to be detected through the CMOS image sensor;
the edge point coordinate obtaining module is used for carrying out convolution feature extraction and processing on a plurality of reducing spring images in the reducing spring image set, obtaining edge point coordinates of a plurality of reducing spirals in the reducing spring, and calculating to obtain an edge point coordinate set;
the curve fitting module is used for performing curve fitting according to the edge point coordinate set to obtain a spring reducing curve through fitting;
the change angle acquisition module is used for acquiring a preset variable-diameter curve according to the design data of the variable-diameter spring and acquiring a preset curve change angle and an actual curve change angle of the preset variable-diameter curve and the spring variable-diameter curve at a detection point;
the angle difference calculation module is used for calculating and obtaining a variable diameter change angle difference according to the preset curve change angle and the actual curve change angle;
and the discharging control module is used for carrying out quality identification and classification on the variable-diameter spring according to the variable-diameter change angle difference to obtain the quality grade of the variable-diameter spring, and carrying out discharging control on the variable-diameter spring according to the quality grade of the variable-diameter spring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311382063.3A CN117152586B (en) | 2023-10-24 | 2023-10-24 | Reducing spring detection method and system for rapid discharging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311382063.3A CN117152586B (en) | 2023-10-24 | 2023-10-24 | Reducing spring detection method and system for rapid discharging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117152586A CN117152586A (en) | 2023-12-01 |
| CN117152586B true CN117152586B (en) | 2024-01-26 |
Family
ID=88910267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311382063.3A Active CN117152586B (en) | 2023-10-24 | 2023-10-24 | Reducing spring detection method and system for rapid discharging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152586B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111151852A (en) * | 2020-01-03 | 2020-05-15 | 湘潭大学 | Method for identifying rotating plasma arc sensing free-form surface by adopting variable diameter adjustment |
| CN113034485A (en) * | 2021-04-09 | 2021-06-25 | 浙江欧视电科技有限公司 | Circle detection method integrating Hough transformation and caliper clustering |
| CN113268819A (en) * | 2020-02-14 | 2021-08-17 | 广州汽车集团股份有限公司 | Debugging method and device for system adopting spiral spring and storage medium |
| CN116703924A (en) * | 2023-08-08 | 2023-09-05 | 通用电梯股份有限公司 | Real-time detection and early warning method for wear state of high-speed elevator parts |
-
2023
- 2023-10-24 CN CN202311382063.3A patent/CN117152586B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111151852A (en) * | 2020-01-03 | 2020-05-15 | 湘潭大学 | Method for identifying rotating plasma arc sensing free-form surface by adopting variable diameter adjustment |
| CN113268819A (en) * | 2020-02-14 | 2021-08-17 | 广州汽车集团股份有限公司 | Debugging method and device for system adopting spiral spring and storage medium |
| CN113034485A (en) * | 2021-04-09 | 2021-06-25 | 浙江欧视电科技有限公司 | Circle detection method integrating Hough transformation and caliper clustering |
| CN116703924A (en) * | 2023-08-08 | 2023-09-05 | 通用电梯股份有限公司 | Real-time detection and early warning method for wear state of high-speed elevator parts |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117152586A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US6104835A (en) | Automatic knowledge database generation for classifying objects and systems therefor | |
| CN107368807B (en) | Monitoring video vehicle type classification method based on visual word bag model | |
| CN111860236B (en) | Small sample remote sensing target detection method and system based on transfer learning | |
| CN111914090B (en) | Method and device for enterprise industry classification identification and characteristic pollutant identification | |
| CN112633382B (en) | Method and system for classifying few sample images based on mutual neighbor | |
| CN108537286B (en) | Complex target accurate identification method based on key area detection | |
| US11237119B2 (en) | Diagnostic methods for the classifiers and the defects captured by optical tools | |
| KR20170091716A (en) | Automatic defect classification without sampling and feature selection | |
| CN102141978A (en) | Method and system for classifying texts | |
| Park et al. | Discriminative feature learning and cluster-based defect label reconstruction for reducing uncertainty in wafer bin map labels | |
| CN107832778B (en) | Same target identification method based on spatial comprehensive similarity | |
| US11416717B2 (en) | Classification model building apparatus and classification model building method thereof | |
| CN109218223A (en) | A kind of robustness net flow assorted method and system based on Active Learning | |
| CN111861103A (en) | Fresh tea leaf classification method based on multiple features and multiple classifiers | |
| CN108280236A (en) | A kind of random forest visualization data analysing method based on LargeVis | |
| CN113487533B (en) | Part assembly quality digital detection system and method based on machine learning | |
| CN111681214A (en) | Aviation bearing surface rivet detection method based on U-net network | |
| CN108074025B (en) | Steel coil surface defect judgment method based on surface defect distribution characteristics | |
| CN105809113A (en) | Three-dimensional human face identification method and data processing apparatus using the same | |
| CN113887342A (en) | Equipment fault diagnosis method based on multi-source signals and deep learning | |
| KR20170100710A (en) | Apparatus and Method for Modeling of Defect to Semiconductor Apparatus, and Computer Program Therefor, and System for Inspection of Defect to Semiconductor Apparatus | |
| WO2018132321A1 (en) | Diagnostic methods for the classifiers and the defects captured by optical tools | |
| CN115169534A (en) | Sample optimization training method of convolutional neural network and computer readable storage medium | |
| CN111881906A (en) | LOGO identification method based on attention mechanism image retrieval | |
| CN117152586B (en) | Reducing spring detection method and system for rapid discharging |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |