CN117029921B - Intelligent detection equipment and method for electronic element - Google Patents
Intelligent detection equipment and method for electronic element Download PDFInfo
- Publication number
- CN117029921B CN117029921B CN202310997431.9A CN202310997431A CN117029921B CN 117029921 B CN117029921 B CN 117029921B CN 202310997431 A CN202310997431 A CN 202310997431A CN 117029921 B CN117029921 B CN 117029921B
- Authority
- CN
- China
- Prior art keywords
- module
- electronic element
- comparison
- model
- specification parameters
- 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 37
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000010276 construction Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 230000005477 standard model Effects 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012797 qualification Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 230000001960 triggered effect Effects 0.000 claims description 6
- 239000000428 dust Substances 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 239000012535 impurity Substances 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 230000005611 electricity Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011179 visual inspection 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of electronic element detection, in particular to intelligent electronic element detection equipment and method, comprising an acquisition layer, an analysis layer and a control layer; the invention can upload standard parameters of the electronic element and collect parameters of the electronic element to be tested to construct the electronic element corresponding to the data to be tested and the model construction of the electronic element corresponding to the standard parameters in the acquisition layer, the analysis layer receives two groups of models constructed in the acquisition layer in real time, compares the visual angles of the two groups of models, and based on the similarity of the selected visual angle comparison model, the invention can respectively construct the electronic element model by uploading the standard parameters of the electronic element and collecting the parameters of the electronic element to be tested, further selects the comparison visual angle on the constructed model, and further realizes the similarity comparison operation of the model based on the selected comparison visual angle to realize the appearance detection of the electronic element, so that the appearance detection of the electronic element is not limited to the image acquisition of the electronic element.
Description
Technical Field
The invention relates to the technical field of electronic element detection, in particular to intelligent electronic element detection equipment and method.
Background
The electronic components are components of electronic elements and small-sized machines and instruments, are often composed of a plurality of parts, can be commonly used in similar products, and often refer to certain parts of industries such as electric appliances, radios, instruments and the like, and are the general names of the electronic elements such as capacitors, transistors, hairsprings, springs and the like. Diodes and the like are common.
The invention patent with the application number 202110530164.5 discloses an electronic component detection device, which comprises a supporting rod, a conveyor belt is fixed on the supporting rod, a base fixed on the ground is arranged on one side of the conveyor belt, and the electronic component detection device is characterized in that: the automatic feeding device is characterized in that a rotating mechanism for assisting in detecting the electronic element is arranged on the base in a rotating mode, a positioning mechanism for positioning the electronic element is arranged on the rotating mechanism, a detecting mechanism for detecting the electronic element is arranged on the base, the detecting mechanism is connected with a distributing mechanism in a transmission mode, the rotating mechanism comprises a rotating shaft which is arranged on the base in a rotating mode, a workbench is fixed at the end portion of the rotating shaft, a supporting plate is fixed on the base, a driving motor is fixed on the supporting plate, a driving bevel gear is fixed at the output end of the driving motor, and a transmission bevel gear which is combined with the driving bevel gear is fixed at the outer side of the rotating shaft.
The application aims at solving the problems: at present, when appearance detection is carried out on a potentiometer, a visual inspection mode of a quality inspector is generally adopted, eye fatigue can be caused by mass products and long-time work, the size of the products is not large, pin offset is not easy to observe, judgment of the quality inspector can be affected, working efficiency is reduced, labor is consumed, time is very long, and therefore, the problem of electronic element detection is solved.
However, the detection of electronic components is still higher in the degree of manual detection, and the electronic component production line for detecting by partially adopting the intelligent mechanical intelligent system can only detect the electronic components by simply two-dimensional images from the forward viewing angle of the electronic components, so that the reliability of detection results is poor, and the applied judging data has certain limitation in the data processing stage before outputting the detection results.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides intelligent detection equipment and method for electronic elements, and solves the technical problems in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
in a first aspect, an electronic component intelligent detection device includes an acquisition layer, an analysis layer, and a control layer;
Uploading standard specification parameters of the electronic element and data to be tested through the acquisition layer, completing model construction of the electronic element corresponding to the data to be tested and the electronic element corresponding to the standard specification parameters in the acquisition layer, receiving two groups of models constructed in the acquisition layer by the analysis layer in real time, selecting a comparison view angle for the two groups of models, based on similarity of the selected view angle comparison model, receiving comparison view angle selection results and model similarity comparison results in the analysis layer by the control layer, and judging or analyzing layer jump of the similarity comparison results based on decision of the two groups of results;
The analysis layer comprises a storage module, a selection module and a comparison module, wherein the storage module is used for receiving two groups of models constructed in the acquisition layer according to the standard specification parameters of the electronic element and the captured standard parameters of the electronic element, storing the models, executing the output operation of the standard models and the latest received to-be-tested models to the selection module, and the selection module is used for selecting the comparison angles applied when the comparison modules perform similarity comparison on the two groups of models and comparing the similarity of the two groups of models under the same visual angle;
The two groups of models are calculated based on the similarity under the same visual angle by the following formula:
Wherein: sim (a, b) is similarity; n a、Nb is the total pixel number of the two-dimensional image respectively presented under the same visual angle of the two groups of models a and b; f ij is the total image intensity; Is the average intensity of the image;
The model constructed according to the standard specification parameters of the electronic element is recorded as a standard model, and the model constructed according to the captured standard specification parameters of the electronic element is recorded as a model to be tested.
Furthermore, the acquisition layer comprises an uploading module, a capturing module and a construction module, wherein the uploading module is used for uploading standard specification parameters of the electronic element, the capturing module is used for capturing the specification parameters of the electronic element, the construction module is used for receiving the uploaded standard specification parameters of the electronic element and the captured specification parameters of the electronic element, and the construction of the model is respectively executed by applying the two groups of parameters;
The capture module is arranged on an output station of electronic element production equipment, the capture module consists of a plurality of ranging modules and mechanical arm modules, the ranging modules are distributed in a matrix shape, the data to be measured corresponds to the positions of the electronic element, namely the positions in the front, the back, the left, the right and the front directions, the positions in the five positive directions, the ranging modules synchronously run, after the surface of the electronic element is subjected to ranging, the mechanical arm modules overturn the electronic element, the ranging modules are triggered to synchronously run again, the ranging operation is executed again, and the ranging result is that the data to be measured corresponds to the specification parameters of the electronic element; the standard specification parameters of the electronic components uploaded by the uploading module are manually uploaded by a system end user.
Further, when the construction module operates to receive the specification parameters of the electronic components fed back by the capturing module, the source ranging module of each group of specification parameters of the electronic components is identified, and data which are derived from the right, left, front and back positive directions and belong to secondary operation measurement in the specification parameters of the received electronic components are deleted through the identification result and further based on the feedback time sequence of the specification parameters;
When the mechanical arm module performs overturning operation on the electronic element, the overturning angle is 180 degrees, and when the distance measuring module performs distance measurement on the electronic element, the distance measuring result is corrected after the distance measuring result is obtained through the following formula:
Wherein: s is a ranging result obtained after correction; s is the ranging result obtained before correction, C is the light speed, and 0.2998m/ns is taken; Δt is the ranging time; delta is the matrix size of the ranging module; gamma is the matrix utilization rate of the ranging module; kappa is the flatness of the ranging target surface; u is the impurity content of the distance measurement environmental dust;
Wherein, the ranging data deleted in the construction module does not participate in the correction operation of the ranging result.
Furthermore, in the construction stage, the standard model and the model to be tested of the electronic element complete the operation of executing the model construction at the same starting point and the same starting point direction in the three-dimensional coordinate system;
When the selection module performs comparison view angle selection, the selection module performs output of the comparison view angle by the following formula:
Wherein: a comparison viewing angle to be output; g is a set of comparison angles of view; n is a set of subtractive items; t is a phase timestamp of the output phase of the comparison view angle; (t 1、t2、...、tn-1、tn) is the time corresponding to the subtraction item; /(I) Taking an integer; /(I)For comparing the/>, in the set of angles of viewItem comparison viewing angle;
wherein, in the above formula When the viewing angle is single, the method is ended, otherwise, the/>, is calculatedAs g, the calculation is performed again until in the above formula/>Is a single viewing angle for comparison.
Further, the comparison angle selected in the selection module includes: the three groups of comparison angles are manually set by a user at the system end to form a set, the three groups of sets are used as calculation targets in the output formulas of the comparison angles, and the output of the comparison angles is executed.
Further, the control layer comprises a receiving module and a skip module, the receiving module is used for receiving the comparison view angle selected by the selection module and the similarity comparison result in the comparison module, determining the output of the similarity comparison result or the trigger operation of the skip module based on the model-to-image ratio in the model image corresponding to the received comparison view angle, and the skip module is used for executing the system skip and returning to the operation stage of the selection module of the analysis layer;
And when the ratio of the model to the image in the model image corresponding to the viewing angle in the receiving module is greater than or equal to 1, executing the output of the similarity comparison result, otherwise, triggering the operation of the jump module, and judging that the electronic element corresponding to the similarity comparison model is unqualified in the state that the jump module continuously operates for three times in the single operation process of the system.
Further, the calculation formula of the model-to-image ratio in the model image corresponding to the comparison view angle is as follows:
wherein: p ratio is more than 0 and less than or equal to 1; q is the total amount of model pixel blocks in the model image; q is the total pixel block amount in the model image;
The model background image in the model image is a conveying belt on an output station of the electronic element production equipment, and the conveying belt is single solid color.
Further, after the skip module triggers the operation, when the receiving module in the control layer operates again, the received similarity comparison result is comprehensively evaluated, and the output is further executed according to the comprehensive evaluation result, so that the comprehensive evaluation logic obeys the following formula:
SIM Heald ＝sim1·ω1+sim2·ω2+...+simn-1·ωn-1+simn·ωn;
Wherein sim n is the n-th group similarity comparison result; omega n is the set logic that the larger the ratio of the model to the image is, the larger the omega value is in the model image corresponding to the n group weight, omega obeys, and the (omega 1+ω2+...+ωn-1+ωn) =1;
the system end user in the receiving module sets a qualification judgment threshold, and the SIM Heald determines whether the electronic component is qualified or not based on comparison between the qualification judgment threshold and the SIM Heald after obtaining the qualification judgment threshold.
Furthermore, the uploading module is connected with the capturing module and the constructing module through medium electrical property, the constructing module is connected with the storage module through medium electrical property, the storage module is connected with the selecting module and the comparing module through medium electrical property, the comparing module is connected with the receiving module through medium electrical property, and the receiving module is connected with the jumping module through medium electrical property.
In a second aspect, an intelligent detection method for electronic components includes the steps of:
Step 1: uploading standard specification parameters of the electronic element; collecting specification parameters of an electronic element to be tested;
step 11: the distance measuring module measures the electronic element to obtain specification parameters and corrects the specification parameters of the electronic element;
step 2: a distinguishing and storing stage after parameter uploading and acquisition;
Step 3: respectively constructing an electronic element standard model and a model to be tested based on the uploaded and collected electronic element specification parameters;
Step 4: a similarity comparison stage of the standard model and the model to be tested;
step 41: the similarity ratio corresponds to the selection of the application viewing angle;
Step 5: and setting a judging threshold value, comprehensively evaluating the electronic component corresponding to the model based on the similarity comparison result, and judging whether the electronic component is qualified or not by applying the judging threshold value and the comprehensive evaluation result of the electronic component.
Compared with the prior art, the technical proposal provided by the invention has the following advantages that
The beneficial effects are that:
1. the invention provides an intelligent detection device for electronic elements, which can respectively construct an electronic element model by uploading standard parameters of the electronic elements and collecting parameters of the electronic elements to be detected in the operation process, further select a comparison view angle on the constructed model, and further realize similarity comparison operation of the model based on the selected comparison view angle so as to realize appearance detection of the electronic elements, so that the appearance detection of the electronic elements is not limited to image collection of the electronic elements, the appearance detection process of the electronic elements is ensured, the diversity is more realized, and the detection result precision is greatly improved.
2. In the running process of the system, in the similarity comparison stage of the electronic element construction model, the comparison angle is selected to realize the similarity comparison of the electronic element construction model, the selection of the comparison angle is more random through the provided comparison angle output algorithm, the electronic element can be compared with different comparison parameters, in addition, the reliability of the output result of the system is further evaluated through the model image obtained in the comparison angle selection stage, and when the reliability is not enough, the system can be driven to jump, so that the purpose of similarity comparison again is realized, and further the purpose of result refinement is achieved.
3. The invention provides an intelligent detection method for electronic elements, which can further maintain the stability of system operation by executing the steps in the method, and can further provide a system to clearly operate logic during the execution of the steps in the method, thereby ensuring the specific implementation of the technical scheme to be more reliable and accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of an intelligent electronic component inspection apparatus;
FIG. 2 is a schematic flow chart of an intelligent detection method for electronic components;
FIG. 3 is a schematic diagram showing the position distribution relationship between a distance measuring module and an electronic device to be measured according to the present invention;
fig. 4 is a schematic diagram of a matrix deployment state of the ranging module according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described below with reference to examples.
Example 1
An intelligent detection device for electronic components in this embodiment, as shown in fig. 1, includes an acquisition layer, an analysis layer, and a control layer;
Uploading standard specification parameters of the electronic element and data to be tested through the acquisition layer, completing model construction of the electronic element corresponding to the data to be tested and the electronic element corresponding to the standard specification parameters in the acquisition layer, receiving two groups of models constructed in the acquisition layer by the analysis layer in real time, selecting a comparison view angle for the two groups of models, based on similarity of the selected view angle comparison model, receiving comparison view angle selection results and model similarity comparison results in the analysis layer by the control layer, and judging or analyzing layer jump of the similarity comparison results based on decision of the two groups of results;
The analysis layer comprises a storage module, a selection module and a comparison module, wherein the storage module is used for receiving two groups of models constructed in the acquisition layer according to the standard specification parameters of the electronic element and the captured standard parameters of the electronic element, storing the models, executing the output operation of the standard models and the latest received to-be-tested models to the selection module, and the selection module is used for selecting the comparison angles applied when the comparison modules perform similarity comparison on the two groups of models and comparing the similarity of the two groups of models under the same visual angle;
the similarity between the two models at the same view angle is calculated by the following formula:
Wherein: sim (a, b) is similarity; n a、Nb is the total pixel number of the two-dimensional image respectively presented under the same visual angle of the two groups of models a and b; f ij is the total image intensity; Is the average intensity of the image;
the model constructed according to the standard specification parameters of the electronic element is recorded as a standard model, and the model constructed according to the captured standard specification parameters of the electronic element is recorded as a model to be tested;
The acquisition layer comprises an uploading module, a capturing module and a construction module, wherein the uploading module is used for uploading standard specification parameters of the electronic element, the capturing module is used for capturing the specification parameters of the electronic element, the construction module is used for receiving the uploaded standard specification parameters of the electronic element and the captured specification parameters of the electronic element, and the construction of the model is respectively executed by applying the two groups of parameters;
the capture module is arranged on an output station of electronic element production equipment, the capture module consists of a plurality of groups of ranging modules and mechanical arm modules, the plurality of groups of ranging modules are distributed on the electronic element corresponding to the data to be measured in a matrix shape, the ranging modules synchronously run, after ranging is carried out on the surface of the electronic element, the mechanical arm modules overturn the electronic element, the ranging modules are triggered to synchronously run again, and ranging operation is carried out again, wherein the ranging result is that the data to be measured corresponds to the specification parameters of the electronic element; the standard specification parameters of the electronic components uploaded by the uploading module are manually uploaded by a system end user;
the control layer comprises a receiving module and a skip module, wherein the receiving module is used for receiving the comparison view angle selected by the selection module and the similarity comparison result in the comparison module, deciding the output of the similarity comparison result or the trigger operation of the skip module based on the received comparison view angle corresponding to the model image and the image ratio, and the skip module is used for executing system skip and returning to the operation stage of the selection module of the analysis layer;
When the ratio of the model to the image in the model image corresponding to the viewing angle in the receiving module is more than or equal to 1, the output of a similarity comparison result is executed, otherwise, the operation of the skip module is triggered, and the skip module judges that the electronic element corresponding to the similarity comparison model is unqualified in the state of continuously operating for three times in the single operation process of the system;
The calculation formula of the duty ratio of the model and the image in the model image corresponding to the viewing angle is as follows:
wherein: p ratio is more than 0 and less than or equal to 1; q is the total amount of model pixel blocks in the model image; q is the total pixel block amount in the model image;
The model background image in the model image is a conveyer belt on an output station of the electronic element production equipment, and the conveyer belt is single solid color;
After the jump module triggers operation, when the receiving module in the control layer operates again, the received similarity comparison result is comprehensively evaluated, and further output is executed according to the comprehensive evaluation result, and the comprehensive evaluation logic obeys:
SIM Heald ＝sim1·ω1+sim2·ω2+...+simn-1·ωn-1+simn·ωn;
Wherein sim n is the n-th group similarity comparison result; omega n is the set logic that the larger the ratio of the model to the image is, the larger the omega value is in the model image corresponding to the n group weight, omega obeys, and the (omega 1+ω2+...+ωn-1+ωn) =1;
The system end user in the receiving module is provided with a qualification judging threshold value, and after the SIM Heald obtains the qualification judging threshold value, the SIM Heald is compared with the qualification judging threshold value to judge whether the electronic element is qualified or not;
The uploading module is connected with the capturing module and the constructing module through medium electricity, the constructing module is connected with the storage module through medium electricity, the storage module is connected with the selecting module and the comparing module through medium electricity, the comparing module is connected with the receiving module through medium electricity, and the receiving module is connected with the jumping module through medium electricity.
In this embodiment, the uploading module operates to upload standard specification parameters of the electronic component, the capturing module captures the specification parameters of the electronic component synchronously, the constructing module further operates to receive the uploaded standard specification parameters of the electronic component and the captured specification parameters of the electronic component, the two sets of parameters are applied to respectively execute the construction of the models, the storage module synchronously receives the two sets of models constructed according to the standard specification parameters of the electronic component and the captured specification parameters of the electronic component in the acquisition layer, the models are stored, the standard models and the latest receiving model are executed to output operations of the selection module, the selection module selects in real time a comparison viewing angle applied by the comparison module when the two sets of models are subjected to similarity comparison, the comparison module is used for comparing the similarity of the two sets of models based on the similarity of the same viewing angle, and finally the receiving module receives the comparison viewing angle and the similarity comparison result in the selection module, the comparison module is triggered to operate based on the output or the skip module of the similarity comparison result in the corresponding model image of the received comparison viewing angle, and the skip module is operated to execute the system to switch back to the analysis layer to select the operation stage of the module;
The similarity calculation formula is used for calculating, so that a relatively digital qualification judgment result can be provided for the system, and the qualification condition of the electronic element can be known more quickly by the system and the user side;
further, a model and image duty ratio calculation formula in the model image corresponding to the comparison view angle is used for calculating, further rotation logic of the system can be provided, and running conditions are provided for executing the comprehensive evaluation logic;
referring to fig. 3 to 4, the three-center cube is shown as an electronic component, and the ranging direction of the ranging module can be further shown according to the arrow indication, and fig. 4 is shown as a matrix distribution state of the ranging module, i.e. a honeycomb matrix.
Example 2
On the basis of embodiment 1, this embodiment further specifically describes an electronic component intelligent detection device in embodiment 1 with reference to fig. 1:
when the construction module operates and receives the specification parameters of the electronic components fed back by the capturing module, the source ranging module of each group of specification parameters of the electronic components is identified, and the received specification parameters of the electronic components are deleted from the right, left, front and back positive directions and belong to data measured by secondary operation through the identification result and further based on the feedback time sequence of the specification parameters;
When the mechanical arm module performs overturning operation on the electronic element, the overturning angle is 180 degrees, and when the distance measuring module performs distance measurement on the electronic element, the distance measuring result is corrected after the distance measuring result is obtained through the following formula:
Wherein: s is a ranging result obtained after correction; s is the ranging result obtained before correction, C is the light speed, and 0.2998m/ns is taken; Δt is the ranging time; delta is the matrix size of the ranging module; gamma is the matrix utilization rate of the ranging module; kappa is the flatness of the ranging target surface; u is the impurity content of the distance measurement environmental dust;
Wherein, the ranging data deleted in the construction module does not participate in the correction operation of the ranging result.
Through the arrangement, when the model construction is completed by the data acquisition of the ranging module, a certain degree of ranging result correction effect is brought to the electronic element, and the electronic element model constructed through the operation is more accurate and fine.
As shown in fig. 1, in the construction stage, the standard model and the model to be tested of the electronic component complete the operation of executing the model construction at the same starting point and the same starting point direction in the three-dimensional coordinate system;
When the selection module performs comparison view angle selection, the selection module performs output of the comparison view angle by the following formula:
Wherein: a comparison viewing angle to be output; g is a set of comparison angles of view; n is a set of subtractive items; t is a phase timestamp of the output phase of the comparison view angle; (t 1、t2、...、tn-1、tn) is the time corresponding to the subtraction item; /(I) Taking an integer; /(I)For comparing the/>, in the set of angles of viewItem comparison viewing angle;
wherein, in the above formula When the viewing angle is single, the method is ended, otherwise, the/>, is calculatedAs g, the calculation is performed again until in the above formula/>Is a single viewing angle for comparison.
Through the arrangement, necessary selection logic is provided for the selection module in the phase of selecting the comparison angle.
As shown in fig. 1, the comparison angles selected in the selection module include: the angles, the distances and the directions are manually set by a user at the system end to form a set, the output formulas of the comparison viewing angles take the three sets as calculation targets, and the output of the comparison viewing angles is executed.
Through the arrangement, the operation logic limitation is further carried out on the selection of the comparison angles of operation of the selection module, so that the selection module can stably output the comparison angles of operation, and necessary data support is provided for the further operation of the system.
Example 3
On the basis of embodiment 1, this embodiment further specifically describes an electronic component intelligent detection device in embodiment 1 with reference to fig. 2:
An intelligent detection method for electronic elements comprises the following steps:
Step 1: uploading standard specification parameters of the electronic element; collecting specification parameters of an electronic element to be tested;
step 11: the distance measuring module measures the electronic element to obtain specification parameters and corrects the specification parameters of the electronic element;
step 2: a distinguishing and storing stage after parameter uploading and acquisition;
Step 3: respectively constructing an electronic element standard model and a model to be tested based on the uploaded and collected electronic element specification parameters;
Step 4: a similarity comparison stage of the standard model and the model to be tested;
step 41: the similarity ratio corresponds to the selection of the application viewing angle;
Step 5: and setting a judging threshold value, comprehensively evaluating the electronic component corresponding to the model based on the similarity comparison result, and judging whether the electronic component is qualified or not by applying the judging threshold value and the comprehensive evaluation result of the electronic component.
In summary, the system in the above embodiment can respectively construct an electronic component model by uploading standard parameters of the electronic component and collecting parameters of the electronic component to be tested, further select a comparison view angle on the constructed model, and further realize similarity comparison operation of the model based on the selected comparison view angle, so as to realize appearance detection of the electronic component, so that the appearance detection of the electronic component is not limited to image collection of the electronic component, the appearance detection process of the electronic component is ensured, the diversity is more provided, and the accuracy of the detection result is greatly improved; in the running process of the system, in a similarity comparison stage for realizing the construction model of the electronic element by selecting the comparison angle, the selection of the comparison angle is more random through the provided comparison angle output algorithm, so that the electronic element can be compared with different comparison parameters, in addition, the reliability of the output result of the system is further evaluated by the model image obtained in the comparison angle selection stage, and when the reliability is not enough, the system can be driven to jump so as to realize the similarity comparison again, thereby achieving the aim of further obtaining the result; meanwhile, the system operation stability can be further maintained through the step execution of the method in the embodiment, and in the step execution process of the method, the system can be further provided to clearly operate logic, so that the specific implementation of the technical scheme is ensured, and the system operation stability is more reliable and accurate.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. An intelligent detection device for electronic elements is characterized by comprising an acquisition layer, an analysis layer and a control layer;
Uploading standard specification parameters of the electronic element and data to be tested through the acquisition layer, completing model construction of the electronic element corresponding to the data to be tested and the electronic element corresponding to the standard specification parameters in the acquisition layer, receiving two groups of models constructed in the acquisition layer by the analysis layer in real time, selecting a comparison view angle for the two groups of models, based on similarity of the selected view angle comparison model, receiving comparison view angle selection results and model similarity comparison results in the analysis layer by the control layer, and judging or analyzing layer jump of the similarity comparison results based on decision of the two groups of results;
The analysis layer comprises a storage module, a selection module and a comparison module, wherein the storage module is used for receiving two groups of models constructed in the acquisition layer according to the standard specification parameters of the electronic element and the captured standard parameters of the electronic element, storing the models, executing the output operation of the standard models and the latest received to-be-tested models to the selection module, and the selection module is used for selecting the comparison angles applied when the comparison modules perform similarity comparison on the two groups of models and comparing the similarity of the two groups of models under the same visual angle;
The two groups of models are calculated based on the similarity under the same visual angle by the following formula:
Wherein: sim (a, b) is similarity; n a、Nb is the total pixel number of the two-dimensional image respectively presented under the same visual angle of the two groups of models a and b; f ij is the total image intensity; Is the average intensity of the image;
the model constructed according to the standard specification parameters of the electronic element is recorded as a standard model, and the model constructed according to the captured standard specification parameters of the electronic element is recorded as a model to be tested;
The acquisition layer comprises an uploading module, a capturing module and a construction module, wherein the uploading module is used for uploading standard specification parameters of the electronic element, the capturing module is used for capturing the specification parameters of the electronic element, the construction module is used for receiving the uploaded standard specification parameters of the electronic element and the captured specification parameters of the electronic element, and the construction of the model is respectively executed by applying the two groups of parameters;
The capture module is arranged on an output station of electronic element production equipment, the capture module consists of a plurality of ranging modules and mechanical arm modules, the ranging modules are distributed in a matrix shape, the data to be measured corresponds to the positions of the electronic element, namely the positions in the front, the back, the left, the right and the front directions, the positions in the five positive directions, the ranging modules synchronously run, after the surface of the electronic element is subjected to ranging, the mechanical arm modules overturn the electronic element, the ranging modules are triggered to synchronously run again, the ranging operation is executed again, and the ranging result is that the data to be measured corresponds to the specification parameters of the electronic element; the standard specification parameters of the electronic components uploaded by the uploading module are manually uploaded by a system end user;
When the construction module operates and receives the electronic element specification parameters fed back by the capturing module, the source ranging module of each group of electronic element specification parameters is identified, and data which are derived from the left, right, front and back positive directions and belong to secondary operation measurement in the received electronic element specification parameters are deleted through the identification result and further based on the feedback time sequence of the specification parameters;
When the mechanical arm module performs overturning operation on the electronic element, the overturning angle is 180 degrees, and when the distance measuring module performs distance measurement on the electronic element, the distance measuring result is corrected after the distance measuring result is obtained through the following formula:
Wherein: s is a ranging result obtained after correction; s is the ranging result obtained before correction, C is the light speed, and 0.2998m/ns is taken; Δt is the ranging time; delta is the matrix size of the ranging module; gamma is the matrix utilization rate of the ranging module; kappa is the flatness of the ranging target surface; u is the impurity content of the distance measurement environmental dust;
Wherein, the ranging data deleted in the construction module does not participate in the correction operation of the ranging result;
in the construction stage, the standard model and the model to be tested of the electronic element finish the operation of executing the model construction at the same starting point and the same starting point direction in the three-dimensional coordinate system;
When the selection module performs comparison view angle selection, the selection module performs output of the comparison view angle by the following formula:
Wherein: PO g0 is the comparison viewing angle to be output; g is a set of comparison angles of view; n is a set of subtractive items; t is a phase timestamp of the output phase of the comparison view angle; (t 1、t2、...、tn-1、tn) is the time corresponding to the subtraction item; Taking an integer; /(I) For comparing the/>, in the set of angles of viewItem comparison viewing angle;
When PO g0 in the above formula is a single comparison view angle, ending, otherwise, taking the obtained PO g0 as g, and executing calculation again until PO g0 in the above formula is a single comparison view angle;
The control layer comprises a receiving module and a skip module, wherein the receiving module is used for receiving the comparison view angle selected by the selection module and the similarity comparison result in the comparison module, deciding the output of the similarity comparison result or the triggering operation of the skip module based on the received comparison view angle corresponding to the model image and the model image ratio, and the skip module is used for executing system skip and returning to the operation stage of the selection module of the analysis layer;
When the ratio of the model to the image in the model image corresponding to the viewing angle in the receiving module is more than or equal to 1, the output of a similarity comparison result is executed, otherwise, the operation of the skip module is triggered, and the skip module judges that the electronic element corresponding to the similarity comparison model is unqualified in the state of continuously operating for three times in the single operation process of the system;
After the jump module triggers operation, when the receiving module in the control layer operates again, the received similarity comparison result is comprehensively evaluated, and further output is executed according to the comprehensive evaluation result, and the comprehensive evaluation logic obeys:
SIM Heald ＝sim1·ω1+sim2·ω2+...+simn-1·ωn-1+simn·ωn;
Wherein sim n is the n-th group similarity comparison result; omega n is the set logic that the larger the ratio of the model to the image is, the larger the omega value is in the model image corresponding to the n group weight, omega obeys, and the (omega 1+ω2+...+ωn-1+ωn) =1;
the system end user in the receiving module sets a qualification judgment threshold, and the SIM Heald determines whether the electronic component is qualified or not based on comparison between the qualification judgment threshold and the SIM Heald after obtaining the qualification judgment threshold.
2. The intelligent electronic component inspection device according to claim 1, wherein the comparison angle selected by the selection module comprises: the three groups of comparison angles are manually set by a user at the system end to form a set, the three groups of sets are used as calculation targets in the output formulas of the comparison angles, and the output of the comparison angles is executed.
3. The intelligent electronic component inspection device according to claim 2, wherein the calculation formula of the model-to-image ratio in the model image corresponding to the angle of view is:
wherein: p ratio is more than 0 and less than or equal to 1; q is the total amount of model pixel blocks in the model image; q is the total pixel block amount in the model image;
The model background image in the model image is a conveying belt on an output station of the electronic element production equipment, and the conveying belt is single solid color.
4. The intelligent electronic component detecting device according to claim 3, wherein the uploading module is connected with the capturing module and the constructing module through a medium electrical property, the constructing module is connected with the storage module through a medium electrical property, the storage module is connected with the selecting module and the comparing module through a medium electrical property, the comparing module is connected with the receiving module through a medium electrical property, and the receiving module is connected with the jumping module through a medium electrical property.
5. An intelligent detection method for electronic components, which is an implementation method for an intelligent detection device for electronic components according to any one of claims 1-4, and is characterized by comprising the following steps:
Step 1: uploading standard specification parameters of the electronic element; collecting specification parameters of an electronic element to be tested;
step 11: the distance measuring module measures the electronic element to obtain specification parameters and corrects the specification parameters of the electronic element;
step 2: a distinguishing and storing stage after parameter uploading and acquisition;
Step 3: respectively constructing an electronic element standard model and a model to be tested based on the uploaded and collected electronic element specification parameters;
Step 4: a similarity comparison stage of the standard model and the model to be tested;
step 41: the similarity ratio corresponds to the selection of the application viewing angle;
Step 5: and setting a judging threshold value, comprehensively evaluating the electronic component corresponding to the model based on the similarity comparison result, and judging whether the electronic component is qualified or not by applying the judging threshold value and the comprehensive evaluation result of the electronic component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310997431.9A CN117029921B (en) | 2023-08-09 | 2023-08-09 | Intelligent detection equipment and method for electronic element |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310997431.9A CN117029921B (en) | 2023-08-09 | 2023-08-09 | Intelligent detection equipment and method for electronic element |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117029921A CN117029921A (en) | 2023-11-10 |
| CN117029921B true CN117029921B (en) | 2024-05-31 |
Family
ID=88625704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310997431.9A Active CN117029921B (en) | 2023-08-09 | 2023-08-09 | Intelligent detection equipment and method for electronic element |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117029921B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9830635B1 (en) * | 2013-03-13 | 2017-11-28 | Vast.com, Inc. | Systems, methods, and devices for determining and displaying market relative position of unique items |
| CN109443218A (en) * | 2018-10-31 | 2019-03-08 | 广东泓胜科技股份有限公司 | A kind of system for supervising vehicle overall dimension |
| CN112014404A (en) * | 2020-08-27 | 2020-12-01 | Oppo（重庆）智能科技有限公司 | Component detection method, device, system, electronic equipment and storage medium |
| CN113538380A (en) * | 2021-07-16 | 2021-10-22 | 华中科技大学同济医学院附属同济医院 | Quantitative analysis method for black high echo intensity of transcranial ultrasound |
| CN113610788A (en) * | 2021-07-27 | 2021-11-05 | 上海众壹云计算科技有限公司 | Fault monitoring method and device for image acquisition device, electronic equipment and storage medium |
| CN114199127A (en) * | 2021-12-07 | 2022-03-18 | 长春汽车工业高等专科学校 | Automobile part size detection system and method based on machine vision |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115077425A (en) * | 2022-08-22 | 2022-09-20 | 深圳市超准视觉科技有限公司 | Product detection equipment and method based on structured light three-dimensional vision |
| CN115170218A (en) * | 2022-03-10 | 2022-10-11 | 华中科技大学 | Neural network sequence recommendation method fusing graph neural network and multi-level comparison learning |
| CN115169529A (en) * | 2022-06-23 | 2022-10-11 | 西北工业大学 | General unsupervised heterogeneous graph representation learning method based on contrast learning |
| CN115290001A (en) * | 2022-10-09 | 2022-11-04 | 江门健维自动化设备有限公司 | Product testing method and system |
| CN116342602A (en) * | 2023-05-30 | 2023-06-27 | 四川都得利管业有限公司 | Fine detection method and system for production quality of plastic pipe |
| CN116416250A (en) * | 2023-06-12 | 2023-07-11 | 山东每日好农业发展有限公司 | Finished product detecting system of fast food canned product production line |
| CN116538948A (en) * | 2023-06-28 | 2023-08-04 | 深圳市鼎邦工程有限公司 | Building structure deformation monitoring system based on optical fiber sensing technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050286753A1 (en) * | 2004-06-25 | 2005-12-29 | Triant Technologies Inc. | Automated inspection systems and methods |
| US20200250897A1 (en) * | 2019-01-31 | 2020-08-06 | Marketech International Corp. | Intelligent prognostics and health management system and method |
-
2023
- 2023-08-09 CN CN202310997431.9A patent/CN117029921B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9830635B1 (en) * | 2013-03-13 | 2017-11-28 | Vast.com, Inc. | Systems, methods, and devices for determining and displaying market relative position of unique items |
| CN109443218A (en) * | 2018-10-31 | 2019-03-08 | 广东泓胜科技股份有限公司 | A kind of system for supervising vehicle overall dimension |
| CN112014404A (en) * | 2020-08-27 | 2020-12-01 | Oppo（重庆）智能科技有限公司 | Component detection method, device, system, electronic equipment and storage medium |
| CN113538380A (en) * | 2021-07-16 | 2021-10-22 | 华中科技大学同济医学院附属同济医院 | Quantitative analysis method for black high echo intensity of transcranial ultrasound |
| CN113610788A (en) * | 2021-07-27 | 2021-11-05 | 上海众壹云计算科技有限公司 | Fault monitoring method and device for image acquisition device, electronic equipment and storage medium |
| CN114199127A (en) * | 2021-12-07 | 2022-03-18 | 长春汽车工业高等专科学校 | Automobile part size detection system and method based on machine vision |
| CN115170218A (en) * | 2022-03-10 | 2022-10-11 | 华中科技大学 | Neural network sequence recommendation method fusing graph neural network and multi-level comparison learning |
| CN115082142A (en) * | 2022-05-10 | 2022-09-20 | 华南理工大学 | Recommendation method, device and medium based on heterogeneous relational graph neural network |
| CN115169529A (en) * | 2022-06-23 | 2022-10-11 | 西北工业大学 | General unsupervised heterogeneous graph representation learning method based on contrast learning |
| CN115077425A (en) * | 2022-08-22 | 2022-09-20 | 深圳市超准视觉科技有限公司 | Product detection equipment and method based on structured light three-dimensional vision |
| CN115290001A (en) * | 2022-10-09 | 2022-11-04 | 江门健维自动化设备有限公司 | Product testing method and system |
| CN116342602A (en) * | 2023-05-30 | 2023-06-27 | 四川都得利管业有限公司 | Fine detection method and system for production quality of plastic pipe |
| CN116416250A (en) * | 2023-06-12 | 2023-07-11 | 山东每日好农业发展有限公司 | Finished product detecting system of fast food canned product production line |
| CN116538948A (en) * | 2023-06-28 | 2023-08-04 | 深圳市鼎邦工程有限公司 | Building structure deformation monitoring system based on optical fiber sensing technology |
Non-Patent Citations (3)
| Title |
|---|
| 基于三维匹配的复杂曲面零件质量检测方法研究;李太峰;中国博士学位论文全文数据库 工程科技II辑;20181015(第10期);C029-6 * |
| 基于等测地区域的三维面貌相似度评价方法;李红艳;武仲科;周明全;武广艳;;计算机工程;20120705(第13期);全文 * |
| 李太峰.基于三维匹配的复杂曲面零件质量检测方法研究.中国博士学位论文全文数据库 工程科技II辑.2018,(第10期),C029-6. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117029921A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6290720B2 (en) | Inspection device, inspection method, and program | |
| CN103776841A (en) | Automatic detection device and method of synthetic leather defect | |
| JP2019100917A (en) | Inspection program generation system, generation method of inspection program and generation program of inspection program | |
| CN102564878A (en) | Hardness tester | |
| CN105548850A (en) | Full-automatic photoelectric detection system for LED nixie tube and method thereof | |
| CN103827626B (en) | Three-dimensional measuring apparatus | |
| CN108090896B (en) | Wood board flatness detection and machine learning method and device and electronic equipment | |
| CN204165517U (en) | A kind of accurate axle external diameter and the automatic detection device of beating | |
| CN107271445B (en) | Defect detection method and device | |
| CN108355979A (en) | Target tracking sorting system on conveyer belt | |
| CN108305250A (en) | The synchronous identification of unstructured robot vision detection machine components and localization method | |
| CN117593550B (en) | Coating system and spot inspection method of coating system | |
| CN110542695A (en) | method and system for checking marking quality and repeated codes | |
| CN111637834A (en) | Three-dimensional data measuring device and method | |
| CN114113144A (en) | Device and method for detecting welding quality of sealing nail | |
| CN117029921B (en) | Intelligent detection equipment and method for electronic element | |
| CN204769596U (en) | Work piece size automated inspection puts on by classification equipment | |
| CN202002893U (en) | Circuit board detector based on multi-angle linear charge coupled devices (CCDs) | |
| CN110381253A (en) | A kind of control method of quality testing, apparatus and system | |
| CN114002234A (en) | Simple ceramic tile surface defect detection device and method | |
| CN117232387A (en) | Laser and scanning three-dimensional modeling terminal equipment and method | |
| CN209565257U (en) | Engine commutator open defect automatic online vision inspection apparatus | |
| CN113686880B (en) | Cutter quality detection device based on vision | |
| JP6395455B2 (en) | Inspection device, inspection method, and program | |
| CN110632081A (en) | Bearing appearance detection equipment based on 2D and 3D vision |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240506 Address after: 518000, Building 3, Building 410, Minle Industrial Zone, Minle Community, Minzhi Street, Longhua District, Shenzhen City, Guangdong Province Applicant after: Shenzhen Fenghua Risheng Technology Co.,Ltd. Country or region after: China Address before: 5th Floor, Zone C, Software Building, No. 169 Songling Road, Laoshan District, Qingdao City, Shandong Province, 266101 Applicant before: QINGDAO SIMCE ELECTRONIC TECHN Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |