CN117237345B - Noble metal detection method and system based on pulse eddy current - Google Patents
Noble metal detection method and system based on pulse eddy current Download PDFInfo
- Publication number
- CN117237345B CN117237345B CN202311500805.8A CN202311500805A CN117237345B CN 117237345 B CN117237345 B CN 117237345B CN 202311500805 A CN202311500805 A CN 202311500805A CN 117237345 B CN117237345 B CN 117237345B
- Authority
- CN
- China
- Prior art keywords
- noble metal
- detection
- standard
- detected
- eddy current
- 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 307
- 229910000510 noble metal Inorganic materials 0.000 title claims abstract description 182
- 238000010586 diagram Methods 0.000 claims abstract description 86
- 239000010970 precious metal Substances 0.000 claims description 58
- 238000000034 method Methods 0.000 claims description 28
- 230000003872 anastomosis Effects 0.000 claims description 24
- 230000002159 abnormal effect Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 9
- 230000002950 deficient Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 13
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 6
- 238000000354 decomposition reaction Methods 0.000 description 5
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 3
- 229910052737 gold Inorganic materials 0.000 description 3
- 239000010931 gold Substances 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 229910052697 platinum Inorganic materials 0.000 description 3
- 229910052709 silver Inorganic materials 0.000 description 3
- 239000004332 silver Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
The invention relates to the technical field of noble metal detection, in particular to a noble metal detection method and a noble metal detection system based on pulse vortex, which are characterized in that a database is constructed, and an outline three-dimensional model diagram of the noble metal to be detected is imported into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected; processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal curve graph of the noble metal to be detected according to the processed pulse vortex data information; pairing and detecting the actual eddy current signal curve graph and a standard eddy current signal curve graph; if the detection result is the first detection result, the noble metal to be detected is marked as a qualified product, and if the detection result is the second detection result, the noble metal to be detected is marked as a disqualified product, so that full-automatic detection and analysis are realized, and the detection efficiency and the reliability of the adherence result can be improved to a greater extent.
Description
Technical Field
The invention relates to the technical field of noble metal detection, in particular to a noble metal detection method and system based on pulse eddy current.
Background
The noble metal detection method based on pulse eddy current is an advanced technology, and aims to meet the increasing demands of noble metal markets for detection accuracy and efficiency. Noble metals, such as gold, silver and platinum, have long been important investment and industrial raw materials, quality and purity of which are critical to market value. Conventional detection methods may have limitations such as time consuming, expensive, and the need for destructive sampling. In this context, pulsed eddy current based detection methods have evolved. This method uses the principle of electromagnetic induction to excite eddy currents on the surface of a substance by a rapid pulsed current, and then monitors and analyzes the response of the eddy currents to obtain information about the nature of the noble metal sample. The method has the characteristics of no destructiveness, rapidness, high accuracy and automation, and becomes an ideal choice for noble metal identification and analysis. Although pulsed eddy current based noble metal detection methods still have some technical drawbacks and challenges, such as the need for highly specialized software and algorithms for processing and interpreting pulsed eddy current data, this may place additional demands on operation and analysis, resulting in low detection efficiency and low reliability of detection results.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a noble metal detection method and system based on pulse eddy current.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the invention discloses a noble metal detection method based on pulse eddy current, which comprises the following steps:
acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
Obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
and if the detection result is the second detection result, determining the parameter information of the abnormal tissue in the noble metal according to the eddy current curve offset graph.
Further, in a preferred embodiment of the present invention, image information of the precious metal to be measured is obtained, and a three-dimensional model diagram of the appearance of the precious metal to be measured is constructed according to the image information, specifically:
acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
Randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
and acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
Further, in a preferred embodiment of the present invention, a database is constructed, and the three-dimensional model diagram of the appearance of the precious metal to be detected is imported into the database for pairing identification, so as to obtain a standard detection scheme and a standard detection result corresponding to the precious metal to be detected, specifically:
prefabricating a plurality of standard noble metal three-dimensional model diagrams, and prefabricating standard detection schemes and standard detection results of the various standard noble metal three-dimensional model diagrams;
Binding various standard noble metal three-dimensional model diagrams and corresponding standard detection schemes with standard detection results to obtain a plurality of standard detection data packets, constructing a database, and importing each standard detection data packet into the database;
acquiring an appearance three-dimensional model diagram of the precious metal to be detected, importing the appearance three-dimensional model diagram into the database, and calculating the similarity between the appearance three-dimensional model diagram and each standard precious metal three-dimensional model diagram in the database through an ICP algorithm to obtain a plurality of similarities;
the similarity is ranked in size to extract the maximum similarity, a standard noble metal three-dimensional model diagram corresponding to the maximum similarity is obtained, and a retrieval label is generated according to the standard noble metal three-dimensional model diagram corresponding to the maximum similarity;
and searching the database according to the search tag to search out a standard detection scheme and a standard detection result corresponding to the noble metal to be detected.
Further, in a preferred embodiment of the present invention, the pulsed eddy current data information is processed to obtain processed pulsed eddy current data information, which specifically includes:
initializing a radius field, calculating the Euclidean distance between each piece of pulse vortex data information in the radius field and the rest pieces of pulse vortex data information, averaging the Euclidean distances, and then performing inversion processing to obtain the local density of each piece of pulse vortex data information in the radius field;
Obtaining local outlier factor values of the pulse vortex data information according to the local density of the pulse vortex data information in the radius field, and comparing the local outlier factor values of the pulse vortex data information with preset local outlier factor values;
removing pulse vortex data information with the local outlier factor value larger than a preset local outlier factor value; the pulse vortex data information of which the local outlier factor value is not more than a preset local outlier factor value is reserved;
and after the processing is finished, updating the pulse vortex data information to obtain the processed pulse vortex data information.
Further, in a preferred embodiment of the present invention, the actual eddy current signal graph and the standard eddy current signal graph are paired and detected, if the detection result is a first detection result, the noble metal to be detected is marked as a qualified product, and if the detection result is a second detection result, the noble metal to be detected is marked as a non-qualified product, and a corresponding eddy current curve offset graph is obtained, specifically:
constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
After alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
if the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
Further, in a preferred embodiment of the present invention, if the detection result is the second detection result, the parameter information of the abnormal structure in the noble metal is determined according to the eddy current curve offset chart, specifically:
prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
Constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
and determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
The invention discloses a noble metal detection system based on pulse eddy current, which comprises a memory and a processor, wherein a noble metal detection method program is stored in the memory, and when the noble metal detection method program is executed by the processor, the following steps are realized:
acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
Acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
and if the detection result is the second detection result, determining the parameter information of the abnormal tissue in the noble metal according to the eddy current curve offset graph.
Further, in a preferred embodiment of the present invention, image information of the precious metal to be measured is obtained, and a three-dimensional model diagram of the appearance of the precious metal to be measured is constructed according to the image information, specifically:
acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
Calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
and acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
Further, in a preferred embodiment of the present invention, the actual eddy current signal graph and the standard eddy current signal graph are paired and detected, if the detection result is a first detection result, the noble metal to be detected is marked as a qualified product, and if the detection result is a second detection result, the noble metal to be detected is marked as a non-qualified product, and a corresponding eddy current curve offset graph is obtained, specifically:
Constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
after alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
if the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
Further, in a preferred embodiment of the present invention, if the detection result is the second detection result, the parameter information of the abnormal structure in the noble metal is determined according to the eddy current curve offset chart, specifically:
Prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
and determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected; acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal curve graph of the noble metal to be detected according to the processed pulse vortex data information; obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; and if the detection result is the first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is the second detection result, marking the noble metal to be detected as a unqualified product, and obtaining a corresponding vortex curve offset graph. The method realizes full-automatic detection and analysis, has lower requirements on detection equipment, and can greatly improve the detection efficiency and the reliability of adherence results.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a first method flow diagram of a pulsed eddy current based noble metal detection method;
FIG. 2 is a second method flow diagram of a pulsed eddy current based noble metal detection method;
FIG. 3 is a system block diagram of a pulsed eddy current based noble metal detection system.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention discloses a noble metal detection method based on pulsed eddy current, comprising the following steps:
s102: acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
s104: constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
s106: acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
s108: acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
S110: obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
s112: and if the detection result is the second detection result, determining the parameter information of the abnormal tissue in the noble metal according to the eddy current curve offset graph.
Specifically, obtaining image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information, wherein the three-dimensional model diagram specifically comprises the following steps:
acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
Randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
and acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
It should be noted that, the image information of the precious metal to be detected is obtained through the camera mounted on the detection device, then feature extraction processing is performed on the image information through the algorithms such as ORB and SIFT to obtain a plurality of contour points, and because of the influence of factors such as the precision of the shooting device, the shooting environment and the extraction algorithm, a part of noise points exist in the obtained contour points, in order to improve the reliability of the subsequent modeling, the noise points are screened out by introducing an isolated forest to eliminate the influence of factors such as the precision of the shooting device, the shooting environment and the extraction algorithm, thereby obtaining sparse contour points, in order to further improve the smoothness of the subsequent modeling, more new contour points are needed to be obtained according to the existing sparse contour points, so as to obtain dense contour points, and then a three-dimensional model diagram of the appearance of the precious metal to be detected is obtained by constructing three-dimensional modeling software such as SolidWorks according to the coordinate information of each dense contour point. The three-dimensional model diagram of the noble metal to be detected with high reduction degree can be obtained rapidly through the method, the detection efficiency can be further improved, and the reliability of the detection result is improved.
Specifically, a database is constructed, and the three-dimensional model diagram of the appearance of the precious metal to be detected is imported into the database for pairing identification, so that a standard detection scheme and a standard detection result corresponding to the precious metal to be detected are obtained, specifically:
prefabricating a plurality of standard noble metal three-dimensional model diagrams, and prefabricating standard detection schemes and standard detection results of the various standard noble metal three-dimensional model diagrams;
binding various standard noble metal three-dimensional model diagrams and corresponding standard detection schemes with standard detection results to obtain a plurality of standard detection data packets, constructing a database, and importing each standard detection data packet into the database;
acquiring an appearance three-dimensional model diagram of the precious metal to be detected, importing the appearance three-dimensional model diagram into the database, and calculating the similarity between the appearance three-dimensional model diagram and each standard precious metal three-dimensional model diagram in the database through an ICP algorithm to obtain a plurality of similarities;
the similarity is ranked in size to extract the maximum similarity, a standard noble metal three-dimensional model diagram corresponding to the maximum similarity is obtained, and a retrieval label is generated according to the standard noble metal three-dimensional model diagram corresponding to the maximum similarity;
And searching the database according to the search tag to search out a standard detection scheme and a standard detection result corresponding to the noble metal to be detected.
It should be noted that, the standard noble metal three-dimensional model diagram is drawn in advance by a technician through three-dimensional software, the standard noble metal three-dimensional model diagram includes but is not limited to model diagrams corresponding to gold, silver, platinum and the like with different shapes and sizes, and standard detection schemes and standard detection results of different standard noble metal three-dimensional model diagrams are set, wherein the standard detection schemes include detection paths, detection voltages, detection time, detection speeds and the like of detection equipment; the standard detection results comprise standard eddy current signal graphs corresponding to gold, silver, platinum and the like with different shape sizes and qualified (or not adulterated) purity. According to the method, the standard detection scheme and the standard detection result corresponding to the precious metal to be detected can be quickly matched through the three-dimensional model diagram of the appearance of the precious metal to be detected, the algorithm is simple, the robustness of the system can be improved, and the detection efficiency is further improved.
As shown in fig. 2, specifically, the pulsed eddy current data information is processed to obtain processed pulsed eddy current data information, specifically:
S202: initializing a radius field, calculating the Euclidean distance between each piece of pulse vortex data information in the radius field and the rest pieces of pulse vortex data information, averaging the Euclidean distances, and then performing inversion processing to obtain the local density of each piece of pulse vortex data information in the radius field;
s204: obtaining local outlier factor values of the pulse vortex data information according to the local density of the pulse vortex data information in the radius field, and comparing the local outlier factor values of the pulse vortex data information with preset local outlier factor values;
s206: removing pulse vortex data information with the local outlier factor value larger than a preset local outlier factor value; the pulse vortex data information of which the local outlier factor value is not more than a preset local outlier factor value is reserved;
s208: and after the processing is finished, updating the pulse vortex data information to obtain the processed pulse vortex data information.
It should be noted that the local outlier algorithm identifies outliers by comparing the relative local densities of the data points, and can quickly find those points that are less dense relative to their neighbors, which may be outliers in the data set, with higher local outlier values indicating that the point is more likely to be an outlier. By the method, abnormal pulse eddy current data acquired by the probe can be screened out, the data reliability is improved, an actual eddy current signal curve chart with high accuracy is drawn, and the reliability of a detection result is further improved.
Specifically, the actual eddy current signal curve graph and the standard eddy current signal curve graph are subjected to pairing detection, if the detection result is a first detection result, the noble metal to be detected is marked as an acceptable product, and if the detection result is a second detection result, the noble metal to be detected is marked as an unacceptable product, and a corresponding eddy current curve offset graph is obtained, specifically:
constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
after alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
if the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
If the contact ratio is greater than the preset contact ratio, it is indicated that the contact ratio of the actual eddy current signal curve graph and the standard eddy current signal curve graph of the noble metal is higher, that no impurity exists in the noble metal or adulteration occurs, that the purity of each region is qualified, a first detection result is generated, and the noble metal to be detected is marked as a qualified product. If the overlap ratio is not greater than the preset overlap ratio, the overlap ratio between the actual eddy current signal curve graph and the standard eddy current signal curve graph of the noble metal is lower, and the fact that impurities exist in the noble metal or adulteration occurs is indicated, a second detection result is generated, the noble metal to be detected is marked as an unqualified product, and the position of a region with unqualified purity is required to be further analyzed.
Specifically, if the detection result is the second detection result, determining parameter information of an abnormal structure in the noble metal according to the eddy current curve offset graph, specifically:
prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
Constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
and determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
The eddy current loss determination graph is characterized by a graph drawn according to eddy current information fed back by the eddy current loss determination graph after the eddy current detection of noble metals with various purity disqualification conditions. The eddy current curve deviation diagram is compared with each eddy current damage assessment curve diagram, then the eddy current damage assessment curve diagram with the largest fitness is matched, and then the position information, impurity type information, size information and the like of abnormal tissues in noble metals can be analyzed according to the eddy current damage assessment curve diagram.
In summary, the detection method based on pulse eddy current is beneficial to reducing noble metal counterfeiting and cheating, can rapidly distinguish whether noble metal is adulterated or not by detecting the authenticity and purity of the noble metal, has simple detection algorithm, realizes full-automatic detection analysis, has lower requirements on detection equipment, and can greatly improve the detection efficiency and the reliability of adherence results.
In addition, after obtaining the image information of the precious metal to be measured, the step of constructing the three-dimensional model diagram of the appearance of the precious metal to be measured according to the image information further comprises the following steps:
constructing a decomposition model, importing the appearance three-dimensional model diagram into the decomposition model, introducing a singular value decomposition algorithm, and performing singular value decomposition on the appearance three-dimensional model diagram to obtain a left singular vector matrix, a diagonal matrix and a right singular vector matrix;
selecting a unit vector as a coordinate vertical axis from the left singular vector matrix, selecting a unit vector as a coordinate horizontal axis from the right singular vector matrix, and constructing a three-dimensional coordinate system based on the coordinate vertical axis and the coordinate horizontal axis;
importing the left singular vector matrix, the diagonal matrix and the right singular vector matrix into the three-dimensional coordinate system, acquiring three-dimensional point cloud data corresponding to each dense edge point, generating a three-dimensional point cloud data matrix according to the three-dimensional point cloud data, and taking the three-dimensional point cloud data matrix as a cloud data coordinate number set of each dense edge point;
and acquiring a limit coordinate point set in the cloud data coordinate set, and importing the limit coordinate point set into a world coordinate system for superposition combination to obtain a corrected three-dimensional model figure of the appearance.
It should be noted that, the model map is converted into a matrix by singular value decomposition, where each element represents the luminance value of a pixel point in the model map, and the matrix is usually a two-dimensional matrix, where rows and columns respectively correspond to the height and width of the image. And then obtaining a limit coordinate point number set by reconstructing a coordinate system, so that the redundancy and the ambiguity of the three-dimensional model diagram of the appearance can be further reduced by using the method, thereby obtaining a model diagram with stronger boundary sense, and further improving the accuracy of subsequent model pairing.
As shown in fig. 3, the second aspect of the present invention discloses a precious metal detection system based on pulsed eddy current, the precious metal detection system comprising a memory 11 and a processor 12, wherein a precious metal detection method program is stored in the memory 11, and when the precious metal detection method program is executed by the processor 12, the following steps are implemented:
acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
Acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
and if the detection result is the second detection result, determining the parameter information of the abnormal tissue in the noble metal according to the eddy current curve offset graph.
Further, in a preferred embodiment of the present invention, image information of the precious metal to be measured is obtained, and a three-dimensional model diagram of the appearance of the precious metal to be measured is constructed according to the image information, specifically:
acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
And acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
Further, in a preferred embodiment of the present invention, the actual eddy current signal graph and the standard eddy current signal graph are paired and detected, if the detection result is a first detection result, the noble metal to be detected is marked as a qualified product, and if the detection result is a second detection result, the noble metal to be detected is marked as a non-qualified product, and a corresponding eddy current curve offset graph is obtained, specifically:
constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
after alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
If the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
Further, in a preferred embodiment of the present invention, if the detection result is the second detection result, the parameter information of the abnormal structure in the noble metal is determined according to the eddy current curve offset chart, specifically:
prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
and determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The noble metal detection method based on the pulse eddy current is characterized by comprising the following steps of:
acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
Acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
if the detection result is a second detection result, determining parameter information of an abnormal tissue in the noble metal according to the eddy current curve offset graph;
the method comprises the steps of constructing a database, importing an appearance three-dimensional model diagram of the precious metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the precious metal to be detected, wherein the method comprises the following specific steps:
Prefabricating a plurality of standard noble metal three-dimensional model diagrams, and prefabricating standard detection schemes and standard detection results of the various standard noble metal three-dimensional model diagrams;
binding various standard noble metal three-dimensional model diagrams and corresponding standard detection schemes with standard detection results to obtain a plurality of standard detection data packets, constructing a database, and importing each standard detection data packet into the database;
acquiring an appearance three-dimensional model diagram of the precious metal to be detected, importing the appearance three-dimensional model diagram into the database, and calculating the similarity between the appearance three-dimensional model diagram and each standard precious metal three-dimensional model diagram in the database through an ICP algorithm to obtain a plurality of similarities;
the similarity is ranked in size to extract the maximum similarity, a standard noble metal three-dimensional model diagram corresponding to the maximum similarity is obtained, and a retrieval label is generated according to the standard noble metal three-dimensional model diagram corresponding to the maximum similarity;
searching the database according to the search tag to search out a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
the method comprises the steps of carrying out pairing detection on an actual vortex signal curve graph and a standard vortex signal curve graph, marking the noble metal to be detected as an acceptable product if a detection result is a first detection result, marking the noble metal to be detected as an unacceptable product if the detection result is a second detection result, and obtaining a corresponding vortex curve offset graph, wherein the method specifically comprises the following steps:
Constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
after alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
if the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
2. The noble metal detection method based on pulse eddy current according to claim 1, wherein the image information of the noble metal to be detected is obtained, and a three-dimensional model diagram of the appearance of the noble metal to be detected is constructed according to the image information, specifically:
Acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
And acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
3. The pulse eddy current-based noble metal detection method according to claim 1, wherein the pulse eddy current data information is processed to obtain processed pulse eddy current data information, specifically:
initializing a radius field, calculating the Euclidean distance between each piece of pulse vortex data information in the radius field and the rest pieces of pulse vortex data information, averaging the Euclidean distances, and then performing inversion processing to obtain the local density of each piece of pulse vortex data information in the radius field;
obtaining local outlier factor values of the pulse vortex data information according to the local density of the pulse vortex data information in the radius field, and comparing the local outlier factor values of the pulse vortex data information with preset local outlier factor values;
removing pulse vortex data information with the local outlier factor value larger than a preset local outlier factor value; the pulse vortex data information of which the local outlier factor value is not more than a preset local outlier factor value is reserved;
And after the processing is finished, updating the pulse vortex data information to obtain the processed pulse vortex data information.
4. The method for detecting noble metal based on pulsed eddy current according to claim 1, wherein if the detection result is a second detection result, determining parameter information of abnormal tissue in the noble metal according to the eddy current curve offset map, specifically:
prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
and determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
5. The noble metal detection system based on pulse eddy current is characterized by comprising a memory and a processor, wherein the memory stores a noble metal detection method program, and when the noble metal detection method program is executed by the processor, the following steps are realized:
Acquiring image information of the precious metal to be detected, and constructing an appearance three-dimensional model diagram of the precious metal to be detected according to the image information;
constructing a database, and importing the three-dimensional model diagram of the appearance of the noble metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
acquiring preset detection parameters according to the standard detection scheme, and transmitting the preset detection parameters to a control terminal of detection equipment so as to control the detection equipment to scan and detect the noble metal to be detected based on the preset detection parameters; the detection parameters comprise a detection path, a detection voltage, a detection time and a detection speed;
acquiring pulse vortex data information fed back by the noble metal to be detected in the process of scanning and detecting the noble metal to be detected, processing the pulse vortex data information to obtain processed pulse vortex data information, and constructing an actual vortex signal graph of the noble metal to be detected according to the processed pulse vortex data information;
obtaining a standard eddy current signal curve graph of the noble metal to be detected according to the standard detection result, and carrying out pairing detection on the actual eddy current signal curve graph and the standard eddy current signal curve graph; if the detection result is a first detection result, marking the noble metal to be detected as a qualified product, and if the detection result is a second detection result, marking the noble metal to be detected as a non-qualified product, and acquiring a corresponding vortex curve offset graph;
If the detection result is a second detection result, determining parameter information of an abnormal tissue in the noble metal according to the eddy current curve offset graph;
the method comprises the steps of constructing a database, importing an appearance three-dimensional model diagram of the precious metal to be detected into the database for pairing identification to obtain a standard detection scheme and a standard detection result corresponding to the precious metal to be detected, wherein the method comprises the following specific steps:
prefabricating a plurality of standard noble metal three-dimensional model diagrams, and prefabricating standard detection schemes and standard detection results of the various standard noble metal three-dimensional model diagrams;
binding various standard noble metal three-dimensional model diagrams and corresponding standard detection schemes with standard detection results to obtain a plurality of standard detection data packets, constructing a database, and importing each standard detection data packet into the database;
acquiring an appearance three-dimensional model diagram of the precious metal to be detected, importing the appearance three-dimensional model diagram into the database, and calculating the similarity between the appearance three-dimensional model diagram and each standard precious metal three-dimensional model diagram in the database through an ICP algorithm to obtain a plurality of similarities;
the similarity is ranked in size to extract the maximum similarity, a standard noble metal three-dimensional model diagram corresponding to the maximum similarity is obtained, and a retrieval label is generated according to the standard noble metal three-dimensional model diagram corresponding to the maximum similarity;
Searching the database according to the search tag to search out a standard detection scheme and a standard detection result corresponding to the noble metal to be detected;
the method comprises the steps of carrying out pairing detection on an actual vortex signal curve graph and a standard vortex signal curve graph, marking the noble metal to be detected as an acceptable product if a detection result is a first detection result, marking the noble metal to be detected as an unacceptable product if the detection result is a second detection result, and obtaining a corresponding vortex curve offset graph, wherein the method specifically comprises the following steps:
constructing a virtual space, importing the actual vortex signal curve graph and the standard vortex signal curve graph into the virtual space, and aligning the X, Y axis coordinate system of the actual vortex signal curve graph and the standard vortex signal curve graph in the virtual space;
after alignment is finished, calculating the coincidence ratio between the actual vortex signal curve graph and the standard vortex signal curve graph through the Euclidean distance algorithm; comparing the contact ratio with a preset contact ratio;
if the overlap ratio is larger than the preset overlap ratio, generating a first detection result, and marking the noble metal to be detected as a qualified product; if the overlap ratio is not greater than the preset overlap ratio, generating a second detection result, and marking the noble metal to be detected as a defective product;
If the detection result is the second detection result, removing a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are overlapped in the virtual space, and reserving a line segment region where the actual vortex signal curve graph and the standard vortex signal curve graph are not overlapped to obtain the vortex curve offset graph.
6. The pulse eddy current-based noble metal detection system according to claim 5, wherein the image information of the noble metal to be detected is obtained, and a three-dimensional model diagram of the appearance of the noble metal to be detected is constructed according to the image information, specifically:
acquiring image information of precious metal to be detected, carrying out feature extraction processing on the image information to obtain a plurality of contour points, constructing an isolated forest model, importing the contour points into the isolated forest model, and constructing a binary tree structure based on randomly selected features until each contour point becomes isolated;
calculating an outlier score for each contour point in the isolated forest model by traversing the tree structure, comparing each outlier score with a preset threshold value, and screening out contour points with outlier scores smaller than the preset threshold value to obtain sparse contour points;
randomly accessing a sparse contour point as a reference point, establishing a three-dimensional coordinate system according to the reference point, calculating Chebyshev distances among the sparse contour points in the three-dimensional coordinate system, and pairing the sparse contour points among the shortest Chebyshev distances to obtain a plurality of pairs of sparse contour point pairs;
Marking coordinate median points of each pair of sparse contour point pairs in the three-dimensional coordinate system, and taking the coordinate median points as new contour points; generating dense contour points according to the new contour points and the sparse contour points;
and acquiring coordinate information of each dense contour point in the three-dimensional coordinate system, generating a contour point coordinate number set, and importing the contour point coordinate number set into three-dimensional modeling software to generate an outline three-dimensional model diagram of the precious metal to be detected.
7. The pulsed eddy current-based noble metal detection system of claim 5, wherein if the detection result is a second detection result, determining parameter information of an abnormal structure in the noble metal according to the eddy current curve offset map, specifically:
prefabricating various eddy current damage assessment graphs, constructing a knowledge graph, and importing the prefabricated eddy current damage assessment graphs into the knowledge graph;
importing the eddy current curve offset graph into the knowledge graph, and calculating the fitness between the eddy current curve offset graph and each eddy current damage assessment graph through a Euclidean distance algorithm to obtain a plurality of fitness;
constructing a sequence table, importing a plurality of anastomoses into the sequence table for size sorting, extracting the maximum anastomoses after sorting is completed, and obtaining an eddy current damage assessment graph corresponding to the maximum anastomoses;
And determining the parameter information of the abnormal tissue in the noble metal according to the eddy current loss curve graph corresponding to the maximum anastomosis degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311500805.8A CN117237345B (en) | 2023-11-13 | 2023-11-13 | Noble metal detection method and system based on pulse eddy current |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311500805.8A CN117237345B (en) | 2023-11-13 | 2023-11-13 | Noble metal detection method and system based on pulse eddy current |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117237345A CN117237345A (en) | 2023-12-15 |
| CN117237345B true CN117237345B (en) | 2024-02-02 |
Family
ID=89098709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311500805.8A Active CN117237345B (en) | 2023-11-13 | 2023-11-13 | Noble metal detection method and system based on pulse eddy current |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117237345B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118011133B (en) * | 2024-04-08 | 2024-06-21 | 西安乾景防务技术有限公司 | CAN bus cable detection and analysis method and system based on intelligent feedback |
| CN118279292B (en) * | 2024-05-29 | 2024-08-27 | 平利县八仙云雾茶业有限公司 | Black tea quality detection method and system based on feature recognition |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102455322A (en) * | 2010-10-19 | 2012-05-16 | 西安扩力机电科技有限公司 | Examination apparatus for eddy current flaw detector |
| CN103366439A (en) * | 2012-04-05 | 2013-10-23 | 深圳国宝造币有限公司 | Metal badge and coin, machine-readable anti-counterfeiting system thereof, and machine-readable anti-counterfeiting method of same |
| JP2016035434A (en) * | 2014-08-04 | 2016-03-17 | 国立大学法人金沢大学 | Method of evaluating metal product by eddy current |
| CN108550002A (en) * | 2018-01-17 | 2018-09-18 | 桂林电子科技大学 | A kind of bank's noble metal intelligence inventory making system and method |
| CN113639804A (en) * | 2021-10-19 | 2021-11-12 | 中国电力科学研究院有限公司 | Method and system for detecting quality of cable conduit |
| CN114689687A (en) * | 2020-12-31 | 2022-07-01 | 中国科学院沈阳自动化研究所 | Automatic eddy current detection system and method for additive manufacturing part |
| 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 |
| CN116091234A (en) * | 2023-03-27 | 2023-05-09 | 深圳上善智能有限公司 | Precious metal intelligent exchange method and system based on Internet |
| CN117016517A (en) * | 2023-09-04 | 2023-11-10 | 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) | Pesticide spraying and drift preventing method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9091664B2 (en) * | 2012-06-07 | 2015-07-28 | Thomas Krause | Pulsed eddy current sensor for precision measurement at-large lift-offs on metallic surfaces |
| CA2932064C (en) * | 2015-06-02 | 2019-12-31 | Syncrude Canada Ltd. | Tramp metal detection |
-
2023
- 2023-11-13 CN CN202311500805.8A patent/CN117237345B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102455322A (en) * | 2010-10-19 | 2012-05-16 | 西安扩力机电科技有限公司 | Examination apparatus for eddy current flaw detector |
| CN103366439A (en) * | 2012-04-05 | 2013-10-23 | 深圳国宝造币有限公司 | Metal badge and coin, machine-readable anti-counterfeiting system thereof, and machine-readable anti-counterfeiting method of same |
| JP2016035434A (en) * | 2014-08-04 | 2016-03-17 | 国立大学法人金沢大学 | Method of evaluating metal product by eddy current |
| CN108550002A (en) * | 2018-01-17 | 2018-09-18 | 桂林电子科技大学 | A kind of bank's noble metal intelligence inventory making system and method |
| CN114689687A (en) * | 2020-12-31 | 2022-07-01 | 中国科学院沈阳自动化研究所 | Automatic eddy current detection system and method for additive manufacturing part |
| CN113639804A (en) * | 2021-10-19 | 2021-11-12 | 中国电力科学研究院有限公司 | Method and system for detecting quality of cable conduit |
| 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 |
| CN116091234A (en) * | 2023-03-27 | 2023-05-09 | 深圳上善智能有限公司 | Precious metal intelligent exchange method and system based on Internet |
| CN117016517A (en) * | 2023-09-04 | 2023-11-10 | 中国农业科学院烟草研究所(中国烟草总公司青州烟草研究所) | Pesticide spraying and drift preventing method |
Non-Patent Citations (1)
| Title |
|---|
| 管状金属基体涂层厚度测量的有限元分析;杨凌 等;中国测试(第09期);第134-138页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117237345A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117237345B (en) | Noble metal detection method and system based on pulse eddy current | |
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| JP5837205B2 (en) | Text detection using image area | |
| CN108376242A (en) | For the characteristics of SSTA persistence descriptor of video | |
| CN112884718B (en) | Method, device, system and storage medium for detecting packaging code-spraying character | |
| CN114463609B (en) | Method and device for determining fluorescent mixed points in cell microscopic image | |
| CN112052813A (en) | Method, device, electronic device and readable storage medium for identifying translocation between chromosomes | |
| CN107203638B (en) | Monitoring video processing method, device and system | |
| CN115471476A (en) | Method, device, equipment and medium for detecting component defects | |
| CN107403179A (en) | A kind of register method and device of article packaged information | |
| CN117236572B (en) | Method and system for evaluating performance of dry powder extinguishing equipment based on data analysis | |
| CN110443306B (en) | Authenticity identification method for wine cork | |
| CN110704667A (en) | Semantic information-based rapid similarity graph detection algorithm | |
| CN115019152A (en) | Image shooting integrity judgment method and device | |
| CN110874602A (en) | Image identification method and device | |
| CN114862870A (en) | Speckle pattern partitioning method, device, equipment and medium | |
| CN114842228A (en) | Speckle pattern partitioning method, device, equipment and medium | |
| CN114399432A (en) | Target identification method, device, equipment, medium and product | |
| CN114550149A (en) | Pointer instrument reading method and system based on deep learning | |
| CN113537253A (en) | Infrared image target detection method and device, computing equipment and storage medium | |
| CN112633366A (en) | Jade recognition method based on feature matching | |
| CN113505784A (en) | Automatic nail annotation analysis method and device, electronic equipment and storage medium | |
| CN111753730A (en) | Image examination method and device | |
| CN111008210A (en) | Commodity identification method and device, codec and storage device | |
| McGill-Smith et al. | Jigsaw Puzzle Solver to Locate Piece Position |
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 |