CN110726643A - Laser detection system and detection method for diamond density test - Google Patents
Laser detection system and detection method for diamond density test Download PDFInfo
- Publication number
- CN110726643A CN110726643A CN201911125552.4A CN201911125552A CN110726643A CN 110726643 A CN110726643 A CN 110726643A CN 201911125552 A CN201911125552 A CN 201911125552A CN 110726643 A CN110726643 A CN 110726643A
- Authority
- CN
- China
- Prior art keywords
- diamond
- measured
- detected
- detection
- white background
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N9/00—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity
- G01N9/02—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity by measuring weight of a known volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N9/00—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity
- G01N9/02—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity by measuring weight of a known volume
- G01N2009/022—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity by measuring weight of a known volume of solids
- G01N2009/024—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity by measuring weight of a known volume of solids the volume being determined directly, e.g. by size of container
Abstract
The invention discloses a laser detection system for diamond density test, which comprises: the detection box is of a hexagonal prism structure, and each surface in the detection box is provided with a white background plate; the laser light sources are respectively arranged at each vertex inside the detection box in a one-to-one correspondence mode and used for projecting the edge profile of the diamond to be detected to the white background plate; the data detection module is used for detecting the diamond to be detected; and the data processing module receives the detection data of the data detection module, outputs the detection data after processing, detects the diamond to be detected through the white background plate of the detection box and the laser light source, quickly obtains the density of the diamond to be detected, and is simple and convenient. The invention also provides a laser detection method for diamond density testing, which is used for collecting the edge contour projection area of the diamond to be tested on each white background plate and determining the volume of the diamond to be tested based on the BP neural network. The volume of the diamond to be detected can be corrected, and the detection precision of the density of the diamond to be detected is improved.
Description
Technical Field
The invention belongs to the technical field of diamond testing, and particularly relates to a laser detection system and a detection method for diamond density testing.
Background
The density of a solid material is a fundamental physical parameter of the solid material, which is the basis for qualitative analysis of the solid material. When the mine is searched in the field, the mineral density of a plurality of similar rocks cannot be quickly identified, and the subjective judgment of engineers is mainly relied on; the jewelry auction industry, how accurately the color and luster of jewelry jade are determined, is a very effective parameter, such as artificial imitation beeswax and natural beeswax.
At present, the solid density test and the volume parameter are obtained by a drainage method, so that liquid is needed to be contained in a container for containing the liquid. Sometimes, the liquid is an organic solvent, such as bromoform, tetrachloroethylene and the like, which is toxic and harmful, cannot be carried on site at all, cannot be operated in the field, and when the diamond material is tested, the diamond material is damaged or polluted to a certain extent by using the organic solvent, so that the value of the diamond material is reduced.
Disclosure of Invention
The invention aims to design and develop a laser detection system for diamond density test, which detects the diamond to be tested through a white background plate of a detection box and a laser light source, quickly obtains the density of the diamond to be tested, and is simple and convenient.
The invention also aims to design and develop a laser detection method for diamond density test, which collects the edge contour projection area of the diamond to be tested on each white background plate and determines the volume of the diamond to be tested based on the BP neural network.
The invention can also correct the volume of the diamond to be detected, and improve the detection precision of the density of the diamond to be detected.
The technical scheme provided by the invention is as follows:
a laser detection system for diamond density testing, comprising:
the detection box is of a hexagonal prism structure, and each surface in the detection box is provided with a white background plate;
the laser light sources are respectively arranged at each vertex inside the detection box in a one-to-one correspondence mode and used for projecting the edge profile of the diamond to be detected to the white background plate;
the data detection module is used for detecting the diamond to be detected;
and the data processing module receives the detection data of the data detection module and outputs the detection data after processing.
Preferably, the data detection module includes:
the area identification sensors are respectively arranged on the white background plate and used for detecting the area of the edge contour projection of the diamond to be detected;
and the weight sensor is arranged on the bottom surface of the detection box and is used for detecting the weight of the diamond to be detected.
Preferably, the data processing module includes:
and the controller receives the area data and the weight data and outputs the density data of the diamond to be detected.
A laser detection method for testing the diamond density collects the edge contour projection area of the diamond to be tested on each white background plate, and determines the volume of the diamond to be tested based on a BP neural network, and specifically comprises the following steps:
step one, acquiring the edge contour projection area [ S ] of the diamond to be detected on each white background plate through a sensor1,S2,S3,S4,S5,S6,Su,Sd]；
Wherein [ S ]1,S2,S3,S4,S5,S6]The edge profile projection areas of the diamond to be measured on six sides of the detection box [ S ]u,Sd]Respectively the edge contour projection areas of the diamond to be detected on the top surface and the bottom surface of the detection box;
step two, normalizing the projection area of the diamond to be detected on the edge contour of each white background plate in sequence, and determining the input layer vector x ═ x of the three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8}; wherein, { x1,x2,x3,x4,x5,x6The coefficients are respectively the edge profile projection area of the diamond to be measured on six sides of the detection box, { x }7,x8Respectively representing the edge contour projection area coefficients of the diamond to be detected on the top surface and the bottom surface of the detection box;
step (ii) ofMapping the input layer vector to a middle layer, wherein the middle layer vector y is { y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
step four, obtaining an output layer vector z ═ z1}; wherein z is1To the volume coefficient of the diamond to be measured, the
V＝z1Vmax，
Wherein z is1As output layer vector parameter, VmaxV is the set maximum volume of the diamond to be measured.
Preferably, the method further comprises correcting the volume of the diamond to be measured:
wherein, VsTo calibrate the volume of the diamond to be measured, DmaxIs the maximum thickness of the diamond to be measured in the vertical direction of the top surface of the detection box1The distance from the center of gravity of the diamond to be measured to the farthest point, xi, of the top surface of the diamond to be measured0Correcting the coefficient and xi on the basis0∈[0.9,1.1]And e is the base of the natural logarithm.
Preferably, the set maximum volume of the diamond to be measured is:
wherein d ismaxIs the maximum diameter length L of the diamond to be measured in any direction with the center of gravity as the center of circlepThe diameter length of the diamond to be measured in the P-th direction with the center of gravity as the center of a circle is taken as the length of the diamond to be measured, and the number of the diamond to be measured in the direction divided with the center of gravity as the center of a circle is taken as the number of the diamond to be measured.
Preferably, in the second step, the formula for normalizing the projection area of the edge profile of the diamond to be measured on each white background plate is as follows:
wherein x iskFor parameters in the input layer vector, XkRespectively representing the edge contour projection area of the diamond to be measured on each white background plate, wherein k is 1,2,3,4,5,6,7 and 8; xmaxAnd XminThe maximum value and the minimum value of the projection area of the edge profile of the diamond to be detected on each white background plate are respectively.
Preferably, the centre of gravity of the diamond to be measured is determined by a suspension method.
Preferably, the base correction coefficient ξ0＝1。
Preferably, the number m of the intermediate layer nodes satisfies:wherein n is the number of nodes of the input layer, and t is the number of nodes of the output layer.
The invention has the following beneficial effects:
(1) the laser detection system for testing the diamond density is designed and developed, the diamond to be tested is detected through the white background plate of the detection box and the laser light source, the diamond density to be tested is quickly obtained, and the laser detection system is simple and convenient.
(2) The laser detection method for diamond density testing, which is designed and developed by the invention, collects the edge contour projection area of the diamond to be tested on each white background plate, and determines the volume of the diamond to be tested based on a BP neural network. The invention can also correct the volume of the diamond to be detected, and improve the detection precision of the density of the diamond to be detected.
Drawings
Fig. 1 is a schematic structural diagram of a laser detection system for diamond density testing according to the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1, the present invention provides a laser detection system for diamond density test, comprising: the detection box 100 is of a hexagonal prism structure, and each surface inside the detection box is provided with a white background plate 110; the laser light sources 120 are respectively arranged at each vertex inside the detection box in a one-to-one correspondence manner (12 vertexes are provided, and the laser light sources are arranged, in the figure, the laser light sources 120 only make a simple illustration, only mark two positions, but do not influence the expression of the whole meaning), and are used for projecting the edge profile of the diamond to be detected onto the corresponding white background plate; the data detection module is used for detecting the diamond to be detected; and the data processing module receives the detection data of the data detection module and outputs the detection data after processing.
The data detection module comprises: the area identification sensors are respectively arranged on the white background plate and used for detecting the area of the edge contour projection of the diamond to be detected; and the weight sensor is arranged on the bottom surface of the detection box and is used for detecting the weight of the diamond to be detected.
The data processing module comprises a controller which receives the area data and the weight data and outputs the density data of the diamond to be detected.
The laser detection system for testing the diamond density is designed and developed, the diamond to be tested is detected through the white background plate of the detection box and the laser light source, the diamond density to be tested is quickly obtained, and the laser detection system is simple and convenient.
The invention also provides a laser detection method for diamond density test, which collects the edge contour projection area of the diamond to be tested on each white background plate and determines the volume of the diamond to be tested based on the BP neural network, and specifically comprises the following steps:
step one, establishing a BP neural network model;
the BP network system structure adopted by the invention is composed of three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing the working state of the equipment are correspondingly provided, and the signal parameters are provided by a data preprocessing module. The second layer is a hidden layer, and has m nodes, and is determined by the training process of the network in a self-adaptive mode. The third layer is an output layer, t nodes are provided in total, and the output is determined by the response actually required by the system.
The mathematical model of the network is:
inputting a layer vector: x ═ x1,x2,…,xn)T
Intermediate layer vector: y ═ y1,y2,…,ym)T
Outputting a layer vector: z is (z)1,z2,…,zt)T
In the invention, the number of nodes of the input layer is n equals to 8, and the number of nodes of the output layer is t equals to 1. The number m of hidden layer nodes is estimated by the following formula:
according to the sampling period, the input 8 parameters are { x1,x2,x3,x4,x5,x6The coefficients are respectively the edge profile projection area of the diamond to be measured on six sides of the detection box, { x }7,x8Respectively representing the edge contour projection area coefficients of the diamond to be detected on the top surface and the bottom surface of the detection box;
before the data is input into the neural network, the data is normalized to a number between 0-1.
The formula for normalizing the projection area of the diamond to be measured on the edge profile of each white background plate is as follows:
wherein x iskFor parameters in the input layer vector, XkRespectively the edge contour projection area of the diamond to be measured on each white background plate, namely [ S ]1,S2,S3,S4,S5,S6,Su,Sd]，k＝1,2,3,4,5,6,7,8；XmaxAnd XminRespectively the edge contour projection area of the diamond to be measured on each white background plate ([ S ]1,S2,S3,S4,S5,S6,Su,Sd]) Maximum and minimum values of (a).
The 1 parameter of the output signal is expressed as: z is a radical of1The volume coefficient of the diamond to be measured;
volume coefficient z of diamond to be measured1Expressed as the ratio of the volume of the diamond to be measured to the set maximum volume of the diamond to be measured
V＝z1Vmax，
Wherein z is1As output layer vector parameter, VmaxV is the set maximum volume of the diamond to be measured.
The set maximum volume of the diamond to be detected is as follows:
wherein d ismaxIs the maximum diameter length L of the diamond to be measured in any direction with the center of gravity as the center of circlepThe diameter length of the diamond to be measured in the P-th direction with the center of gravity as the center of a circle is taken as the length of the diamond to be measured, and the number of the diamond to be measured in the direction divided with the center of gravity as the center of a circle is taken as the number of the diamond to be measured.
Step two: and (5) training the BP neural network.
After the BP neural network node model is established, the training of the BP neural network can be carried out. Obtaining training samples according to empirical data of the product, and giving a connection weight w between an input node i and a hidden layer node jijConnection weight w between hidden layer node j and output layer node kjkThreshold value theta of hidden layer node jjThreshold value w of node k of output layerij、wjk、θj、θkAre all random numbers between-1 and 1.
Continuously correcting w in the training processijAnd wjkUntil the system error is less than or equal to the expected error, the neural net is completedAnd (4) training the collaterals.
As shown in table 1, a set of training samples is given, along with the values of the nodes in the training process.
TABLE 1 training Process node values
Step three, collecting data operation parameters and inputting the data operation parameters into a neural network to obtain a regulation and control coefficient;
the trained artificial neural network is solidified in the chip, so that the hardware circuit has the functions of prediction and intelligent decision making, and intelligent hardware is formed. After the intelligent hardware is powered on and started, the laser detection system starts to operate.
Using a sensor to acquire the edge contour projection area [ S ] of the diamond to be measured on each white background plate1,S2,S3,S4,S5,S6,Su,Sd](ii) a Normalizing the parameters to obtain an input vector x ═ x of the BP neural network1,x2,x3,x4,x5,x6,x7,x8Obtaining an output vector z ═ z { z } through operation of a BP neural network1}；
Output the volume of the diamond to be measured so that
V＝z1Vmax，
Wherein z is1As output layer vector parameter, VmaxV is the set maximum volume of the diamond to be measured.
Step four: correcting the volume of the diamond to be detected:
wherein, VsTo calibrate the volume of the diamond to be measured, DmaxIs to be treatedMeasuring the maximum thickness of diamond in the vertical direction of the top surface of the detection box1The distance from the center of gravity of the diamond to be measured to the farthest point, xi, of the top surface of the diamond to be measured0Correcting the coefficient and xi on the basis0∈[0.9,1.1]And e is the base of the natural logarithm.
Wherein, the center of gravity of the diamond to be measured is obtained by a suspension method, and the basic correction coefficient xi0＝1。
The laser detection method for diamond density testing, which is designed and developed by the invention, collects the edge contour projection area of the diamond to be tested on each white background plate, and determines the volume of the diamond to be tested based on a BP neural network. The invention can also correct the volume of the diamond to be detected, and improve the detection precision of the density of the diamond to be detected.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (10)
1. A laser detection system for diamond density testing, comprising:
the detection box is of a hexagonal prism structure, and each surface in the detection box is provided with a white background plate;
the laser light sources are respectively arranged at each vertex inside the detection box in a one-to-one correspondence mode and used for projecting the edge profile of the diamond to be detected to the white background plate;
the data detection module is used for detecting the diamond to be detected;
and the data processing module receives the detection data of the data detection module and outputs the detection data after processing.
2. The laser detection system for diamond density testing according to claim 1, wherein said data detection module comprises:
the area identification sensors are respectively arranged on the white background plate and used for detecting the area of the edge contour projection of the diamond to be detected;
and the weight sensor is arranged on the bottom surface of the detection box and is used for detecting the weight of the diamond to be detected.
3. The laser detection system for diamond density testing according to claim 2, wherein said data processing module comprises:
and the controller receives the area data and the weight data and outputs the density data of the diamond to be detected.
4. A laser detection method for diamond density testing is characterized by collecting edge contour projection areas of diamonds to be tested on each white background plate and determining the volume of the diamonds to be tested based on a BP neural network, and specifically comprises the following steps:
step one, acquiring the edge contour projection area [ S ] of the diamond to be detected on each white background plate through a sensor1,S2,S3,S4,S5,S6,Su,Sd]；
Wherein [ S ]1,S2,S3,S4,S5,S6]The edge profile projection areas of the diamond to be measured on six sides of the detection box [ S ]u,Sd]Respectively the edge contour projection areas of the diamond to be detected on the top surface and the bottom surface of the detection box;
step two, normalizing the projection area of the diamond to be detected on the edge contour of each white background plate in sequence, and determining the input layer vector x ═ x of the three-layer BP neural network1,x2,x3,x4,x5,x6,x7,x8}; wherein, { x1,x2,x3,x4,x5,x6The coefficients are respectively the edge profile projection area of the diamond to be measured on six sides of the detection box, { x }7,x8Respectively representing the edge contour projection area coefficients of the diamond to be detected on the top surface and the bottom surface of the detection box;
step three, the input layer vector is mapped to a middle layer, and the middle layer vector y is { y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
step four, obtaining an output layer vector z ═ z1}; wherein z is1To the volume coefficient of the diamond to be measured, the
V＝z1Vmax，
Wherein z is1As output layer vector parameter, VmaxV is the set maximum volume of the diamond to be measured.
5. The laser probing method for diamond density measurement according to claim 4, further comprising calibrating the volume of diamond to be measured:
wherein, VsTo calibrate the volume of the diamond to be measured, DmaxIs the maximum thickness of the diamond to be measured in the vertical direction of the top surface of the detection box1The distance from the center of gravity of the diamond to be measured to the farthest point, xi, of the top surface of the diamond to be measured0Correcting the coefficient and xi on the basis0∈[0.9,1.1]And e is the base of the natural logarithm.
6. The laser detection method for diamond density measurement according to claim 4 or 5, wherein the set maximum volume of diamond to be measured is:
wherein d ismaxIs the maximum diameter length L of the diamond to be measured in any direction with the center of gravity as the center of circlepThe diameter length of the diamond to be measured in the P-th direction with the center of gravity as the center of a circle is taken as the length of the diamond to be measured, and the number of the diamond to be measured in the direction divided with the center of gravity as the center of a circle is taken as the number of the diamond to be measured.
7. The laser detection method for diamond density measurement according to claim 6, wherein in the second step, the formula for normalizing the projection area of the edge profile of the diamond to be measured on each white background plate is as follows:
wherein x iskFor parameters in the input layer vector, XkRespectively representing the edge contour projection area of the diamond to be measured on each white background plate, wherein k is 1,2,3,4,5,6,7 and 8; xmaxAnd XminThe maximum value and the minimum value of the projection area of the edge profile of the diamond to be detected on each white background plate are respectively.
8. The laser probing method for diamond density measurement as claimed in claim 5 wherein the center of gravity of the diamond to be measured is determined by hanging.
9. The laser detection method for diamond density test according to claim 5 or 8, wherein said basic correction coefficient ξ0＝1。
10. The laser probing method for diamond density measurement according to claim 4,5, 7 or 8 wherein said number m of interlayer nodes satisfies:wherein n is the number of nodes of the input layer, and t is the number of nodes of the output layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125552.4A CN110726643A (en) | 2019-11-18 | 2019-11-18 | Laser detection system and detection method for diamond density test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911125552.4A CN110726643A (en) | 2019-11-18 | 2019-11-18 | Laser detection system and detection method for diamond density test |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110726643A true CN110726643A (en) | 2020-01-24 |
Family
ID=69225298
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911125552.4A Withdrawn CN110726643A (en) | 2019-11-18 | 2019-11-18 | Laser detection system and detection method for diamond density test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110726643A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1419322A (en) * | 2002-12-31 | 2003-05-21 | 中国建筑材料科学研究院 | Ceramic light-gathering cavity material, ceramic light-gathering cavity and making method thereof |
| CN1554576A (en) * | 2003-12-24 | 2004-12-15 | 厦门大学 | Process for preparing gallium nitride p-type effective doping under laser induction |
| CN103903303A (en) * | 2012-12-27 | 2014-07-02 | 清华大学 | Three-dimensional model establishing method and device |
| CN105404153A (en) * | 2015-12-17 | 2016-03-16 | 吉林大学 | Coil winding machine control method based on BP nerve network, and coil winding machine |
| WO2016142689A1 (en) * | 2015-03-06 | 2016-09-15 | Micromass Uk Limited | Tissue analysis by mass spectrometry or ion mobility spectrometry |
| CN106537458A (en) * | 2014-03-12 | 2017-03-22 | 利弗环球有限责任公司 | Systems and methods for reconstructing 3-dimensional model based on vertices |
| CN107462493A (en) * | 2017-08-29 | 2017-12-12 | 北京中建建筑科学研究院有限公司 | A kind of plastic products apparent density assay method |
| US20180059126A1 (en) * | 2015-03-06 | 2018-03-01 | Micromass Uk Limited | Cell Population Analysis |
| CN108544146A (en) * | 2018-04-28 | 2018-09-18 | 辽宁机电职业技术学院 | A kind of one side welding device and its control method |
| CN109142141A (en) * | 2018-06-19 | 2019-01-04 | 湖北大学 | A kind of three-dimensional laser real-time detection solid material density system and method |
| WO2019010470A1 (en) * | 2017-07-07 | 2019-01-10 | University Of Louisville Research Foundation, Inc. | Segmentation of medical images |
| CN109615653A (en) * | 2018-12-19 | 2019-04-12 | 上海大学 | Percolating water area detecting and recognition methods based on deep learning and visual field projection model |
| CN110333330A (en) * | 2019-06-13 | 2019-10-15 | 江苏康缘药业股份有限公司 | A kind of detection method of tablet disintegration times |
-
2019
- 2019-11-18 CN CN201911125552.4A patent/CN110726643A/en not_active Withdrawn
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1419322A (en) * | 2002-12-31 | 2003-05-21 | 中国建筑材料科学研究院 | Ceramic light-gathering cavity material, ceramic light-gathering cavity and making method thereof |
| CN1554576A (en) * | 2003-12-24 | 2004-12-15 | 厦门大学 | Process for preparing gallium nitride p-type effective doping under laser induction |
| CN103903303A (en) * | 2012-12-27 | 2014-07-02 | 清华大学 | Three-dimensional model establishing method and device |
| CN106537458A (en) * | 2014-03-12 | 2017-03-22 | 利弗环球有限责任公司 | Systems and methods for reconstructing 3-dimensional model based on vertices |
| WO2016142689A1 (en) * | 2015-03-06 | 2016-09-15 | Micromass Uk Limited | Tissue analysis by mass spectrometry or ion mobility spectrometry |
| US20180059126A1 (en) * | 2015-03-06 | 2018-03-01 | Micromass Uk Limited | Cell Population Analysis |
| CN105404153A (en) * | 2015-12-17 | 2016-03-16 | 吉林大学 | Coil winding machine control method based on BP nerve network, and coil winding machine |
| WO2019010470A1 (en) * | 2017-07-07 | 2019-01-10 | University Of Louisville Research Foundation, Inc. | Segmentation of medical images |
| CN107462493A (en) * | 2017-08-29 | 2017-12-12 | 北京中建建筑科学研究院有限公司 | A kind of plastic products apparent density assay method |
| CN108544146A (en) * | 2018-04-28 | 2018-09-18 | 辽宁机电职业技术学院 | A kind of one side welding device and its control method |
| CN109142141A (en) * | 2018-06-19 | 2019-01-04 | 湖北大学 | A kind of three-dimensional laser real-time detection solid material density system and method |
| CN109615653A (en) * | 2018-12-19 | 2019-04-12 | 上海大学 | Percolating water area detecting and recognition methods based on deep learning and visual field projection model |
| CN110333330A (en) * | 2019-06-13 | 2019-10-15 | 江苏康缘药业股份有限公司 | A kind of detection method of tablet disintegration times |
Non-Patent Citations (6)
| Title |
|---|
| IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS: "High-Dimensional Function Approximation With Neural Networks for Large Volumes of Data", 《IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS》 * |
| KARADAS, M 等: "Feasibility and resolution limits of opto-magnetic imaging of neural network activity in brain slices using color centers in diamond", 《SCIENTIFIC REPORTS》 * |
| 栾雅春: "丹东黄蜡石的宝石矿物学特征", 《昆明冶金高等专科学校学报》 * |
| 王静 等: "采用两层级联神经网络从少量投影重构二维图像", 《计算机辅助设计与图形学学报》 * |
| 胡淑娟 等: "投影寻踪法在建立积雪深度模型上的应用", 《水文》 * |
| 赵攀 等: "基于图像参数的BP网络之岩石颗粒体积估算", 《计算机测量与控制》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106568783B (en) | A kind of hardware defect detecting system and method | |
| CN104299247B (en) | A kind of video target tracking method based on adaptive measuring matrix | |
| CN108763857A (en) | A kind of process soft-measuring modeling method generating confrontation network based on similarity | |
| CN109919934A (en) | A kind of liquid crystal display panel defect inspection method based on the study of multi-source domain depth migration | |
| CN108491858A (en) | Method for detecting fatigue driving based on convolutional neural networks and system | |
| CN106841075B (en) | COD ultraviolet spectra on-line checking optimization method neural network based | |
| CN109190665A (en) | A kind of general image classification method and device based on semi-supervised generation confrontation network | |
| CN108898215A (en) | A kind of sludge bulking INTELLIGENT IDENTIFICATION method based on two type fuzzy neural networks | |
| CN109242194B (en) | Thickener underflow concentration prediction method based on mixed model | |
| CN108647583A (en) | A kind of face recognition algorithms training method based on multiple target study | |
| CN106777527A (en) | Monkey operation energy consumption analysis method based on neural network model | |
| CN107909564A (en) | A kind of full convolutional network image crack detection method based on deep learning | |
| CN104463243B (en) | Sex-screening method based on average face feature | |
| CN109934810A (en) | A kind of defect classification method based on improvement population wavelet neural network | |
| CN108960421A (en) | The unmanned surface vehicle speed of a ship or plane online forecasting method based on BP neural network of improvement | |
| CN107506862A (en) | A kind of online real-time estimate system and method for grinding particle size based on Internet of Things | |
| Wang et al. | Features extraction of flotation froth images and BP neural network soft-sensor model of concentrate grade optimized by shuffled cuckoo searching algorithm | |
| CN110309609A (en) | A kind of architecture indoor air quality evaluation method based on rough set and wavelet neural network | |
| CN106568647A (en) | Nerve network-based concrete strength predication method | |
| CN109948527A (en) | Small sample terahertz image foreign matter detecting method based on integrated deep learning | |
| CN113758890A (en) | Gas concentration calculation method, device, equipment and storage medium | |
| CN109002862A (en) | A kind of flexible measurement method neural network based and system towards copper ore floatation machine | |
| CN103984856A (en) | System and method for predicting longitudinal crack width of wall body based on neural network | |
| CN106845051A (en) | A kind of near infrared no-wound blood sugar test wavelength Variable Selection method based on Combinatorial Optimization | |
| CN110543656A (en) | LED fluorescent powder glue coating thickness prediction method based on deep learning |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200124 |