CN112434738A - Decision tree algorithm-based solder paste detection method, system, electronic device and medium - Google Patents
Decision tree algorithm-based solder paste detection method, system, electronic device and medium Download PDFInfo
- Publication number
- CN112434738A CN112434738A CN202011333502.8A CN202011333502A CN112434738A CN 112434738 A CN112434738 A CN 112434738A CN 202011333502 A CN202011333502 A CN 202011333502A CN 112434738 A CN112434738 A CN 112434738A
- Authority
- CN
- China
- Prior art keywords
- solder paste
- recognition model
- morphology parameters
- detection
- decision tree
- 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.)
- Pending
Links
- 229910000679 solder Inorganic materials 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 23
- 238000003066 decision tree Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 238000012797 qualification Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 abstract description 15
- 238000004519 manufacturing process Methods 0.000 abstract description 5
- 239000000725 suspension Substances 0.000 abstract description 3
- 239000006071 cream Substances 0.000 description 5
- 238000007689 inspection Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30152—Solder
Abstract
The invention provides a solder paste detection method, a solder paste detection system, electronic equipment and a medium based on a decision tree algorithm, wherein the method comprises the following steps: acquiring the shape parameters of the solder paste; carrying out normalization processing on the morphology parameters, and setting corresponding qualified threshold values; marking the solder paste sample according to the qualified threshold and the morphology parameters to obtain a data set; and training the data set to obtain a recognition model, and finishing solder paste detection through the recognition model. The tin paste detection is completed through the recognition model, the qualified tin paste is recognized, the characteristics of the morphology parameters of the qualified tin paste are obtained, the characteristics are used as judgment conditions for judging the qualification of the tin paste, the detection of the tin paste is completed, the judgment through a single morphology parameter is avoided, the probability of erroneous judgment is reduced, and the capacity loss caused by the suspension of a production line is further avoided.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a solder paste detection method and system based on a decision tree algorithm, electronic equipment and a medium.
Background
In the IT manufacturing industry, a process of a Printed Circuit Board (PCB) needs to be detected to ensure that the PCB can meet requirements of morphology, quality, reliability and the like, and in the PCB detection process, Solder Paste detection, especially Solder Paste thickness (sol Paste Inspection/SPI) detection, is an important link. At present, the SPI detection efficiency and the accuracy are low, the production efficiency is influenced, and the capacity loss is caused.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a method, a system, an electronic device and a medium for solder paste detection based on a decision tree algorithm, which are used to solve the problem of inconvenient solder paste detection in the prior art.
In order to achieve the above and other related objects, the present invention provides a solder paste testing method based on a decision tree algorithm, comprising:
obtaining the morphology parameters of the solder paste, wherein the morphology parameters at least comprise one of the following parameters: offset, height, area, volume;
carrying out normalization processing on the morphology parameters, and setting corresponding qualified threshold values;
marking the solder paste sample according to the qualified threshold and the morphology parameters to obtain a data set;
and training the data set to obtain a recognition model, and finishing solder paste detection through the recognition model.
Optionally, the step of training the data set to obtain the recognition model includes: and (4) marking the qualified sample as 0, marking the unqualified sample as 1, acquiring the cross entropy of the morphology parameters, and determining the morphology parameters as the recognition model when the cross entropy is 0.
Optionally, corresponding qualified threshold values are respectively set according to the morphology parameters, cross entropies corresponding to the morphology parameters are sequentially obtained, and when each cross entropy is 0, a qualified judgment condition of the solder paste is obtained.
Optionally, the recognition model is determined according to a determination condition that the solder paste is qualified.
Optionally, the mathematical expression of the cross entropy is:
where Encopy (t) is the cross entropy, t is the profile parameter, and p (i | t) is the probability of class i.
Optionally, the step of training the data set to obtain the recognition model further includes: and training the data set through a random forest algorithm to obtain the recognition model.
Optionally, the offset comprises an X-axis offset and a Y-axis offset.
A solder paste detection system based on a decision tree algorithm comprises:
the acquisition module is used for acquiring the morphology parameters of the solder paste, and the morphology parameters at least comprise one of the following parameters: offset, height, area, volume;
the preprocessing module is used for carrying out normalization processing on the morphology parameters and setting corresponding qualified threshold values;
the training module is used for marking the solder paste sample according to the qualified threshold value and the morphology parameters to obtain a data set;
the detection module is used for training the data set to obtain a recognition model, the solder paste detection is completed through the recognition model, and the acquisition module, the preprocessing module and the training module are connected with the detection module.
An electronic device, comprising:
one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform one or more of the methods.
One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods described.
As described above, the decision tree algorithm-based solder paste detection method, system, electronic device and medium of the present invention have the following beneficial effects:
the tin paste detection is completed through the recognition model, the qualified tin paste is recognized, the characteristics of the morphology parameters of the qualified tin paste are obtained, the characteristics are used as judgment conditions for judging the qualification of the tin paste, the detection of the tin paste is completed, the judgment through a single morphology parameter is avoided, the probability of erroneous judgment is reduced, and the capacity loss caused by the suspension of a production line is further avoided.
Drawings
Fig. 1 is a schematic diagram of a solder paste inspection method based on a decision tree algorithm according to an embodiment of the invention.
FIG. 2 is a schematic diagram of a solder paste inspection system based on a decision tree algorithm according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
It should be noted that the drawings provided in the present embodiment are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated. The structures, proportions, sizes, and other dimensions shown in the drawings and described in the specification are for understanding and reading the present disclosure, and are not intended to limit the scope of the present disclosure, which is defined in the claims, and are not essential to the art, and any structural modifications, changes in proportions, or adjustments in size, which do not affect the efficacy and attainment of the same are intended to fall within the scope of the present disclosure. In addition, the terms "upper", "lower", "left", "right", "middle" and "one" used in the present specification are for clarity of description, and are not intended to limit the scope of the present invention, and the relative relationship between the terms and the terms is not to be construed as a scope of the present invention.
The inventor finds that some of the Solder pastes which are judged to be unqualified in the Solder Paste thickness (sol Paste Inspection/SPI) detection still have normal performance, but the Solder pastes cannot be judged to be qualified through the current SPI detection, so that the SPI detection has misjudgment and capacity loss, and in order to provide the accuracy of the Solder Paste detection/SPI detection, the inventor provides a Solder Paste detection method based on a decision tree algorithm, please refer to fig. 1, and the invention provides a Solder Paste detection method based on the decision tree algorithm, which comprises the following steps:
s1: obtaining the morphology parameters of the solder paste, wherein the morphology parameters at least comprise one of the following parameters: offset, height, area, volume, such as may be obtained by an SPI device;
s2: normalizing the morphology parameters, and setting corresponding qualified threshold values to enable the data of each morphology parameter to be between 0 and 1, so that invalid data can be deleted in order to avoid generating larger sample deviation of the solder paste;
s3: marking the solder paste sample according to the qualified threshold and the morphology parameters to obtain a data set;
s4: the method comprises the steps of training a data set to obtain an identification model, completing solder paste detection through the identification model, obtaining the characteristics of the morphology parameters of qualified solder paste through identifying the qualified solder paste, using the characteristics as judgment conditions for judging the qualification of the solder paste, completing the detection of the solder paste, avoiding judging through a single morphology parameter, reducing the probability of generating misjudgment, and further avoiding the capacity loss caused by the suspension of a production line.
In some implementations, the step of training the data set to obtain the recognition model includes: and (4) marking the qualified sample as 0, marking the unqualified sample as 1, acquiring the cross entropy of the morphology parameters, and determining the morphology parameters as the recognition model when the cross entropy is 0.
In some implementation processes, corresponding qualified threshold values are respectively set according to the morphology parameters, cross entropies corresponding to the morphology parameters are sequentially obtained, and when the cross entropies are 0, a qualified judgment condition of the solder paste is obtained. For example, when x (x-axis offset) <0.1, y (y-axis offset) <0.1, area >0.7, volume >0.6, height >0.6 are found, the pass threshold value can be determined to pass, and the determination is performed, and the recognition model is determined according to the determination condition that the solder paste is pass. For another example, first training x (x-axis offset) <0.1, calculating information gain, selecting one feature with increased information gain for the next branch, then determining y (y-axis offset) <0.1, area >0.7, volume >0.6, and height >0.6, and when the cross entropy is 0, obtaining the corresponding determination condition.
In some implementations, the mathematical expression of the cross entropy is:
in the implementation process, p (i | t) is 2 types of qualified or unqualified, when the probability is 1, the corresponding cross entropy obtained by mathematical expression of the cross entropy is 0, namely the qualified/unqualified probability is 100%, and the process of supervised learning is to find the judgment condition of the classification of various morphology parameters to enable the corresponding cross entropy to be 0.
In some implementations, the step of training the data set to obtain the recognition model further includes: and training the data set through a Random Forest algorithm (Random Forest) to obtain the recognition model.
Referring to fig. 2, the present invention further provides a solder paste detection system based on a decision tree algorithm, including:
the acquisition module is used for acquiring the morphology parameters of the solder paste, and the morphology parameters at least comprise one of the following parameters: offset, height, area, volume;
the preprocessing module is used for carrying out normalization processing on the morphology parameters and setting corresponding qualified threshold values;
the training module is used for marking the solder paste sample according to the qualified threshold value and the morphology parameters to obtain a data set;
the detection module is used for training the data set to obtain a recognition model, the solder paste detection is completed through the recognition model, and the acquisition module, the preprocessing module and the training module are connected with the detection module. Through the tin cream detection is accomplished to the recognition model, through discerning qualified tin cream, acquires the characteristic of the morphological parameter of qualified tin cream to regard it as the basis of judging that the tin cream is qualified, accomplish the detection to the tin cream, avoid judging through single morphological parameter, reduce the probability that produces the erroneous judgement, and then avoid producing the productivity loss that line pause caused.
An embodiment of the present invention provides an electronic device, including: one or more processors; and one or more machine readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform one or more of the methods. The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
Embodiments of the invention also provide one or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform one or more of the methods described herein. The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A solder paste detection method based on a decision tree algorithm is characterized by comprising the following steps:
obtaining the morphology parameters of the solder paste, wherein the morphology parameters at least comprise one of the following parameters: offset, height, area, volume;
carrying out normalization processing on the morphology parameters, and setting corresponding qualified threshold values;
marking the solder paste sample according to the qualified threshold and the morphology parameters to obtain a data set;
and training the data set to obtain a recognition model, and finishing solder paste detection through the recognition model.
2. The decision tree algorithm-based solder paste testing method according to claim 1, wherein the step of training the data set to obtain the recognition model comprises: and (4) marking the qualified sample as 0, marking the unqualified sample as 1, acquiring the cross entropy of the morphology parameters, and determining the morphology parameters as the recognition model when the cross entropy is 0.
3. The decision tree algorithm-based solder paste detection method according to claim 2, wherein corresponding qualification thresholds are respectively set according to the morphology parameters, cross entropies corresponding to the morphology parameters are sequentially obtained, and when the cross entropies are all 0, a judgment condition that the solder paste is qualified is obtained.
4. The method of claim 3, wherein the recognition model is determined based on a determination that the solder paste is acceptable.
5. The decision tree algorithm-based solder paste detection method according to claim 2, wherein the mathematical expression of the cross entropy is:
where Encopy (t) is the cross entropy, t is the profile parameter, and p (i | t) is the probability of class i.
6. The decision tree algorithm-based solder paste testing method according to claim 2, wherein the step of training the data set to obtain the recognition model further comprises: and training the data set through a random forest algorithm to obtain the recognition model.
7. The decision tree algorithm-based solder paste detection method according to any one of claims 1 to 6, wherein the offset comprises an X-axis offset and a Y-axis offset.
8. A solder paste detection system based on a decision tree algorithm is characterized by comprising:
the acquisition module is used for acquiring the morphology parameters of the solder paste, and the morphology parameters at least comprise one of the following parameters: offset, height, area, volume;
the preprocessing module is used for carrying out normalization processing on the morphology parameters and setting corresponding qualified threshold values;
the training module is used for marking the solder paste sample according to the qualified threshold value and the morphology parameters to obtain a data set;
the detection module is used for training the data set to obtain a recognition model, the solder paste detection is completed through the recognition model, and the acquisition module, the preprocessing module and the training module are connected with the detection module.
9. An electronic device, comprising:
one or more processors; and
one or more machine-readable media having instructions stored thereon that, when executed by the one or more processors, cause the electronic device to perform the method recited by one or more of claims 1-7.
10. One or more machine-readable media having instructions stored thereon, which when executed by one or more processors, cause an apparatus to perform the method recited by one or more of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011333502.8A CN112434738A (en) | 2020-11-24 | 2020-11-24 | Decision tree algorithm-based solder paste detection method, system, electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011333502.8A CN112434738A (en) | 2020-11-24 | 2020-11-24 | Decision tree algorithm-based solder paste detection method, system, electronic device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112434738A true CN112434738A (en) | 2021-03-02 |
Family
ID=74698626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011333502.8A Pending CN112434738A (en) | 2020-11-24 | 2020-11-24 | Decision tree algorithm-based solder paste detection method, system, electronic device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112434738A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040220770A1 (en) * | 2002-08-22 | 2004-11-04 | Toyota Jidosha Kabushiki Kaisha | Pass/fail judgment device, pass/fail judgment program, pass/fail judgment method, and multivariate statistics analyzer |
| CN109360183A (en) * | 2018-08-20 | 2019-02-19 | 中国电子进出口有限公司 | A kind of quality of human face image appraisal procedure and system based on convolutional neural networks |
| CN110598761A (en) * | 2019-08-26 | 2019-12-20 | 深圳大学 | Dispensing detection method and device and computer readable storage medium |
| CN111079638A (en) * | 2019-12-13 | 2020-04-28 | 河北爱尔工业互联网科技有限公司 | Target detection model training method, device and medium based on convolutional neural network |
| CN111766253A (en) * | 2019-03-15 | 2020-10-13 | 鸿富锦精密电子（成都）有限公司 | Solder paste printing quality detection method, data processing device, and computer storage medium |
| CN111833324A (en) * | 2020-07-09 | 2020-10-27 | 中国计量大学 | Optical fiber ferrule defect detection method based on deep learning |
-
2020
- 2020-11-24 CN CN202011333502.8A patent/CN112434738A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040220770A1 (en) * | 2002-08-22 | 2004-11-04 | Toyota Jidosha Kabushiki Kaisha | Pass/fail judgment device, pass/fail judgment program, pass/fail judgment method, and multivariate statistics analyzer |
| CN109360183A (en) * | 2018-08-20 | 2019-02-19 | 中国电子进出口有限公司 | A kind of quality of human face image appraisal procedure and system based on convolutional neural networks |
| CN111766253A (en) * | 2019-03-15 | 2020-10-13 | 鸿富锦精密电子（成都）有限公司 | Solder paste printing quality detection method, data processing device, and computer storage medium |
| CN110598761A (en) * | 2019-08-26 | 2019-12-20 | 深圳大学 | Dispensing detection method and device and computer readable storage medium |
| CN111079638A (en) * | 2019-12-13 | 2020-04-28 | 河北爱尔工业互联网科技有限公司 | Target detection model training method, device and medium based on convolutional neural network |
| CN111833324A (en) * | 2020-07-09 | 2020-10-27 | 中国计量大学 | Optical fiber ferrule defect detection method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109839385B (en) | Self-adaptive PCB defect visual positioning detection and classification system | |
| CN111340027A (en) | Steel pile identification method and system, electronic equipment and medium | |
| CN110672323A (en) | Bearing health state assessment method and device based on neural network | |
| CN112070837A (en) | Part positioning and grabbing method and system based on visual analysis | |
| WO2023226706A1 (en) | Defect detection method and apparatus | |
| CN114375107A (en) | Method, device and equipment for reconstructing unstructured influence factors of solder paste printing of SMT (surface mount technology) production line | |
| CN115631178A (en) | Automatic wafer defect detection method, system, equipment and storage medium | |
| CN109325539A (en) | Insulator falls crosstalk detecting method and device | |
| CN116993725B (en) | Intelligent patch information processing system of flexible circuit board | |
| CN112434738A (en) | Decision tree algorithm-based solder paste detection method, system, electronic device and medium | |
| CN114018219A (en) | Transmission tower vibration monitoring method, device, equipment and storage medium | |
| CN115761648A (en) | Oil leakage evaluation method, device, equipment, medium and product applied to transformer | |
| Chand | Investigating Vision Based Sorting of Used Items | |
| CN115311237A (en) | Image detection method and device and electronic equipment | |
| CN110874837B (en) | Defect automatic detection method based on local feature distribution | |
| CN114565772A (en) | Set feature extraction method and device, electronic equipment and storage medium | |
| CN114596302A (en) | PCB defect detection method, system, medium, equipment and terminal | |
| CN115619698A (en) | Method and device for detecting defects of circuit board and model training method | |
| CN111194004B (en) | Base station fingerprint positioning method, device and system and computer readable storage medium | |
| CN112732842A (en) | Data processing method and system based on environment big data, electronic device and medium | |
| CN112926443A (en) | Method and device for judging whether people exist in tobacco leaf purchasing conveyor belt based on convolutional neural network | |
| CN112419274A (en) | Solder paste detection method, system, electronic device and medium | |
| CN112801998B (en) | Printed circuit board detection method and device, computer equipment and storage medium | |
| CN114943769B (en) | Positioning method, positioning device, electronic equipment and medium | |
| CN115372793B (en) | Circuit detection method for integrated circuit |
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 |