CN112257735A - Internal defect radar detection system based on artificial intelligence - Google Patents
Internal defect radar detection system based on artificial intelligence Download PDFInfo
- Publication number
- CN112257735A CN112257735A CN202010439001.1A CN202010439001A CN112257735A CN 112257735 A CN112257735 A CN 112257735A CN 202010439001 A CN202010439001 A CN 202010439001A CN 112257735 A CN112257735 A CN 112257735A
- Authority
- CN
- China
- Prior art keywords
- detection
- disease
- radar
- model
- image
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 230000007547 defect Effects 0.000 title claims abstract description 31
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000012544 monitoring process Methods 0.000 claims abstract description 3
- 201000010099 disease Diseases 0.000 claims description 55
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 55
- 238000012549 training Methods 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000009412 basement excavation Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 5
- 230000000149 penetrating effect Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009417 prefabrication Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000011800 void material Substances 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
- G06F18/21—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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V3/00—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation
- G01V3/12—Electric or magnetic prospecting or detecting; Measuring magnetic field characteristics of the earth, e.g. declination, deviation operating with electromagnetic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The invention discloses an internal defect radar detection system based on artificial intelligence, which comprises a detection front end, a detection cloud end and a detection terminal, wherein the detection front end is connected with the detection cloud end; the detection front end is used for acquiring a radar scanning image and preprocessing the image; the detection cloud is used for identifying the image of the monitoring front end according to the intelligent image identification model; and the detection terminal is used for acquiring the identification result from the detection cloud and displaying the identification result. According to the method, the intelligent recognition model is built, automatic analysis of radar scan data is realized through the intelligent recognition model, the experience of interpreters is not depended on, the recognition result is stable, the efficiency is high, the labor cost is reduced, the accuracy of image recognition can be improved, and the batch recognition of images is realized.
Description
Technical Field
The invention relates to the field of engineering detection, in particular to an internal defect radar detection system based on artificial intelligence.
Background
The ground penetrating radar is a non-damage detection technology, and can achieve the detection purpose by emitting high-frequency electromagnetic waves to the underground or a target body on the ground surface and processing and analyzing echo signals without any damage to the ground surface and the target body. When the ground penetrating radar works, high-frequency electromagnetic pulses with certain intensity are transmitted to an underground medium, and the high-frequency electromagnetic waves are directionally transmitted to the underground through the transmitting antenna in a wide-band pulse mode and are received by the receiving antenna. When high frequency electromagnetic waves propagate in a medium, the path, electromagnetic field strength and waveform of the high frequency electromagnetic waves vary according to the electrical characteristics and geometric forms of the medium passing through the medium. The spatial position and structure of the subsurface or earth-penetrating body can be determined by collecting, processing and analyzing the time-domain waveform of the received reflected signal. The ground penetrating radar can perform rapid and continuous section imaging and large-range detection, and data acquisition and processing imaging are integrally completed.
At present, the analysis work of the ground penetrating radar data is completed manually, the required labor cost is high, and the interpretation result is extremely unstable due to the fact that the analysis work depends on the experience of interpretation personnel excessively. Secondly, the detection area is generally very large, the manual interpretation is difficult to be well executed due to the huge data volume, erroneous judgment and missed judgment are easy to occur, and the efficiency is low.
Disclosure of Invention
The invention aims to provide an internal defect radar detection system based on artificial intelligence so as to improve the accuracy and efficiency of defect detection.
The invention achieves the aim through the following technical scheme: an internal defect radar detection system based on artificial intelligence comprises a detection front end, a detection cloud end and a detection terminal;
the detection front end is used for acquiring a radar scanning image and preprocessing the image;
the detection cloud is used for identifying the image of the monitoring front end according to the intelligent image identification model;
the detection terminal is used for acquiring the identification result from the detection cloud and displaying the identification result;
the preprocessing specifically includes time zero offset, background clearing, snow noise interference elimination, horizontal scale adjustment and signal amplitude automatic gain adjustment processing of the radar scanning image.
The intelligent picture identification model is obtained through the following steps:
1) obtaining a disease map set
And (3) manually identifying the disease types and regions in the radar image according to the radar disease characteristics, and determining the disease types represented by the picture characteristics by adopting a manual excavation verification method for the suspicious part to form a rich and accurate disease map set.
2) Intelligent recognition model for training pictures
And taking the abundant and accurate disease atlas as training data to train the intelligent image recognition model.
Two models are recommended and trained, wherein the model is characterized in that: identifying whether the picture has diseases or not, and marking out the disease area; model II: and identifying whether the picture has diseases or not, identifying the types of the diseases and marking the disease areas.
The acquisition of the intelligent image recognition model further comprises the following step 3) of model verification:
and importing other pictures with definite disease types into the model to obtain a recognition result, and if the recognition effect of the model does not meet the requirement, expanding training data aiming at the mistaken recognition of the disease types until the recognition accuracy of the model reaches the expectation.
The disease atlas obtained in the step 1) can be obtained by the following method:
and prefabricating defects, and acquiring radar images of the prefabricated defects so as to form a disease atlas with definite disease types and areas.
The detection cloud adopts a Baidu cloud easy customized training and service platform to construct the intelligent picture recognition model and select a general algorithm or an AutoDL Transfer algorithm.
Compared with the prior art, the invention has the following beneficial effects:
1) according to the method, the intelligent recognition model is constructed, then automatic analysis of radar scan data is realized through the intelligent recognition model, the experience of interpreters is not relied on, the recognition result is stable, the efficiency is high, the labor cost is reduced, the accuracy of image recognition can be improved, and the batch recognition of images is realized;
2) according to the method, a set of atlas with clear disease types and ranges is obtained through a manual identification and verification mode or a defect prefabrication mode, an intelligent identification model is constructed on the basis of the atlas, and the intelligent identification model can be fully guaranteed to have better accuracy;
3) the image is preprocessed during model construction and before image recognition, interference signals can be removed after the image is preprocessed, local signals are highlighted, construction characteristics are better displayed, and a small target body is displayed more clearly, so that internal defects or construction of image reaction can be clearer, and the recognition accuracy of the method can be improved to a great extent;
4) according to the invention, two sets of intelligent identification models are constructed, and when the disease type is not required to be identified, the image identification can be directly carried out through the model I, so that higher accuracy is obtained.
Drawings
FIG. 1 is a connection diagram of an artificial intelligence based radar detection system for internal defects according to an embodiment of the present invention;
FIG. 2 is a flow chart of an artificial intelligence based internal defect radar detection system in accordance with an embodiment of the present invention;
3a-3d comparing the original image and the processed image recognition effect before and after image preprocessing;
FIG. 4 is a radar image of a water-rich area;
FIG. 5 is a void defect radar image;
FIGS. 6a-6d are display views of pictures after disease types and areas are marked in the platform;
7a-7b are examples of the effect of defect identification for model (r);
FIGS. 8a-8d are examples of model (model) (defect identification effect).
Detailed Description
The technical solution of the present invention will be described in detail below with reference to the specific embodiments and the accompanying drawings. It is to be understood that the described embodiments are merely illustrative of some, but not all, embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the solution of the present invention, shall fall within the scope of the present invention.
An internal defect radar detection system based on artificial intelligence is shown in figure 1 and mainly comprises three parts: the system comprises a detection front end, a detection cloud end and a detection terminal.
The detection front end is a Lao Rei ground penetrating radar and RADAN7 software system. And a Baidu cloud easy DL customized training and service platform is adopted in the detection cloud. The detection terminal is a computer or a mobile phone with a corresponding APP program and is used for displaying the detection result.
FIG. 2 is a flow chart of the detection of the system, including the steps of:
A. and (3) selecting shielding antennas (200MHz, 400MHz and 900MHz) with different frequencies by using the Lao-Rey ground penetrating radar according to the depth to be detected on site, and collecting the time domain waveform of the on-site detection object.
B. Preprocessing the radar image output by step a using RADAN7 software. The preprocessing specifically includes time zero offset, background removal, snow noise interference elimination, horizontal scale adjustment and automatic signal amplitude gain adjustment through RADA 7 software. After the image is preprocessed, interference signals can be eliminated, local signals are highlighted, the structural characteristics are better displayed, and the small target body is more clearly displayed, so that the internal defects or the structures of the image reaction are clearer, and the identification accuracy of the model can be improved to a great extent.
As shown in fig. 3a to 3d, the preprocessed image can enhance the image characteristics of the defect type, so that the defect that cannot be automatically recognized by a part of the original image can be automatically recognized after being preprocessed. Fig. 3a shows radar detection original images without preprocessing. Fig. 3b is a diagram of a preprocessed radar image of the original image of fig. 3 a. Fig. 3c shows the identification effect of the original image of radar detection without preprocessing shown in fig. 3a, and it can be seen that the image without preprocessing cannot identify the defect area when the defect features are not obvious. Fig. 3d shows the recognition effect of fig. 3b on the preprocessed radar detection, where again the defect features are not evident, the preprocessed picture can identify the diseased area.
C. And (3) importing the standard format pictures processed by RADA 7 software into a Baidu cloud easy custom training and service platform in batches.
D. And selecting different trained models for image disease analysis according to data analysis requirements.
E. And printing or displaying the detection result on the detection terminal.
The model in the step D is an intelligent picture identification model, and the obtaining process is as follows:
d1, extracting picture disease characteristics
The current cognition is mainly that the disease types are four as follows:
a water-rich area: the wave packet appears to be primarily a top surface reflected wave. Due to the rapid attenuation of electromagnetic waves, the reflection below the top surface is weak, the water-rich abnormal top surface reflected wave is in phase with the incident wave, and the bottom surface reflected wave is opposite to the incident wave.
Soil body loosening area: the radar image generally shows that the in-phase axis is transversely discontinuous, and the waveform structure is relatively disordered and irregular.
And (3) emptying: the radar image generally shows weak reflection of a shallow stratum, the same phase axis is broken, and an upper and a lower obvious reflection interfaces exist.
Cavity: the radar image shows the characteristics of a weak reflector in a cavity area, inclined horizontal reflected waves and irregular scattered waves on two sides of the cavity area, vertical interface section waves of the cavity area, large irregular scattered waves below the cavity area, a strong reflecting surface of a top interface of the cavity area, continuous horizontal reflected waves at the bottom of a bottom interface of the cavity area and the like.
D2, acquiring a disease map set
And manually identifying the disease types and areas in the pictures according to the radar disease characteristics, and determining the picture characteristics representing the disease types by adopting a manual excavation verification method for the suspicious parts to form an accurate and rich disease picture set.
D3 training picture intelligent recognition model
And deep learning modeling, wherein low-level features are combined into more abstract high-level features in a specific mode to further analyze the data. The neural network comprises a plurality of hidden layers, and has more layers and higher accuracy compared with a common neural network. The Baidu cloud easy customized training and service platform is used for building a deep learning classification model. The cloud service can select a general algorithm or an AutoDL Transfer algorithm, and takes a rich and accurate disease atlas as training data. According to actual needs, two models are trained, wherein the model is used for distinguishing whether an image has a disease or not and marking out a diseased area; and secondly, distinguishing whether the picture has diseases or not and identifying the types and the areas of the diseases at the same time.
D4, model verification
And importing the residual pictures of the disease graph centralized model training into the model to obtain a picture disease identification result. If the model identification effect is not satisfactory, the training data can be expanded according to the fault type identified by mistake. And after the model training meets the expected accuracy requirement, releasing the model and carrying out formal application.
Fig. 4 and 5 are radar detection cross-sectional views after disease types and regions are marked. And (5) carrying out manual excavation verification on the in-doubt images.
And (3) introducing the radar detection cross-sectional views with the determined disease types and areas into a Baidu cloud easy customized training and service platform in batches, and marking the disease types and the positions of the pictures on the platform, as shown in FIGS. 6a to 6 d. A general algorithm is selected in the cloud service, rich and accurate radar detection section images are used as training data, and an intelligent picture recognition model is trained.
After a large amount of training, a perfect model is released. 7a-7b are the results of identification using model I, it can be seen that the identification accuracy of each disease area in the image is more than 96%. Fig. 8a to 8d show the result of identification using the model 2, and it can be seen that the type of the disease in each area in the image and the identification accuracy of the disease area are more than 95%.
Claims (6)
1. An internal defect radar detection system based on artificial intelligence is characterized by comprising a detection front end, a detection cloud end and a detection terminal;
the detection front end is used for acquiring a radar scanning image and preprocessing the image;
the detection cloud is used for identifying the image of the monitoring front end according to the intelligent image identification model;
the detection terminal is used for acquiring the identification result from the detection cloud and displaying the identification result;
the preprocessing specifically includes time zero offset, background clearing, snow noise interference elimination, horizontal scale adjustment and signal amplitude automatic gain adjustment processing of the radar scanning image.
2. The radar detection system for internal defects according to claim 1, wherein the intelligent identification model of pictures is obtained by the following steps:
1) obtaining a disease map set
Manually identifying the type and the area of the disease in the radar image according to the radar disease characteristics, and determining the type of the disease represented by the picture characteristics by adopting a manual excavation verification method for the suspected part to form a disease map set;
2) intelligent recognition model for training pictures
And taking the disease atlas as training data to train the intelligent image recognition model.
3. The radar detection system for internal defects according to claim 2, wherein in step 2), two models are trained, wherein: identifying whether the picture has diseases or not, and marking out the disease area; model II: and identifying whether the picture has diseases or not, identifying the types of the diseases and marking the disease areas.
4. The radar detection system for internal defects according to claim 2 or 3, wherein the obtaining of the intelligent recognition model for pictures further comprises the step 3) of verifying the model:
and importing other pictures with definite disease types into the model, obtaining a recognition result, and if the recognition effect of the model does not meet the requirement, expanding training data aiming at the mistaken recognition of the disease types until the recognition accuracy of the model reaches the expectation.
5. The radar internal defect detection system of claim 2, wherein the step 1) obtains the disease map set by:
and prefabricating defects, and acquiring radar images of the prefabricated defects so as to form a disease atlas with definite disease types and areas.
6. The radar internal defect detection system of claim 1, wherein the detection cloud adopts a Baidu cloud EasyDL customized training and service platform to construct the intelligent picture recognition model selection general algorithm or an AutoDL Transfer algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010439001.1A CN112257735A (en) | 2020-05-22 | 2020-05-22 | Internal defect radar detection system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010439001.1A CN112257735A (en) | 2020-05-22 | 2020-05-22 | Internal defect radar detection system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112257735A true CN112257735A (en) | 2021-01-22 |
Family
ID=74224330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010439001.1A Pending CN112257735A (en) | 2020-05-22 | 2020-05-22 | Internal defect radar detection system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112257735A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837163A (en) * | 2021-11-29 | 2021-12-24 | 深圳大学 | Tunnel monitoring method and system based on three-dimensional ground penetrating radar and storage medium |
| CN115063345A (en) * | 2022-05-11 | 2022-09-16 | 水利部交通运输部国家能源局南京水利科学研究院 | Electromagnetic wave standard map-based dam hidden danger identification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5673050A (en) * | 1996-06-14 | 1997-09-30 | Moussally; George | Three-dimensional underground imaging radar system |
| CN107527067A (en) * | 2017-08-01 | 2017-12-29 | 中国铁道科学研究院铁道建筑研究所 | A kind of Railway Roadbed intelligent identification Method based on GPR |
| CN109685011A (en) * | 2018-12-25 | 2019-04-26 | 北京华航无线电测量研究所 | A kind of underground utilities detection recognition method based on deep learning |
-
2020
- 2020-05-22 CN CN202010439001.1A patent/CN112257735A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5673050A (en) * | 1996-06-14 | 1997-09-30 | Moussally; George | Three-dimensional underground imaging radar system |
| CN107527067A (en) * | 2017-08-01 | 2017-12-29 | 中国铁道科学研究院铁道建筑研究所 | A kind of Railway Roadbed intelligent identification Method based on GPR |
| CN109685011A (en) * | 2018-12-25 | 2019-04-26 | 北京华航无线电测量研究所 | A kind of underground utilities detection recognition method based on deep learning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113837163A (en) * | 2021-11-29 | 2021-12-24 | 深圳大学 | Tunnel monitoring method and system based on three-dimensional ground penetrating radar and storage medium |
| CN113837163B (en) * | 2021-11-29 | 2022-03-08 | 深圳大学 | Tunnel monitoring method and system based on three-dimensional ground penetrating radar and storage medium |
| CN115063345A (en) * | 2022-05-11 | 2022-09-16 | 水利部交通运输部国家能源局南京水利科学研究院 | Electromagnetic wave standard map-based dam hidden danger identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11900630B2 (en) | Method for detecting leakage of water supply pipe based on ground-penetrating radar three-dimensional image attribute analysis | |
| CN104020495B (en) | Automatic underground pipeline parameter recognizing method on basis of ground penetrating radar | |
| CN109782274B (en) | Water damage identification method based on time-frequency statistical characteristics of ground penetrating radar signals | |
| CN112462346A (en) | Ground penetrating radar roadbed defect target detection method based on convolutional neural network | |
| CN111798411B (en) | Concrete inner steel bar intelligent positioning method based on ground penetrating radar and deep learning | |
| CN112130132A (en) | Underground pipeline detection method and system based on ground penetrating radar and deep learning | |
| CN112257735A (en) | Internal defect radar detection system based on artificial intelligence | |
| CN106446919A (en) | Quick detection method for ground penetrating radar hyperbolic curve target | |
| CN113359101B (en) | Underground target detection method, system and computer storage medium | |
| CN103485265A (en) | Road quality detection method of UWB (ultra wide band) GPR (GPR) and detection device of method | |
| CN114266892A (en) | Pavement disease identification method and system for multi-source data deep learning | |
| CN116778329A (en) | Urban road underground shallow disease detection method, device, equipment and medium | |
| Sun et al. | Estimating parameters of the tree root in heterogeneous soil environments via mask-guided multi-polarimetric integration neural network | |
| CN103218614A (en) | Method for identifying severe convection weather based on combination of manifold learning and rough set | |
| CN206091960U (en) | Multi -functional pit shaft detection device | |
| CN111652063A (en) | Gray level stacking chart identification method of ground penetrating radar | |
| CN115859081A (en) | Visual detection method and device for pipeline | |
| CN109905190A (en) | A kind of modeling method of low frequency propagation of ground wave time delay time-varying characteristics | |
| CN112581456B (en) | Image crack real-time extraction method suitable for ultrasonic imaging logging | |
| CN112964938B (en) | Lightning single-station positioning method, device and system based on artificial intelligence | |
| CN109061628A (en) | A kind of Enteromorpha extracting method for sweeping enhancing slowly based on multifunction radar | |
| CN115542278A (en) | Ground penetrating radar original data-based pavement damage area judgment method | |
| Guo et al. | Research on tunnel lining image target recognition method based on YOLOv3 | |
| CN113988142A (en) | Tunnel lining cavity acoustic identification method based on convolutional neural network | |
| CN106442576A (en) | Hidden quality nondestructive detection method and system of shield tunnel structure |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210325 Address after: 528437 room 409-17, 4 / F, building C, innovation center building, 34 Xiangshan Avenue, Cuiheng New District, Zhongshan City, Guangdong Province Applicant after: Guangdong Jianke Innovation Technology Research Institute Co.,Ltd. Address before: 510599 1st floor, Fengdong building, No. 121, Xianlie East Road, Tianhe District, Guangzhou, Guangdong Province Applicant before: GUANGDONG CONSTRUCTION PROJECT QUALITY SAFETY INSPECTION STATION Co.,Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240202 Address after: 510599 1st floor, Fengdong building, No. 121, Xianlie East Road, Tianhe District, Guangzhou, Guangdong Province Applicant after: GUANGDONG CONSTRUCTION PROJECT QUALITY SAFETY INSPECTION STATION CO.,LTD. Country or region after: China Address before: 528437 room 409-17, 4 / F, building C, innovation center building, 34 Xiangshan Avenue, Cuiheng New District, Zhongshan City, Guangdong Province Applicant before: Guangdong Jianke Innovation Technology Research Institute Co.,Ltd. Country or region before: China |