CN115903020A - Three-dimensional seismic data reconstruction method, apparatus, and medium - Google Patents
Three-dimensional seismic data reconstruction method, apparatus, and medium Download PDFInfo
- Publication number
- CN115903020A CN115903020A CN202211423672.4A CN202211423672A CN115903020A CN 115903020 A CN115903020 A CN 115903020A CN 202211423672 A CN202211423672 A CN 202211423672A CN 115903020 A CN115903020 A CN 115903020A
- Authority
- CN
- China
- Prior art keywords
- dimensional seismic
- image
- data
- reconstruction
- neural network
- 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
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The embodiment of the invention discloses a three-dimensional seismic data reconstruction method, equipment and a medium. The method comprises the following steps: constructing a three-dimensional seismic image with data loss by using complete three-dimensional seismic data; performing preliminary reconstruction on the three-dimensional seismic image based on the image contour; training a neural network model by using the preliminarily reconstructed three-dimensional seismic image to enable the output of the neural network model to be close to the complete three-dimensional seismic data; converting three-dimensional seismic data to be reconstructed into a three-dimensional seismic image to be reconstructed, and performing primary reconstruction on the three-dimensional seismic image based on an image contour; and inputting the three-dimensional seismic image after the primary reconstruction into the trained neural network model to obtain three-dimensional seismic data after the secondary reconstruction. The method and the device improve the accuracy and reliability of the three-dimensional seismic data reconstruction.
Description
Technical Field
The embodiment of the invention relates to the technical field of seismic data processing, in particular to a three-dimensional seismic data reconstruction method, equipment and medium.
Background
Seismic data acquired in the field usually have the problem of seismic channel loss, and the reconstruction of the seismic data is always a difficult problem in seismic data processing.
At present, the seismic data are reconstructed by using a deep learning method, and the originally acquired seismic data are directly used as network input. Under the condition of complex underground structure, it is difficult to directly learn the data rule from the original seismic data, and the result is not very stable.
Disclosure of Invention
The embodiment of the invention provides a three-dimensional seismic data reconstruction method, equipment and a medium, which improve the precision and reliability of three-dimensional seismic data reconstruction.
In a first aspect, an embodiment of the present invention provides a three-dimensional seismic data reconstruction method, including:
constructing a three-dimensional seismic image with data loss by using complete three-dimensional seismic data;
performing preliminary reconstruction on the three-dimensional seismic image based on the image contour;
training a neural network model by using the preliminarily reconstructed three-dimensional seismic image to enable the output of the neural network model to be close to the complete three-dimensional seismic data;
converting three-dimensional seismic data to be reconstructed into a three-dimensional seismic image to be reconstructed, and performing primary reconstruction on the three-dimensional seismic image based on an image contour; and inputting the three-dimensional seismic image after the primary reconstruction into the trained neural network model to obtain three-dimensional seismic data after the secondary reconstruction.
In a second aspect, an embodiment of the present invention provides an electronic device, including:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the three-dimensional seismic data reconstruction method described above.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the three-dimensional seismic data reconstruction method described above.
The embodiment of the invention converts the seismic data into the seismic image, extracts the straight line or curve outline formed by the seismic signals through the outline recognition of the two-dimensional seismic image, fills the missing data on the seismic channels based on the image outline and realizes the initial reconstruction of the three-dimensional seismic data. And then, learning accurate missing data from the preliminarily reconstructed three-dimensional seismic data by using the trained neural network model, and making up the deviation between the preliminarily reconstructed seismic data and the complete seismic data. The method overcomes the defects of low precision and poor stability existing in the process of directly learning missing data from original seismic data, adds a primary reconstruction process based on contour recognition in the neural network model, reduces the calculation pressure and performance requirements of the neural network model, and improves the precision and reliability of three-dimensional seismic data reconstruction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for reconstructing three-dimensional seismic data according to an embodiment of the invention.
FIG. 2 is a schematic diagram of a two-dimensional seismic image provided by an embodiment of the invention.
Fig. 3 is a schematic mechanism diagram of a U-Net neural network according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as being fixed or detachable or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
FIG. 1 is a flow chart of a method for reconstructing three-dimensional seismic data according to an embodiment of the present invention. The method is suitable for the situation that the neural network model is used for reconstructing the missing data in the three-dimensional seismic data. The method is executed by an electronic device, and specifically includes the following steps, as shown in fig. 1.
And S110, constructing a three-dimensional seismic image with data missing by using the complete three-dimensional seismic data.
And the complete three-dimensional seismic data has a plurality of groups and is used for constructing a sample set of a neural network model. Specifically, for each complete set of three-dimensional seismic data, it is converted into a three-dimensional seismic image. The three-dimensional seismic image is composed of a plurality of two-dimensional seismic images along the inLine direction, values of a plurality of pixel points in each two-dimensional seismic image are modified to be smaller than a set threshold value, and the modified two-dimensional seismic images form the three-dimensional seismic image with data loss.
The set threshold value can be set according to actual needs, and the pixel points smaller than the set threshold value are the points of signal loss. Generally, these pixel points are seismic points on several seismic traces, which are the objects of subsequent seismic data reconstruction.
And S120, performing preliminary reconstruction on the three-dimensional seismic image based on the image contour.
The method comprises the steps of introducing a traditional image processing technology into seismic data reconstruction, firstly, carrying out primary reconstruction on a three-dimensional seismic image based on a salient outline, wherein the seismic image after the primary reconstruction already has more complete seismic data compared with an original three-dimensional seismic image with data loss, and only has certain difference in accuracy and reliability. Specifically, the process of the preliminary reconstruction includes the following steps:
step one, image contour recognition is carried out on each two-dimensional seismic image. FIG. 2 is a schematic representation of a two-dimensional seismic image, and it can be seen that the pixel values in the seismic image form a plurality of lines or curves, and thus the result of the contour identification is these lines or curves.
And step two, fitting the contour curve by adopting a polynomial simulation method. More specifically, in the case of a simpler geological structure, the image contour shows a straight line with a certain slope, and then the straight line can be fitted by using a first-order polynomial. Under the condition of complex geological structure, the prominent profile is represented as a curve with more complex form, and the curve form of the curve can be fitted by a polynomial curve no matter which curve is used.
And thirdly, performing interpolation operation according to the polynomial obtained by fitting, filling pixel points with data missing, obtaining a preliminarily reconstructed two-dimensional seismic image, and forming the preliminarily reconstructed three-dimensional seismic image by using the plurality of preliminarily reconstructed two-dimensional seismic images. Specifically, if data are missing at the intersection position of the contour curve and each seismic channel, difference calculation can be performed through a polynomial expression of the contour curve and the sequence number of the seismic channel, and the missing pixel points are filled up by adopting the result of interpolation calculation.
Optionally, the contour region is obtained in sequence, contour screening can be carried out, another pixel threshold value is set, and the contour larger than the threshold value is screened out, namely, only the contour larger than a certain pixel area is reserved, so that the hybrid contour extracted from the image can be removed, noise recovery is prevented, and the signal-to-noise ratio of the seismic data is effectively improved.
S130, training a neural network model by using the preliminarily reconstructed three-dimensional seismic image, so that the output of the neural network model is close to the complete three-dimensional seismic data.
Optionally, the neural network model is a U-Net neural network. As shown in FIG. 3, the up-sampling layer of the U-Net neural network adopts a maximum pooling layer, and the down-sampling layer adopts an deconvolution layer. FIG. 3 shows the data processing process of the two-dimensional seismic image with the channel 1 in the U-Net neural network, and finally the two-dimensional seismic image with the same size is obtained. If N two-dimensional seismic images are input into the U-Net neural network shown in FIG. 3, a three-dimensional seismic image with N channels is finally obtained.
Specifically, the whole network processes the two-dimensional seismic image with the channel 1 as follows:
in the maximum pooling layer down-sampling stage: assume that the initially input image size is: a gray scale map of 1280 × 1000 × 1 is changed to a size of 64 × 500 × 64 by performing a convolution operation with 2 times of convolution kernels of 3 × 3 × 64 (64 convolution kernels, resulting in 64 feature maps), and then changed to 32 × 250 × 128 by performing a max pooling operation of 2 × 2, where the 3 × 3 convolution is followed by the ReLU nonlinear transform. Then, the convolution operation of 3 × 3 × 256 is performed 2 times, and finally, the size is changed to 16 × 125 × 256.
In the deconvolution up-sampling process phase: the size of the image is 16 × 125 × 256, the image is first changed to 32 × 250 × 128 by performing deconvolution operation of 2 × 2, the image is spliced with the deconvolved image to obtain an image of 32 × 250 × 256, and then convolution operation of 3 × 3 × 512 is performed. By analogy, after reaching the top layer, the image becomes 128 × 1000 × 64 in size, and 3 × 3 × 64 convolution operations are performed twice more. An image of 128 × 1000 × 32 size is obtained, and the convolution operation of 1 × 1 × 2 and 1 × 1 × 1 is performed again to obtain an image of 128 × 1000 × 1.
In order to enhance the diversity of samples, an elastic transformation mode can be adopted to enhance the data of the preliminarily reconstructed three-dimensional seismic image when a sample set is constructed; and taking the enhanced sample set as a sample set for training the neural network model.
Optionally, a full-link layer is added at the last layer (after the last down-sampling and before the first up-sampling) in order to add extra information (e.g. whether a certain graph is something of a certain class). Optionally, an output (prediction) is performed for each upsampling, and the obtained results are fused to restore details in the image.
Through the neural network model, the secondary reconstruction of the seismic image is realized on the basis of the seismic image primarily reconstructed. After two times of reconstruction, the seismic image has complete data information and has higher accuracy and stability.
S140, converting three-dimensional seismic data to be reconstructed into a three-dimensional seismic image to be reconstructed, and performing primary reconstruction on the three-dimensional seismic image based on an image contour; and inputting the three-dimensional seismic image after the primary reconstruction into the trained neural network model to obtain three-dimensional seismic data after the secondary reconstruction.
The trained neural network model can be used for reconstructing all three-dimensional seismic data, but the input of the network model is a three-dimensional seismic image after primary reconstruction is carried out through an image outline. Specifically, after a group of three-dimensional seismic data to be reconstructed is taken, the three-dimensional seismic data is converted into a three-dimensional seismic image to be reconstructed, then contour recognition is carried out on each two-dimensional seismic image in the three-dimensional seismic image along the inLine direction, preliminary reconstruction is carried out on each two-dimensional seismic image based on the salient contour, and the three-dimensional seismic image after preliminary reconstruction is formed together. And inputting the three-dimensional seismic image after the primary reconstruction into the trained neural network model to obtain three-dimensional seismic data after the secondary reconstruction.
The data reconstruction process is carried out in the inLine plane, and the continuity of data in the plane can be ensured. In order to prevent the reconstructed seismic data from having data salience along the crossLine direction, optionally, after obtaining the three-dimensional seismic data after the secondary reconstruction, converting the data volume into a plurality of two-dimensional seismic images along the crossLine direction; and performing linear filtering on the two-dimensional seismic images along the crossLine direction, and forming final three-dimensional seismic data by the filtered two-dimensional seismic images.
In the embodiment, the seismic data are converted into the seismic image, the linear or curved contour formed by the seismic signals is extracted through contour recognition of the two-dimensional seismic image, missing data on a seismic channel is filled based on the image contour, and preliminary reconstruction of the three-dimensional seismic data is realized. And then, learning accurate missing data from the preliminarily reconstructed three-dimensional seismic data by using the trained neural network model, and making up the deviation between the preliminarily reconstructed seismic data and the complete seismic data. The method overcomes the defects of low precision and poor stability existing in the process of directly learning missing data from original seismic data, adds a primary reconstruction process based on contour recognition in the neural network model, reduces the calculation pressure and performance requirements of the neural network model, and improves the precision and reliability of three-dimensional seismic data reconstruction.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 4, the electronic device includes a processor 50, a memory 51, an input device 52, and an output device 53; the number of processors 50 in the device may be one or more, and one processor 50 is taken as an example in fig. 4; the processor 50, the memory 51, the input device 52 and the output device 53 in the apparatus may be connected by a bus or other means, which is exemplified in fig. 4.
The memory 51 is used as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the three-dimensional seismic data reconstruction method in the embodiment of the present invention. The processor 50 executes software programs, instructions and modules stored in the memory 51 to perform various functional applications of the apparatus and data processing, i.e., to implement the three-dimensional seismic data reconstruction method described above.
The memory 51 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 51 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 51 may further include memory located remotely from the processor 50, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 52 may be used to receive input numeric or character information and generate key signal inputs relating to user settings and function controls of the apparatus. The output device 53 may include a display device such as a display screen.
Embodiments of the present invention also provide a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the three-dimensional seismic data reconstruction method of any of the embodiments.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of three-dimensional seismic data reconstruction, comprising:
constructing a three-dimensional seismic image with data loss by using complete three-dimensional seismic data;
performing preliminary reconstruction on the three-dimensional seismic image based on the image contour;
training a neural network model by using the preliminarily reconstructed three-dimensional seismic image to enable the output of the neural network model to be close to the complete three-dimensional seismic data;
converting three-dimensional seismic data to be reconstructed into a three-dimensional seismic image to be reconstructed, and performing primary reconstruction on the three-dimensional seismic image based on an image contour; and inputting the three-dimensional seismic image after the primary reconstruction into the trained neural network model to obtain three-dimensional seismic data after the secondary reconstruction.
2. The method of claim 1, wherein constructing a three-dimensional seismic image with data loss using the complete three-dimensional seismic data comprises:
converting the complete three-dimensional seismic data into a three-dimensional seismic image, wherein the three-dimensional seismic image consists of a plurality of two-dimensional seismic images along the inLine direction;
and in each two-dimensional seismic image, modifying the values of the plurality of pixel points to be smaller than a set threshold value, and forming the three-dimensional seismic image with data loss by each modified two-dimensional seismic image.
3. The method of claim 2, wherein the preliminary reconstructing of the three-dimensional seismic image based on the image profile comprises:
carrying out image contour identification on each two-dimensional seismic image;
fitting the contour curve by adopting a polynomial simulation method;
and performing interpolation operation according to the polynomial obtained by fitting, filling pixel points with data loss, obtaining a two-dimensional seismic image after preliminary reconstruction, and forming a three-dimensional seismic image after preliminary reconstruction by using a plurality of two-dimensional seismic images after preliminary reconstruction together.
4. The method of claim 3, further comprising, after said performing image contour recognition on each two-dimensional seismic image:
and screening the screened contours, screening out the contours with the pixel values larger than a set threshold value, and rejecting the rest contours.
5. The method of claim 1, wherein the neural network model is a U-Net neural network.
6. The method of claim 5, wherein the up-sampling layer of the U-Net neural network is a maximum pooling layer and the down-sampling layer is an deconvolution layer.
7. The method of claim 5, wherein training a neural network model using the preliminarily reconstructed three-dimensional seismic image comprises:
performing data enhancement on the preliminarily reconstructed three-dimensional seismic image by adopting an elastic transformation mode;
and training the neural network model by using the enhanced sample set.
8. The method of claim 1, wherein after inputting the primarily reconstructed three-dimensional seismic image into the trained neural network model to obtain the secondarily reconstructed three-dimensional seismic data, further comprising:
converting the three-dimensional seismic data subjected to secondary reconstruction into a plurality of two-dimensional seismic images along the crossLine direction;
and performing linear filtering on the two-dimensional seismic images along the crossLine direction, and forming final three-dimensional seismic data by the filtered two-dimensional seismic images.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of three-dimensional seismic data reconstruction as recited in any of claims 1-8.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a method of three-dimensional seismic data reconstruction as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211423672.4A CN115903020A (en) | 2022-11-15 | 2022-11-15 | Three-dimensional seismic data reconstruction method, apparatus, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211423672.4A CN115903020A (en) | 2022-11-15 | 2022-11-15 | Three-dimensional seismic data reconstruction method, apparatus, and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115903020A true CN115903020A (en) | 2023-04-04 |
Family
ID=86480024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211423672.4A Pending CN115903020A (en) | 2022-11-15 | 2022-11-15 | Three-dimensional seismic data reconstruction method, apparatus, and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115903020A (en) |
-
2022
- 2022-11-15 CN CN202211423672.4A patent/CN115903020A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113240580B (en) | Lightweight image super-resolution reconstruction method based on multi-dimensional knowledge distillation | |
| CN113221969A (en) | Semantic segmentation system and method based on Internet of things perception and based on dual-feature fusion | |
| CN111832570A (en) | Image semantic segmentation model training method and system | |
| CN108960345A (en) | A kind of fusion method of remote sensing images, system and associated component | |
| CN114758337B (en) | Semantic instance reconstruction method, device, equipment and medium | |
| CN111914654B (en) | Text layout analysis method, device, equipment and medium | |
| CN109816659B (en) | Image segmentation method, device and system | |
| CN112861795A (en) | Method and device for detecting salient target of remote sensing image based on multi-scale feature fusion | |
| CN112633156A (en) | Vehicle detection method, image processing apparatus, and computer-readable storage medium | |
| CN113297986A (en) | Handwritten character recognition method, device, medium and electronic equipment | |
| CN114913325B (en) | Semantic segmentation method, semantic segmentation device and computer program product | |
| CN113592009A (en) | Image semantic segmentation method and device, storage medium and electronic equipment | |
| CN113505796A (en) | Real-time high-precision panoramic segmentation method | |
| CN115903020A (en) | Three-dimensional seismic data reconstruction method, apparatus, and medium | |
| CN115272667B (en) | Farmland image segmentation model training method and device, electronic equipment and medium | |
| CN115082371B (en) | Image fusion method and device, mobile terminal equipment and readable storage medium | |
| CN113962332B (en) | Salient target identification method based on self-optimizing fusion feedback | |
| CN113450364B (en) | Tree-shaped structure center line extraction method based on three-dimensional flux model | |
| CN112052863B (en) | Image detection method and device, computer storage medium and electronic equipment | |
| CN112419216A (en) | Image interference removing method and device, electronic equipment and computer readable storage medium | |
| CN115965839A (en) | Image recognition method, storage medium, and apparatus | |
| CN115661449B (en) | Image segmentation and training method and device for image segmentation model | |
| CN113628108B (en) | Image super-resolution method and system based on discrete representation learning and terminal | |
| CN117132761A (en) | Target detection method and device, storage medium and electronic equipment | |
| CN113034381B (en) | Single image denoising method and device based on cavitated kernel prediction network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 125, Building 6, Chuangzhi Green Valley Development Center, No. 788, Hongpu Road, Shangcheng District, Hangzhou City, Zhejiang Province, 310020 Applicant after: Tracy Energy Technology Co.,Ltd. Address before: Room 125, Building 6, Chuangzhi Green Valley Development Center, No. 788, Hongpu Road, Shangcheng District, Hangzhou City, Zhejiang Province, 310020 Applicant before: Tracy Energy Technology (Hangzhou) Co.,Ltd. Address after: Room 125, Building 6, Chuangzhi Green Valley Development Center, No. 788, Hongpu Road, Shangcheng District, Hangzhou City, Zhejiang Province, 310020 Applicant after: Tracy Energy Technology (Hangzhou) Co.,Ltd. Address before: Room 125, Building 6, Chuangzhi Green Valley Development Center, No. 788, Hongpu Road, Shangcheng District, Hangzhou City, Zhejiang Province, 310020 Applicant before: Tracy energy technology (Hangzhou) Co.,Ltd. |