CN106777612B - Method and device for establishing PCB type prediction model and PCB design - Google Patents

Method and device for establishing PCB type prediction model and PCB design Download PDF

Info

Publication number
CN106777612B
CN106777612B CN201611101799.9A CN201611101799A CN106777612B CN 106777612 B CN106777612 B CN 106777612B CN 201611101799 A CN201611101799 A CN 201611101799A CN 106777612 B CN106777612 B CN 106777612B
Authority
CN
China
Prior art keywords
pcb
neural network
schematic diagram
data
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201611101799.9A
Other languages
Chinese (zh)
Other versions
CN106777612A (en
Inventor
沈文
李炳林
黄在朝
邓辉
喻强
王玮
虞跃
陈磊
刘川
陶静
姚启桂
张增华
王向群
孙晓艳
陈伟
卜宪德
田文峰
吕立东
姚继明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Global Energy Interconnection Research Institute
Original Assignee
State Grid Corp of China SGCC
Global Energy Interconnection Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Global Energy Interconnection Research Institute filed Critical State Grid Corp of China SGCC
Priority to CN201611101799.9A priority Critical patent/CN106777612B/en
Publication of CN106777612A publication Critical patent/CN106777612A/en
Application granted granted Critical
Publication of CN106777612B publication Critical patent/CN106777612B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/30—Circuit design
    • G06F30/39—Circuit design at the physical level
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Geometry (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Character Discrimination (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A method and apparatus for creating a predictive model of a PCB type and a PCB design, wherein the method for creating the predictive model of the PCB type includes: acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams; and training a neural network model according to the two-dimensional characteristic data and the preset type number of the PCB schematic diagram as training data until the error between the output data of the neural network and the preset type number of the PCB schematic diagram is smaller than a preset error, so that the problems of low efficiency, long research and development period and high cost of the conventional PCB design mode are solved.

Description

Method and device for establishing PCB type prediction model and PCB design
Technical Field
The invention relates to the field of intelligent design, in particular to a method and a device for establishing a PCB type prediction model and PCB design.
Background
The Printed Circuit Board (PCB) is a support body of electronic components and a carrier for electrical connection of the electronic components, the PCB design is based on a circuit schematic diagram, and functions required by a circuit designer are realized, and various factors such as layout of external connection of the PCB, optimized layout of internal electronic components, optimized layout of metal wires and through holes, electromagnetic protection, heat dissipation and the like are generally considered in the design process of the PCB.
The PCB design assisting tools used at present are Protel, Cadence spb, MentorEE and the like, and the PCB design assisting tools still stay in the design assisting stage of ensuring wiring constraint, signal integrity, electromagnetic compatibility simulation and the like to passively meet the requirements of developers in the aspect of intelligent design assisting, so that the current PCB design is rapidly realized on the basis of assisting the developers to optimize the PCB design and deeply learn the existing reference design, and the field of improving the design efficiency is not enough.
The current method for designing the manual layout PCB has the following defects:
in the process of manually laying out the PCB design, the work repetition degree is high, taking the PCB design of the industrial Ethernet switch as an example, the whole design comprises the design of a CPU part circuit, a DDR and other storage part circuits, a switching part circuit, an Ethernet port, a power supply and other peripheral circuits, and the repeated drawing workload often occurs on the premise that the circuit part of the newly designed industrial Ethernet switch selects the same device every time. Meanwhile, for inexperienced designers, the situations of unreasonable device layout, reverse high-speed data time sequence, imperfect impedance matching and the like can occur in the PCB design.
Disclosure of Invention
Therefore, the technical problems to be solved by the invention are that the existing PCB design mode has low efficiency, long research and development period and high cost.
In view of the above, the present invention provides a method for building a prediction model of a PCB type, comprising:
acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams;
and training a neural network model according to the two-dimensional characteristic data and the preset type number of the PCB schematic diagram as training data until the error between the output data of the neural network and the preset type number of the PCB schematic diagram is smaller than a preset error.
Preferably, the two-dimensional characteristic data of the PCB schematic is obtained from chip types related in the PCB schematic and the number of the corresponding chip types.
Preferably, the training of the neural network model includes:
and when the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagram is not less than the preset error precision, adjusting the weight value of the neuron in the neural network model.
Preferably, the output of the neural network is obtained by:
Figure BDA0001169741690000021
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and w isiN is the neuron weight, xiAnd the PCB schematic diagram characteristic data.
Preferably, the neural network model is a function chain neural network model.
The invention also provides a PCB design method, which comprises the following steps:
acquiring two-dimensional characteristic data of a PCB schematic diagram to be designed;
inputting the two-dimensional characteristic data into the model established by the method for establishing the PCB type prediction model to obtain output data;
and determining a design template of the PCB schematic diagram according to the output data.
Accordingly, the present invention provides an apparatus for creating a predictive model of a PCB type, comprising:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams;
and the training unit is used for training a neural network model according to the two-dimensional characteristic data and the preset type number of the PCB schematic diagram as training data until the error between the output data of the neural network and the preset type number of the PCB schematic diagram is smaller than a preset error.
Preferably, the two-dimensional characteristic data of the PCB schematic is obtained from chip types related in the PCB schematic and the number of the corresponding chip types.
Preferably, the training unit comprises:
and the adjusting unit is used for adjusting the weight of the neuron in the neural network model when the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagram is not less than the preset error precision.
Preferably, the output of the neural network is obtained by:
Figure BDA0001169741690000031
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and w isiN is the neuron weight, xiAnd the PCB schematic diagram characteristic data.
Preferably, the neural network model is a function chain neural network model.
Correspondingly, the invention also provides a PCB design device, which comprises:
the characteristic data acquisition unit is used for acquiring two-dimensional characteristic data of a PCB schematic diagram to be designed;
the output data acquisition unit is used for inputting the two-dimensional characteristic data into the model established by the method for establishing the PCB type prediction model to obtain output data;
and the design template determining unit is used for determining the design template of the PCB schematic diagram according to the output data.
The technical scheme of the invention has the following advantages:
the method comprises the steps of obtaining two-dimensional feature data of a plurality of PCB schematic diagrams and type numbers of the preset PCB schematic diagrams, taking the two-dimensional feature data and the type numbers of the preset PCB schematic diagrams as training data, training a neural network model until the absolute value of the difference value between the output data of the neural network and the type numbers of the preset PCB schematic diagrams is smaller than preset error precision, determining a design template of the PCB schematic diagrams according to the obtained output data, and designing the PCB by using the design template of the PCB schematic diagrams, so that the problems of low efficiency, long research and development period and high cost of the existing PCB design mode are solved.
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 building a predictive model of PCB types according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for creating a predictive model of a PCB type according to an embodiment of the present invention;
FIG. 3 is a flow chart of a PCB design method provided by another embodiment of the present invention;
fig. 4 is a flow chart illustrating a structure of a PCB designing apparatus according to another embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present 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.
The embodiment of the invention provides a method for establishing a prediction model of a PCB type, which comprises the following steps of:
and S11, acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams. The two-dimensional feature data of the PCB schematic diagram is preferably obtained by the chip types and the numbers of the corresponding chip types related in the PCB schematic diagram, for example, the chip types included in the PCB schematic diagram include x1, x2, x3 and x4, the corresponding numbers are A, B, C, D respectively, and then the array composed of x1, x2, x3, x4 and A, B, C, D is the two-dimensional feature data of the PCB schematic diagram; the type number of the preset PCB schematic, for example, specifies the category number of the circuit of the 88E6095 switch chip as 1, specifies the category number of the other amplifying circuit as 2, and so on, and the category numbers corresponding to the categories of the multiple functional circuits can be preset.
And S12, training the neural network model according to the two-dimensional characteristic data and the type number of the preset PCB schematic diagram as training data until the error between the output data of the neural network and the type number of the preset PCB schematic diagram is smaller than the preset error. The neural network model is preferably a function chain neural network model, and specifically, the following formula is shown:
|y'-y|＞k
wherein y' is output data of the neural network, y is a type number of a preset PCB schematic diagram, and k is a preset error.
Preferably, the training of the neural network model in step S12 specifically includes the following steps:
and when the absolute value of the difference value between the output data of the neural network and the type number of the preset PCB schematic diagram is not less than the preset error precision, adjusting the weight value of the neuron in the neural network model. Wherein, each neuron weight in the neural network is endowed with a random value in an interval of 0-1.
As a specific embodiment, the output of the neural network is obtained by the following formula:
Figure BDA0001169741690000061
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and wiN is the neuron weight, xiCharacteristic data of the PCB schematic diagram.
Wherein, wxt＝w1x1+...+wnxn+wn+1x1x2+...+wn+n(n-1)/2xn-1xn，wi,i＝1,2,3...n；
According to the method for establishing the PCB type prediction model provided by the embodiment of the invention, the neural network model is trained by acquiring the two-dimensional characteristic data of a plurality of PCB schematic diagrams and the preset type number of the PCB schematic diagrams and taking the two-dimensional characteristic data and the preset type number of the PCB schematic diagrams as training data until the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagrams is less than the preset error precision, and the PCB type prediction model is obtained by training the neural network model, so that the PCB type recognition efficiency and accuracy are improved.
Accordingly, an embodiment of the present invention provides an apparatus for building a prediction model of a PCB type, as shown in fig. 2, including:
the acquiring unit 21 is configured to acquire two-dimensional feature data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams;
and the training unit 22 is configured to train the neural network model according to the two-dimensional feature data and the preset type number of the PCB schematic as training data until an error between output data of the neural network and the preset type number of the PCB schematic is smaller than a preset error.
Preferably, the two-dimensional characteristic data of the PCB schematic is obtained from the chip models and the number of the corresponding chip models involved in the PCB schematic.
Preferably, the training unit 22 comprises:
and the adjusting unit is used for adjusting the weight of the neuron in the neural network model when the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagram is not less than the preset error precision.
Preferably, the output of the neural network is obtained by:
Figure BDA0001169741690000071
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and wiN is the neuron weight, xiCharacteristic data of the PCB schematic diagram.
Preferably, the neural network model is a function-chain neural network model.
According to the device for establishing the PCB type prediction model, the acquisition unit is used for acquiring the two-dimensional characteristic data of the PCB schematic diagrams and the preset type number of the PCB schematic diagrams, the two-dimensional characteristic data and the preset type number of the PCB schematic diagrams are used as training data, the neural network model is trained until the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagrams is smaller than the preset error precision, the neural network model is trained to obtain the PCB type prediction model, and the PCB type recognition efficiency and accuracy are improved.
Another embodiment of the present invention further provides a PCB design method, as shown in fig. 3, including:
s31, acquiring two-dimensional characteristic data of the PCB schematic diagram to be designed;
s32, inputting the two-dimensional characteristic data into the model established by the method for establishing the PCB type prediction model according to the embodiment to obtain output data;
and S33, determining the design template of the PCB schematic diagram according to the output data.
Specifically, for example, when the obtained output data is 2, a PCB design template corresponding to the preset category 2 is displayed from the database, and then the PCB design can be performed according to the design template.
According to the PCB design method provided by the embodiment of the invention, the design template of the PCB schematic diagram is determined through the obtained output data, and then the design template of the PCB schematic diagram is utilized to design the PCB, so that the problems of low efficiency, long research and development period and high cost of the conventional PCB design mode are solved.
Accordingly, another embodiment of the present invention further provides a PCB designing apparatus, as shown in fig. 4, including:
a feature data obtaining unit 41, configured to obtain two-dimensional feature data of a PCB schematic to be designed;
an output data obtaining unit 42, configured to input the two-dimensional feature data into the model established by the method for establishing a PCB-type prediction model according to the above embodiment, so as to obtain output data;
and a design template determining unit 43, configured to determine a design template of the PCB schematic according to the output data.
The PCB design device provided by the embodiment obtains the two-dimensional characteristic data of the PCB schematic diagram to be designed through the characteristic data obtaining unit, then obtains the output data by utilizing the prediction model of the PCB type, determines the design template of the PCB schematic diagram, and then utilizes the design template of the PCB schematic diagram to design the PCB, thereby solving the problems of low efficiency, long research and development period and high cost of the existing PCB design mode.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.

Claims (10)

1. A PCB design method, comprising:
acquiring two-dimensional characteristic data of a PCB schematic diagram to be designed;
inputting the two-dimensional characteristic data into a model established by a method for establishing a PCB type prediction model to obtain output data;
determining a design template of the PCB schematic diagram according to the output data;
the method for establishing the PCB type prediction model comprises the following steps:
acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams;
and training a neural network model according to the two-dimensional characteristic data and the preset type number of the PCB schematic diagram as training data until the error between the output data of the neural network and the preset type number of the PCB schematic diagram is smaller than a preset error.
2. The PCB design method of claim 1, wherein the two-dimensional feature data of the PCB schematic is obtained from chip models involved in the PCB schematic and the number of the corresponding chip models.
3. The PCB design method of claim 1, wherein the training of the neural network model comprises:
and when the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagram is not less than the preset error precision, adjusting the weight value of the neuron in the neural network model.
4. The PCB design method of claim 3, wherein the output of the neural network is obtained by:
Figure FDA0002671375260000021
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and w isiN is the neuron weight, xiFor the PCB schematic diagram feature data, wxt＝w1x1+…+wnxn+wn+1x1x2+…+wn+n(n-1)/2xn-1xn。
5. The PCB design method of any of claims 1-4, wherein the neural network model is a function chain neural network model.
6. A PCB design apparatus, comprising:
the characteristic data acquisition unit is used for acquiring two-dimensional characteristic data of a PCB schematic diagram to be designed;
an output data acquisition unit for inputting the two-dimensional feature data into a model established by a device for establishing a prediction model of a PCB type to obtain output data;
the design template determining unit is used for determining a design template of the PCB schematic diagram according to the output data;
the device for establishing the PCB type prediction model comprises the following steps:
the device comprises an acquisition unit, a processing unit and a display unit, wherein the acquisition unit is used for acquiring two-dimensional characteristic data of a plurality of PCB schematic diagrams and preset type numbers of the PCB schematic diagrams;
and the training unit is used for training a neural network model according to the two-dimensional characteristic data and the preset type number of the PCB schematic diagram as training data until the error between the output data of the neural network and the preset type number of the PCB schematic diagram is smaller than a preset error.
7. The PCB design device of claim 6, wherein the two-dimensional characteristic data of the PCB schematic is obtained by the chip models involved in the PCB schematic and the number of the corresponding chip models.
8. The PCB design device of claim 6, wherein the training unit comprises:
and the adjusting unit is used for adjusting the weight of the neuron in the neural network model when the absolute value of the difference value between the output data of the neural network and the preset type number of the PCB schematic diagram is not less than the preset error precision.
9. The PCB design device of claim 8, wherein the output of the neural network is obtained by:
Figure FDA0002671375260000031
wherein y 'is the output of the neural network model, theta is the bias of y', theta is between 0 and 1, and w isiN is the neuron weight, xiFor the PCB schematic diagram feature data, wxt＝w1x1+…+wnxn+wn+1x1x2+…+wn+n(n-1)/2xn-1xn。
10. The PCB design device of any of claims 6-9, wherein the neural network model is a function chain neural network model.
CN201611101799.9A 2016-12-02 2016-12-02 Method and device for establishing PCB type prediction model and PCB design Active CN106777612B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611101799.9A CN106777612B (en) 2016-12-02 2016-12-02 Method and device for establishing PCB type prediction model and PCB design

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611101799.9A CN106777612B (en) 2016-12-02 2016-12-02 Method and device for establishing PCB type prediction model and PCB design

Publications (2)

Publication Number Publication Date
CN106777612A CN106777612A (en) 2017-05-31
CN106777612B true CN106777612B (en) 2020-12-01

Family

ID=58883662

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611101799.9A Active CN106777612B (en) 2016-12-02 2016-12-02 Method and device for establishing PCB type prediction model and PCB design

Country Status (1)

Country Link
CN (1) CN106777612B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI676939B (en) * 2018-06-22 2019-11-11 富比庫股份有限公司 Electronic component packaging classification system using neural network for classification
CN109858360B (en) * 2018-12-28 2020-09-18 华中科技大学 Dynamic management method and system for electromagnetic compatibility of fleet
CN117172190B (en) * 2023-11-01 2023-12-29 启东市旭能电子科技有限公司 PCB design method and device based on establishment of PCB prediction model

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101246200B (en) * 2008-03-10 2010-08-04 湖南大学 Analog PCB intelligent test system based on neural network
CN102855346B (en) * 2012-07-24 2014-04-23 中国电力科学研究院 Electromagnetic compatibility forecasting method based on function link neural network
CN102883548B (en) * 2012-10-16 2015-03-18 南京航空航天大学 Component mounting and dispatching optimization method for chip mounter on basis of quantum neural network
CN103593718A (en) * 2013-11-26 2014-02-19 国家电网公司 Load combination forecasting method and device
CN104463209B (en) * 2014-12-08 2017-05-24 福建坤华仪自动化仪器仪表有限公司 Method for recognizing digital code on PCB based on BP neural network

Also Published As

Publication number Publication date
CN106777612A (en) 2017-05-31

Similar Documents

Publication Publication Date Title
CN106777612B (en) Method and device for establishing PCB type prediction model and PCB design
CN110610052B (en) PCB automatic wiring system and method
CN106406531B (en) Method for manufacturing VR virtual printed circuit board factory
CN110705080B (en) Precise assembling method and device for digital twin model
WO2020087874A1 (en) Reflow soldering simulation optimization method and system, computer storage medium, and device
CN110765723B (en) Routing modeling optimization method and device based on BP neural network
US6629307B2 (en) Method for ensuring correct pin assignments between system board connections using common mapping files
CN117709017A (en) Compact model extraction method of integrated circuit device
CN110135082B (en) Method for avoiding via hole by copper sheet on negative film layer in PCB design
Abdrakhmanov et al. Experience of using EasyEDA to develop training boards on the PIC16f887 microcontroller
Danković et al. An electromechanical approach to a printed circuit board design course
CN100520791C (en) Print circuit board before-typesetting processing system and method
CN115879406A (en) Integrated circuit post-simulation method and device, electronic equipment and storage medium
CN101989310A (en) Automatic system and method of wiring design of circuit board
Zhang et al. IR-drop modeling and reduction for high-performance printed circuit boards
CN114282485A (en) PCB design method for electronic circuit
CN102930080B (en) Rear panel large-small-hole drilling data processing method and rear panel manufacturing method
CN108021985A (en) A kind of model parameter training method and device
CN104102526A (en) Collaborative interface for co-simulation of PSCAD (power system computer aided design) with third-party simulation software or hardware
US6230115B1 (en) Simulator, simulation method, and medium having simulation program recorded, taking account of timing in electronic component and signal transmission through transmission line on printed-circuit board
WO2015062397A1 (en) Data description method for automatically implementing electronic system design
Zhang et al. Distributed parallel computing technique for EM modeling
CN105260490B (en) Circuit layout device and circuit arrangement method
CN1979500A (en) Part arrangement automatical checking system and method
CN117172190B (en) PCB design method and device based on establishment of PCB prediction model

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 102209 Beijing City, the future of science and Technology City Binhe Road, No. 18, No.

Applicant after: Global energy Internet Institute, Inc.

Applicant after: State Grid Corporation of China

Address before: 102211 Beijing city Changping District Xiaotangshan town big East Village Road No. 270

Applicant before: GLOBAL ENERGY INTERCONNECTION RESEARCH INSTITUTE

Applicant before: State Grid Corporation of China

CB02 Change of applicant information
CB02 Change of applicant information

Address after: 102209 18 Riverside Avenue, Changping District science and Technology City, Beijing

Applicant after: Global energy Internet Institute, Inc.

Applicant after: State Grid Corporation of China

Address before: 102209 18 Riverside Avenue, Changping District science and Technology City, Beijing

Applicant before: Global energy Internet Institute, Inc.

Applicant before: State Grid Corporation of China

GR01 Patent grant
GR01 Patent grant