WO2020114978A1 - Device and method for creating piping and instrument diagram (p&id) for power plant - Google Patents

Device and method for creating piping and instrument diagram (p&id) for power plant Download PDF

Info

Publication number
WO2020114978A1
WO2020114978A1 PCT/EP2019/083337 EP2019083337W WO2020114978A1 WO 2020114978 A1 WO2020114978 A1 WO 2020114978A1 EP 2019083337 W EP2019083337 W EP 2019083337W WO 2020114978 A1 WO2020114978 A1 WO 2020114978A1
Authority
WO
WIPO (PCT)
Prior art keywords
power plant
piping
historical
instrument diagram
requirements
Prior art date
Application number
PCT/EP2019/083337
Other languages
French (fr)
Inventor
Wei Li
Hai Tao Li
Original Assignee
Siemens Aktiengesellschaft
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 Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Publication of WO2020114978A1 publication Critical patent/WO2020114978A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/14—Pipes
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements.
  • FIG. 4 is a schematic diagram of a piping and instrument diagram (P&ID) creation system according to an exemplary embodiment .
  • P&ID piping and instrument diagram
  • the P&ID mechanism creation unit 310 may be implemented as the same device or unit with the piping and instrument diagram (P&ID) creation unit 300, or may be a separate device and unit for executing their algorithm/system respectively.
  • P&ID piping and instrument diagram
  • P&ID mechanism creation system 311 obtained by training, and then, according to the inputted piping and instrument diagram (P&ID) , obtain a P&ID mechanism that corresponds to the piping and instrument diagram (P&ID) .
  • P&ID piping and instrument diagram
  • the P&ID mechanism creation unit 310 may create a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) .
  • Such a historical P&ID mechanism may be further used for training the piping and instrument diagram (P&ID) creation system 301.
  • a P&ID mechanism may be used to plot the meaning conveyed by using a symbol used for a piping and instrument diagram (P&ID) , the meaning conveyed by using a connection between symbols, etc.
  • a historical power plant persona may be obtained manually or may be obtained automatically on the basis of the historical requirement information about a historical power plant project
  • the piping and instrument diagram (P&ID) creation unit 300 may comprise a power plant persona creation unit 330.
  • the power plant persona creation unit 330 may, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using the power plant persona creation system 331, automatically create a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) .
  • the power plant persona creation system 331 may be a trained artificial intelligence algorithm. Therefore, the power plant persona creation unit 330 may be a device or unit that has computing power for executing such an algorithm.
  • a target piping and instrument diagram may be created by using a piping and instrument diagram (P&ID) creation system.
  • the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) .
  • said deep learning algorithm may comprise a deep belief network (DBN) .
  • DBN deep belief network

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention provides a device and method for creating a piping and instrument diagram (P&ID) for a power plant. Said device comprises: a requirement input unit, configured to input initial requirements of a target power plant project; and a piping and instrument diagram (P&ID) creation unit, configured to, based on initial requirements, create a target piping and instrument diagram (P&ID) by using a piping and instrument diagram (P&ID) creation system, wherein the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID), a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID), and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID).

Description

DEVICE AND METHOD FOR CREATING PIPING AND INSTRUMENT DIAGRAM
(P&ID) FOR POWER PLANT
Technical Field
The present invention relates to a device and method for creating a piping and instrument diagram (P&ID) for a power plant .
Background Art
When developing a power plant design, an engineer creates a piping and instrument diagram (P&ID) for each system in a power plant based on specific requirements, boundary condition, local standard, policy requirements, etc. for a power plant project. For different power plant design projects, different requirements need to be met; highly similar power plant projects still differ more or less. Therefore, an engineer needs to develop a project design based on the requirements for the power plant project, according to standards, or by modifying a P&ID template.
Currently, a power plant design engineer can establish a relationship between an instrument symbol and piping by using a computer-aided design (CAD) tool, for example, AutoCAD, or can automatically establish such a relationship by using, for example, a COMOS P&ID template and configurator. However, such a method requires template analysis, as well as creation of appropriate configurators and an enormous amount of templates.
Summary of the Invention
An objective of the present invention is to solve the above- mentioned problem and/or other problems by providing a device and method for creating a piping and instrument diagram (P&ID) for a power plant .
In an exemplary embodiment, a device for creating a piping and instrument diagram (P&ID) for a power plant comprises: a requirement input unit, configured to input initial requirements of a target power plant project; and a piping and instrument diagram (P&ID) creation unit, configured to, based on initial requirements, create a target piping and instrument diagram (P&ID) by using a piping and instrument diagram (P&ID) creation system, wherein the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) . For example, said deep learning algorithm comprises a deep belief network (DBN) .
The piping and instrument diagram (P&ID) creation unit comprises: a P&ID mechanism creation unit, configured to, based on a historical piping and instrument diagram (P&ID) , and by using a P&ID mechanism creation system, create a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) , wherein the P&ID mechanism creation system is obtained by using a pattern recognition algorithm (CNN) using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard. For example, said pattern recognition algorithm comprises a convolutional neural network (CNN) .
The piping and instrument diagram (P&ID) creation unit comprises: a power plant persona creation unit, configured to, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using a power plant persona creation system, create a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) , wherein the power plant persona creation system is obtained by using a supervisory learning algorithm using, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project. For example, said supervisory learning algorithm comprises a Gaussian mixture model (GMM) .
Here, a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements.
Requirement information comprises at least one type of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements.
Said device further comprises: an identification unit, configured to identify a created target piping and instrument diagram (P&ID) by using a KKS power plant identification system, thereby obtaining an identified target piping and instrument diagram (P&ID) .
Therefore, the piping and instrument diagram (P&ID) creation unit may, based on initial requirements, create, by using the power plant persona creation unit, a target power plant persona that corresponds to a target piping and instrument diagram (P&ID) , and then, based on the target power plant persona, create a target piping and instrument diagram (P&ID) by using the P&ID mechanism creation unit.
In addition, an exemplary embodiment further provides a method for creating a piping and instrument diagram (P&ID) for a power plant, characterized in that said method comprises: inputting initial requirements of a target power plant project; and creating, based on initial requirements, a target piping and instrument diagram (P&ID) by using a piping and instrument diagram (P&ID) creation system, wherein the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) . For example, said deep learning algorithm comprises a deep belief network (DBN) .
Said method further comprises: creating, based on a historical piping and instrument diagram (P&ID) , and by using a P&ID mechanism creation system, a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) , wherein the P&ID mechanism creation system is obtained by using a pattern recognition algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard. For example, said pattern recognition algorithm comprises a convolutional neural network (CNN) .
Said method further comprises: creating, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using a power plant persona creation system, a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) , wherein the power plant persona creation system is obtained by using a supervisory learning algorithm using, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project. For example, said supervisory learning algorithm comprises a Gaussian mixture model (GMM) .
Here, a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements. Requirement information comprises at least one type of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements.
Said method further comprises: identifying a created target piping and instrument diagram (P&ID) by using a KKS power plant identification system, thereby obtaining an identified target piping and instrument diagram (P&ID) .
Therefore, the step of creating a target piping and instrument diagram (P&ID) comprises: creating, based on initial requirements and by using a power plant persona creation system, a target power plant persona that corresponds to a target piping and instrument diagram (P&ID) , and then creating, based on the target power plant persona and by using a piping and instrument diagram (P&ID) creation system, a target piping and instrument diagram (P&ID) .
In addition, an exemplary embodiment further provides an electronic device, said electronic device comprising: at least one processor; and a memory coupled to said at least one processor, said memory storing an instruction that, when executed by said at least one processor, causes said electronic device to execute the method as described above.
In addition, an exemplary embodiment further provides a nonvolatile machine-readable medium, said nonvolatile machine- readable medium storing a computer-executable instruction that, when executed, causes at least one processor to execute the method as described above.
In addition, an exemplary embodiment further provides a computer program, comprising a computer-executable instruction that, when executed, causes at least one processor to execute the method as described above.
As mentioned above, a device according to the exemplary embodiment may, by using a trained artificial intelligence algorithm or system, automatically obtain a piping and instrument diagram (P&ID) based on requirement information about a target power plant . An engineer may make further adjustments based on an obtained piping and instrument diagram (P&ID), thereby obtaining a final result; alternatively, an engineer may directly use an obtained piping and instrument diagram (P&ID) as a result of the power plant project. Thus, the amount of time required for and workload of piping and instrument diagram (P&ID) design may be reduced.
Brief Description of the Drawings
The following drawings are intended to illustratively describe and explain, instead of limiting the scope of, the present invention, wherein
Figure 1 is a schematic diagram of a device for creating a piping and instrument diagram (P&ID) for a power plant according to an exemplary embodiment;
Figure 2 is a schematic diagram of a P&ID mechanism creation system according to an exemplary embodiment;
Figure 3 is a schematic diagram of a power plant persona creation system according to an exemplary embodiment; and
Figure 4 is a schematic diagram of a piping and instrument diagram (P&ID) creation system according to an exemplary embodiment .
Description of reference numerals:
100: Requirement input unit 300: Piping and instrument diagram (P&ID) creation unit 500: Identification unit
Specific Embodiments
In order to provide a better understanding of the technical features, objectives, and beneficial effects of the present invention, specific embodiments of the present invention will be described below with reference to the drawings.
Figure 1 is a schematic diagram for a device for creating a piping and instrument diagram (P&ID) for a power plant according to an exemplary embodiment. As shown in Figure 1, a device according to an exemplary embodiment comprises a requirement input unit 100 and a piping and instrument diagram (P&ID) creation unit 300.
The requirement input unit 100 may input or obtain initial requirements of a target power plant project. For example, when developing a P&ID design for a target power plant, it is possible to manually input requirement information about the target power plant project by using the requirement input unit 100. Thus, the requirement input unit 100 may comprise, for example, a graphical user interface, for conveniently inputting requirement information. Further, the requirement input unit 100 may, based on, for example, a project proposal or any other project preparation document of the target power plant project, automatically obtain initial requirements. However, the exemplary embodiment is not limited thereto; in another exemplary embodiment, any data needed for training an algorithm (system) used for the piping and instrument diagram (P&ID) creation unit 300 may also be inputted or obtained by using the requirement input unit 100.
When the target requirements of the target power plant project is to be inputted or obtained by using the requirement input unit 100, the piping and instrument diagram (P&ID) creation unit 300 may create a target piping and instrument diagram (P&ID) based on initial requirements and by using a piping and instrument diagram (P&ID) creation system 301 (see Figure 4) . Here, the piping and instrument diagram (P&ID) creation system 301 may be a trained artificial intelligence algorithm. Therefore, the piping and instrument diagram (P&ID) creation unit 300 may be a device or unit that has computing power for executing such an algorithm. The piping and instrument diagram (P&ID) creation system 301 and a training method thereof will be described below in detail.
In an exemplary embodiment, the piping and instrument diagram (P&ID) creation system 301 may be obtained by training with relevant information about a future or historical power plant project. For example, the system may be obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) of a historical power plant project design, a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) . Here, the deep learning algorithm may be a deep belief network (DBN) or any other appropriate deep learning algorithm.
In this exemplary embodiment, the historical piping and instrument diagram (P&ID) of a historical power plant project design in the data used for training may be known; for example, it may be the piping and instrument diagram (P&ID) of a power plant project previously completed. A historical P&ID mechanism may be one that corresponds to a historical piping and instrument diagram (P&ID) .
A historical P&ID mechanism may be obtained manually or automatically based on a historical piping and instrument diagram (P&ID) . For example, the piping and instrument diagram (P&ID) creation unit 300 may comprise the P&ID mechanism creation unit 310. The P&ID mechanism creation unit 310 may, based on a piping and instrument diagram (P&ID) and by using a P&ID mechanism creation system 311, create a P&ID mechanism that corresponds to the piping and instrument diagram (P&ID) . Here, the P&ID mechanism creation system 311 may be a trained artificial intelligence algorithm. Thereffore, the P&ID mechanism creation unit 310 may be a device or unit that has computing power for executing such an algorithm. For example, the P&ID mechanism creation unit 310 may be implemented as the same device or unit with the piping and instrument diagram (P&ID) creation unit 300, or may be a separate device and unit for executing their algorithm/system respectively. The P&ID mechanism creation system and a training method thereof will be described below with reference to Figure 2.
Figure 2 is a schematic diagram for a P&ID mechanism creation system according to an exemplary embodiment . As shown in Figure 2, the P&ID mechanism creation system 311 may be obtained by inputting, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard into a selected pattern recognition algorithm. In an exemplary embodiment, a convolutional neural network (CNN) may be used as a pattern recognition algorithm for training, thereby obtaining the P&ID mechanism creation system 311.
Therefore, the P&ID mechanism creation unit 310 may run the
P&ID mechanism creation system 311 obtained by training, and then, according to the inputted piping and instrument diagram (P&ID) , obtain a P&ID mechanism that corresponds to the piping and instrument diagram (P&ID) . For example, if a historical piping and instrument diagram (P&ID) is inputted, the P&ID mechanism creation unit 310 may create a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) . Such a historical P&ID mechanism may be further used for training the piping and instrument diagram (P&ID) creation system 301. Here, a P&ID mechanism may be used to plot the meaning conveyed by using a symbol used for a piping and instrument diagram (P&ID) , the meaning conveyed by using a connection between symbols, etc.
A historical power plant persona used for training may be power plant persona information that is included in a historical piping and instrument diagram (P&ID) corresponding to a historical power plant project or that is used for plotting a historical piping and instrument diagram (P&ID) , for example, one or more types of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements. For example, information about power plant system requirements may comprise requirement information about a water supply system, a condensate system, a main vapor system , etc.; information about power plant main component requirements may comprise requirement information about a gas turbine, a steam turbine, a generator, etc.; and information about power plant scheme selection requirements may comprise layout-related requirement information about single-axle/one- to-one, multi-axle, two-to-one, etc. Historical power plant persona information may be power plant persona information obtained by an engineer based on a historical power plant project. Here, requirement information about a power plant project may comprise one or more types of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements. For example, information about power plant performance requirements may, for example, be a combined circulatory efficiency of 50% or higher under an ISO work condition, a thermal load of 300 MW or higher at each unit, a thermoelectric rate of 60% or higher, etc.; information about environmental requirements may, for example, be nitrogen oxide emission (calculated by N02) < 20 mg/m3, sulfur dioxide emission < 35 mg/m3, etc.; and information about power plant persona requirements may, for example, be the need for adding a housing to an exhaust-heat boiler, etc. A historical power plant persona may be obtained manually or may be obtained automatically on the basis of the historical requirement information about a historical power plant project For example, the piping and instrument diagram (P&ID) creation unit 300 may comprise a power plant persona creation unit 330. The power plant persona creation unit 330 may, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using the power plant persona creation system 331, automatically create a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) . Here, the power plant persona creation system 331 may be a trained artificial intelligence algorithm. Therefore, the power plant persona creation unit 330 may be a device or unit that has computing power for executing such an algorithm. For example, the power plant persona creation unit 330 may be implemented as the same device or unit with the piping and instrument diagram (P&ID) creation unit 300, or may be a separate device and unit for executing their algorithm/system respectively. The P&ID mechanism creation system and a training method thereof will be described below with reference to Figure 3.
Figure 3 is a schematic diagram for a power plant persona creation system according to an exemplary embodiment. As shown in Figure 3, the power plant persona creation system 331 may be obtained by inputting, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project into a selected supervisory learning algorithm. In an exemplary embodiment, a Gaussian mixture model (GMM) may be used as a pattern recognition algorithm for training, thereby obtaining the power plant persona creation system 331.
Therefore, the power plant persona creation unit 330 may run the power plant persona creation system 331 obtained by training and, based on the inputted requirement information about a historical or target power plant project, obtain a historical or current power plant persona that corresponds to the requirement information about the historical or target power plant project.
Figure 4 is a schematic diagram for a piping and instrument diagram (P&ID) creation system according to an exemplary embodiment. As shown in Figure 4, the piping and instrument diagram (P&ID) creation system may be obtained by training with a deep learning algorithm DBN using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) . Specifically, the P&ID mechanism creation unit 310 may create a historical P&ID mechanism based on a historical piping and instrument diagram (P&ID) and by using a P&ID mechanism creation system, and input the created historical P&ID mechanism as training data into a deep learning algorithm DBN. Further, the power plant persona creation unit 330 may, based on historical requirement information about a historical power plant project that corresponds to the historical piping and instrument diagram (P&ID) , obtain the historical power plant persona information that corresponds to the historical power plant project, and provide the created historical power plant persona information as training data to the deep learning algorithm DBN. Therefore, training may be carried out by using such input data and the deep learning algorithm DBN, thereby finally obtaining the piping and instrument diagram (P&ID) creation system 301. The piping and instrument diagram (P&ID) creation system 301 obtained by training may, with the target requirements of the target power plant project as input, obtain the piping and instrument diagram (P&ID) of the expected target power plant.
However, an exemplary embodiment is not limited thereto. For example, in another exemplary embodiment, said device may further comprise an identification unit 500, as shown in Figure 1. The identification unit 500 may identify a created target piping and instrument diagram (P&ID) , thereby obtaining an identified target piping and instrument diagram (P&ID) . For example, the identification unit 500 may carry out identification by using a Kraftwerk-Kennzeichen system (KKS) , thereby obtaining a KKS-identified piping and instrument diagram (P&ID) .
As mentioned above, a device according to the exemplary embodiment may, by using a trained artificial intelligence algorithm or system, automatically obtain a piping and instrument diagram (P&ID) based on requirement information about a target power plant . An engineer may make further adjustments based on an obtained piping and instrument diagram (P&ID), thereby obtaining a final result; alternatively, an engineer may directly use an obtained piping and instrument diagram (P&ID) as a result of the power plant project. Thus, the amount of time required for and workload of piping an instrument diagram (P&ID) design may be reduced.
In addition, according to an exemplary embodiment, a method for creating a piping and instrument diagram (P&ID) for a power plant is further provided. Said method may be executed by using the device as described above with reference to Figures 1 to 4. Therefore, repetitive descriptions of the same or similar features will be omitted.
First, initial requirements of a target power plant project may be inputted. Then, based on initial requirements, a target piping and instrument diagram (P&ID) may be created by using a piping and instrument diagram (P&ID) creation system. Here, the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) . For example, said deep learning algorithm may comprise a deep belief network (DBN) .
In order obtain a P&ID mechanism, said method may be used to, based on a historical piping and instrument diagram (P&ID) , and by using a P&ID mechanism creation system, create a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) , Here, the P&ID mechanism creation system is obtained by using a pattern recognition algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard. For example, said pattern recognition algorithm may comprise a convolutional neural network (CNN) .
In order to obtain a power plant persona, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using a power plant persona creation system, a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) may be created. Here, the power plant persona creation system is obtained by using a supervisory learning algorithm using, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project. For example, said supervisory learning algorithm comprises a Gaussian mixture model (GMM) .
Here, a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements. Requirement information may comprise at least one type of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements.
When a target piping and instrument diagram (P&ID) is created, a target power plant persona that corresponds to the target piping and instrument diagram (P&ID) may be created on the basis of initial requirements and by using a power plant persona creation system; then, a target piping and instrument diagram (P&ID) may be created on the basis of the target power plant persona and by using a P&ID creation system. After creation of a piping and instrument diagram (P&ID) , the created target piping and instrument diagram (P&ID) may further be identified, for example, by using a KKS power plant identification system, to obtain an identified piping and instrument diagram (P&ID) .
A device and method for creating a piping and instrument diagram (P&ID) for a power plant according to the present application have been described above with reference to Figures 1 to 4. The above-described device for determining existence of any dependence violations in source code may be implemented by hardware, by software, or by using a combination of hardware and software.
In the present application, a device for creating a piping and instrument diagram (P&ID) for a power plant may be implemented by an electronic device. According to an embodiment, the electronic device may comprise at least one processor, and the processor executes at least one computer-readable instruction (namely, the above-mentioned element implemented by software) stored or coded in a computer-readable storage medium (namely, a memory) .
In an embodiment, the memory stores a computer-executable instruction that, when executed, causes at least one processor to execute the above-described method for creating a piping and instrument diagram (P&ID) for a power plant.
It should be understood that a computer-executable instruction stored in the memory, when executed, causes at least one processor to perform the various operations and functions of each embodiment of the present invention described above with reference to Figures 1 to 4.
According to an embodiment, a program product, for example, a nonvolatile machine-readable medium, is provided. The nonvolatile machine-readable medium may comprise an instruction (namely, the above-described element implemented by software) ; the instruction, when executed, causes the machine to perform the various operations and functions of each embodiment of the present application described above with reference to Figures 1 to 4.
According to an embodiment, a computer program is provided, comprising a computer-executable instruction; said computer- executable instruction, when executed, causes at least one processor to perform the various operations and functions of each embodiment of the present application described above with reference to Figures 1 to 4.
It should be understood that, although the specification describes the embodiments separately, an embodiment does not contain only one independent technical solution, and that such a method of description is only for the sake of clarity; those of ordinary skill in the art should treat the specification as a whole, and the technical solutions provided in the embodiments can be appropriately combined into other embodiments that those of ordinary skill in the art understand
The above-described specific embodiments are only illustrative of the present invention, instead of limiting the scope of the present invention. Any equivalent variations, modifications, or combinations made by any of those of ordinary skill in the art without departing from the spirit or principle of the prevent invention shall fall within the scope of the present invention .

Claims

Claims
1. A device for creating a piping and instrument diagram (P&ID) for a power plant, characterized in that said device comprises: a requirement input unit (100) , configured to input initial requirements of a target power plant project; and
a piping and instrument diagram (P&ID) creation unit (300) , configured to, based on initial requirements, create a target piping and instrument diagram (P&ID) by using a piping and instrument diagram (P&ID) creation system,
wherein the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) .
2. The device as claimed in claim 1, characterized in that said deep learning algorithm comprises a deep belief network.
3. The device as claimed in claim 1, characterized in that said piping and instrument diagram (P&ID) creation unit (300) comprises :
a P&ID mechanism creation unit (310) , configured to, based on a historical piping and instrument diagram (P&ID) , and by using a P&ID mechanism creation system, create a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) ,
wherein the P&ID mechanism creation system is obtained by using a pattern recognition algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard.
4. The device as claimed in claim 3, characterized in that said pattern recognition algorithm comprises a convolutional neural network.
5. The device as claimed in claim 3, characterized in that said piping and instrument diagram (P&ID) creation unit (300) comprises :
a power plant persona creation unit (330) , configured to, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using a power plant persona creation system, create a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) ,
wherein the power plant persona creation system is obtained by using a supervisory learning algorithm using, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project .
6. The device as claimed in claim 5, characterized in that said supervisory learning algorithm comprises a Gaussian mixture model.
7. The device as claimed in claim 5, characterized in that a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements.
8. The device as claimed in claim 5, characterized in that requirement information comprises at least one type of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements.
9. The device as claimed in claim 1, characterized in that said device further comprises:
an identification unit (500) , configured to identify a created target piping and instrument diagram (P&ID) by using a KKS power plant identification system, thereby obtaining an identified target piping and instrument diagram (P&ID) .
10. The device as claimed in claim 5, characterized in that said piping and instrument diagram (P&ID) creation unit (300) is configured to, based on initial requirements, create, by using the power plant persona creation unit (330) , a target power plant persona that corresponds to a target piping and instrument diagram (P&ID) , and then, based on the target power plant persona, create a target piping and instrument diagram (P&ID) by using the P&ID mechanism creation unit (310) .
11. A method for creating a piping and instrument diagram (P&ID) for a power plant, characterized in that said method comprises :
inputting initial requirements of a target power plant project; and
creating, based on initial requirements, a target piping and instrument diagram (P&ID) by using a piping and instrument diagram (P&ID) creation system,
wherein the piping and instrument diagram (P&ID) creation system is obtained by training with a deep learning algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a historical P&ID mechanism that corresponds to a historical piping and instrument diagram (P&ID) , and a historical power plant persona that corresponds to a historical piping and instrument diagram (P&ID) .
12. The method as claimed in claim 11, characterized in that said deep learning algorithm comprises a deep belief network.
13. The method as claimed in claim 11, characterized in that said method further comprises: creating, based on a historical piping and instrument diagram (P&ID) , and by using a P&ID mechanism creation system, a historical P&ID mechanism that corresponds to the historical piping and instrument diagram (P&ID) ,
wherein the P&ID mechanism creation system is obtained by using a pattern recognition algorithm using, as training data, at least one of a historical piping and instrument diagram (P&ID) , a piping and instrument diagram (P&ID) template meeting a preset standard, and a piping and instrument diagram (P&ID) legend meeting a preset standard.
14. The method as claimed in claim 13, characterized in that said pattern recognition algorithm comprises a convolutional neural network.
15. The method as claimed in claim 13, characterized in that said method further comprises:
creating, based on historical requirement information about the historical power plant project that corresponds to a historical piping and instrument diagram (P&ID) , and by using a power plant persona creation system, a historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) ,
wherein the power plant persona creation system is obtained by using a supervisory learning algorithm using, as training data, at least one type of historical requirement information about a historical power plant project and the historical power plant persona that corresponds to the historical piping and instrument diagram (P&ID) of the historical power plant project .
16. The method as claimed in claim 15, characterized in that said supervisory learning algorithm comprises a Gaussian mixed model .
17. The method as claimed in claim 15, characterized in that a power plant persona comprises at least one type of information about power plant system requirements, information about power plant process requirements, information about power plant main component requirements, information about power plant instrument requirements, information about power plant equipment requirements, information about power plant scheme selection requirements, and information about power plant legend requirements; and
requirement information comprises at least one type of information about power grid requirements, information about power plant performance requirements, information about policy and regulatory requirements, information about standard requirements, information about environmental requirements, and information about power plant persona requirements.
18. The method as claimed in claim 11, characterized in that said method further comprises:
identifying a created target piping and instrument diagram (P&ID) by using a KKS power plant identification system, thereby obtaining an identified target piping and instrument diagram (P&ID) .
19. The method as claimed in claim 15, characterized in that the step of creating a target piping and instrument diagram (P&ID) comprises:
creating, based on initial requirements and by using a power plant persona creation system, a target power plant persona that corresponds to a target piping and instrument diagram (P&ID) , and then creating, based on the target power plant persona and by using a piping and instrument diagram (P&ID) creation system, a target piping and instrument diagram (P&ID)
20. An electronic device, characterized by comprising:
at least one processor; and
a memory coupled to said at least one processor, said memory storing an instruction that, when executed by said at least one processor, causes said electronic device to execute the method as claimed in any one of claims 11 to 19.
21. A nonvolatile machine-readable medium, characterized in that said nonvolatile machine-readable medium stores a computer-executable instruction that, when executed, causes at least one processor to execute the method as claimed in any one of claims 11 to 19.
22. A computer program, comprising a computer-executable instruction that, when executed, causes at least one processor to execute the method as claimed in any one of claims 11 to 19
PCT/EP2019/083337 2018-12-06 2019-12-02 Device and method for creating piping and instrument diagram (p&id) for power plant WO2020114978A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811489861.5 2018-12-06
CN201811489861.5A CN111291462B (en) 2018-12-06 2018-12-06 Apparatus and method for generating piping and instrumentation maps P & ID for power plants

Publications (1)

Publication Number Publication Date
WO2020114978A1 true WO2020114978A1 (en) 2020-06-11

Family

ID=68762754

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2019/083337 WO2020114978A1 (en) 2018-12-06 2019-12-02 Device and method for creating piping and instrument diagram (p&id) for power plant

Country Status (2)

Country Link
CN (1) CN111291462B (en)
WO (1) WO2020114978A1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926269A (en) * 2021-03-15 2021-06-08 上海交通大学 Method and system for grouping and cleaning data of edge nodes of power plant
CN113343642A (en) * 2021-08-09 2021-09-03 浙江浙能技术研究院有限公司 Automatic group-level KKS code mapping method based on supervised sequence generation network
CN113343643A (en) * 2021-08-09 2021-09-03 浙江浙能技术研究院有限公司 Supervised-based multi-model coding mapping recommendation method
CN114626117A (en) * 2020-12-14 2022-06-14 水利部水利水电规划设计总院 Coding method of hydraulic engineering information model for long-distance water transmission engineering

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160004794A1 (en) * 2014-07-02 2016-01-07 General Electric Company System and method using generative model to supplement incomplete industrial plant information

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030074244A1 (en) * 2001-04-11 2003-04-17 Braxton Charles R. Distributed energy technology assurance
US20030009401A1 (en) * 2001-04-27 2003-01-09 Enerwise Global Technologies, Inc. Computerized utility cost estimation method and system
JP4253146B2 (en) * 2001-10-31 2009-04-08 株式会社東芝 Power plant management system and management method
EP2260365A4 (en) * 2008-02-25 2012-08-08 Invensys Sys Inc System and method for generating control system database and graphics from schema-based intermediate descriptions
US20100095232A1 (en) * 2008-10-15 2010-04-15 Daniel Measurement And Control, Inc. Calculating and plotting statistical data
WO2012161804A1 (en) * 2011-02-24 2012-11-29 Clean Urban Energy, Inc. Integration of commercial building operations with electric system operations and markets
US20140032169A1 (en) * 2012-07-24 2014-01-30 General Electric Company Systems and methods for improving control system reliability
US10387793B2 (en) * 2014-11-25 2019-08-20 International Business Machines Corporation Automatic generation of training cases and answer key from historical corpus
EP3029535A3 (en) * 2014-12-03 2016-07-13 Rockwell Automation Technologies, Inc. P&ID and control system synchronization
CN106909931B (en) * 2015-12-23 2021-03-16 阿里巴巴集团控股有限公司 Feature generation method and device for machine learning model and electronic equipment
CN107766457A (en) * 2017-09-27 2018-03-06 华能国际电力股份有限公司上海石洞口第二电厂 A kind of thermal power plant's operation management system and its task executing method
CN108595757A (en) * 2018-03-21 2018-09-28 新智数字科技有限公司 Energy device modeling, energy source station dispatching method, device and equipment

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160004794A1 (en) * 2014-07-02 2016-01-07 General Electric Company System and method using generative model to supplement incomplete industrial plant information

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ELYAN EYAD ET AL: "Symbols Classification in Engineering Drawings", 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), IEEE, 8 July 2018 (2018-07-08), pages 1 - 8, XP033418899, DOI: 10.1109/IJCNN.2018.8489087 *
MICHAEL NIELSEN: "Neural Networks and Deep Learning", 31 December 2015 (2015-12-31), XP055648841, Retrieved from the Internet <URL:http://static.latexstudio.net/article/2018/0912/neuralnetworksanddeeplearning.pdf> [retrieved on 20191203], DOI: 10.1093/annonc/mdy166 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114626117A (en) * 2020-12-14 2022-06-14 水利部水利水电规划设计总院 Coding method of hydraulic engineering information model for long-distance water transmission engineering
CN114626117B (en) * 2020-12-14 2023-11-24 水利部水利水电规划设计总院 Coding method of hydraulic engineering information model for long-distance water delivery engineering
CN112926269A (en) * 2021-03-15 2021-06-08 上海交通大学 Method and system for grouping and cleaning data of edge nodes of power plant
CN113343642A (en) * 2021-08-09 2021-09-03 浙江浙能技术研究院有限公司 Automatic group-level KKS code mapping method based on supervised sequence generation network
CN113343643A (en) * 2021-08-09 2021-09-03 浙江浙能技术研究院有限公司 Supervised-based multi-model coding mapping recommendation method
CN113343643B (en) * 2021-08-09 2021-11-02 浙江浙能技术研究院有限公司 Supervised-based multi-model coding mapping recommendation method

Also Published As

Publication number Publication date
CN111291462A (en) 2020-06-16
CN111291462B (en) 2023-08-08

Similar Documents

Publication Publication Date Title
WO2020114978A1 (en) Device and method for creating piping and instrument diagram (p&amp;id) for power plant
Vázquez-Canteli et al. CityLearn v1. 0: An OpenAI gym environment for demand response with deep reinforcement learning
Blanco et al. An efficient robust solution to the two-stage stochastic unit commitment problem
CN106779143A (en) One kind production scheduling method for optimizing scheduling
CN114066333A (en) Data processing method and device
Yan et al. Engineering drawings recognition using a case-based approach
CN113641830B (en) Model pre-training method, device, electronic equipment and storage medium
Taheri et al. Adaptive robust optimal transmission switching considering the uncertainty of net nodal electricity demands
CN106775884A (en) Method and equipment for upgrading control program of wind generating set
CN104182613B (en) The ship electric power plant fault diagnosis model construction method of the petri net based on rough set
EP3629251A1 (en) Neural network processing method, computer system, and storage medium
CN116502671A (en) Artificial intelligence model control system and control method
CN103955368A (en) Software fuzzy adaptive support system and development method
CN104091225A (en) Object-oriented electric power system scheduling operation ticket system
Correa-Florez et al. Reduced scenario methodology for treating uncertainty in transmission expansion with large wind power penetration
WO2021192728A1 (en) System and method for detecting and correcting laser-cutting distortion
Woerrlein et al. On the Usage of Deep Learning for Modelling Energy Consumption in Simulation Models.
Massel et al. Contingency management and semantic modeling in energy sector
Ebrie et al. Reinforcement Learning-Based Multi-Objective Optimization for Generation Scheduling in Power Systems
US11454957B2 (en) Systems and methods for operation and design of industrial system
US10191938B2 (en) Editing of volume of data
Correa-Florez et al. Multi-objective transmission expansion planning considering uncertainty in wind power and demand
US20240037016A1 (en) Computer readable storage medium, debugging support device, debugging support method, and machine learning device
CN117291137B (en) Method, apparatus and medium for generating layout elements
Faizrakhmanov et al. Formation of an energy-efficient cutting tool path in waterjet and laser cutting CNC machines

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19813322

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19813322

Country of ref document: EP

Kind code of ref document: A1