Big data acquisition platform, method and device for full-range analog machine of nuclear power plant

Abstract

The invention relates to a big data acquisition platform, method and device for a full-range simulator of a nuclear power plant. A data acquisition control program of the platform is used for reading a simulation scene definition script, analyzing the simulation scene definition script to obtain a simulation instruction, and sending the simulation instruction to an algorithm scheduling module. The simulation scene definition script is a scene definition script for generating a specific running scene in the simulator. And the algorithm scheduling module is used for scheduling a corresponding model calculation program to perform simulation calculation according to the simulation instruction so as to generate operation data, and calling a data aggregation program to aggregate the operation data of the specific scene to the shared memory. And the data acquisition program is used for reading the data from the shared memory according to the acquisition instruction sent by the algorithm scheduling module, and storing the data as a time sequence data file or sending the data outwards through a network. Synchronous and automatic collection of simulation data of a complex system can be achieved, and the data requirements of nuclear power artificial intelligence application for a large amount of, diversified and high-quality unit operation data are met.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power data acquisition, and in particular to a big data acquisition platform, method and device for a full-range simulator of a nuclear power plant. Background Art

[0002] In nuclear power plants, the data of complex systems (such as nuclear power units) have the characteristics of more steady-state operation data, less transient operation data, and serious homogeneity of data samples, which makes them unsuitable for big data application research. For example, it is impossible to support complex systems to carry out transient operation analysis and fault diagnosis applications based on big data. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a nuclear power plant full-range simulator big data collection platform, method and device.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a nuclear power plant full-range simulator big data acquisition platform, including a simulation system, the simulation system includes an algorithm scheduling module, a plurality of model calculation programs, the platform also includes a data acquisition control program, a data aggregation program, a data acquisition program and a shared memory;

[0005] The data acquisition control program is used to read the simulation scenario definition script and parse it to obtain simulation instructions, and send the simulation instructions to the algorithm scheduling module; the simulation scenario definition script is a scenario definition script that generates a specific running scenario in the simulator;

[0006] The algorithm scheduling module is used to schedule the corresponding model calculation program to perform simulation calculation according to the simulation instruction to generate corresponding operation data, and call the data aggregation program to select required data from the operation data generated in the operation scenario and aggregate them into the exclusive area of ​​the shared memory;

[0007] The data acquisition program is used to read data from the shared memory according to the acquisition instruction issued by the algorithm scheduling module, and save it as a time series data file in a text format.

[0008] Furthermore, in the nuclear power plant full-range simulator big data acquisition platform described in the present invention, the platform also includes a data verification program, which is used to obtain the content of the timing data file, and to perform offline verification on the data format and output the verification result; the data format includes the number of fields in each row of data.

[0009] Furthermore, in the nuclear power plant full-range simulator big data acquisition platform described in the present invention, the data acquisition program is also used to transmit the data in real time to a third-party application system through a standard network communication interface.

[0010] Furthermore, in the nuclear power plant full-range simulator big data acquisition platform of the present invention, the script corresponding to each operation scenario includes a plurality of simulation instructions, and the data acquisition control program is used to:

[0011] According to reading simulation instructions from the simulation scenario definition script, and following the definition sequence in the script, the simulation instructions are sent one by one to the algorithm scheduling module. Before issuing a simulation instruction, it is necessary to confirm that the algorithm scheduling module has completed executing the previous simulation instruction.

[0012] Furthermore, in the nuclear power plant full-range simulator big data acquisition platform described in the present invention, the model calculation program includes a core calculation program, a thermal calculation program, a control logic calculation program, and an electrical calculation program, and the operating data includes core model data, thermal model data, instrumentation and control model data, electrical model data, and IO interface data.

[0013] In addition, the present invention also provides a nuclear power plant full-range simulator big data collection method, which is applied to a nuclear power plant full-range simulator big data collection device, the device is communicatively connected with the simulation system, and includes the following steps:

[0014] S1, reading a simulation scenario definition script, parsing it to obtain a simulation instruction, and sending the simulation instruction to a simulation system, wherein the simulation scenario definition script is a scenario definition script for generating a specific running scenario in a simulator;

[0015] S2, selecting required data from the operation data generated by the simulation system executing the simulation instruction and aggregating them into the shared memory exclusive area;

[0016] S3. Collect data from the shared memory exclusive area, and save the collected data as a time series data file.

[0017] Furthermore, in the nuclear power plant full range simulator big data collection method of the present invention, the method further comprises:

[0018] S4. Perform offline verification on the number of fields of the characteristic variables and the target variables in the time series data file, and output the verification result.

[0019] Furthermore, in the nuclear power plant full range simulator big data collection method of the present invention, the method further comprises:

[0020] S5. Transmit data to third-party application systems in real time through standard network communication interfaces.

[0021] Furthermore, in the nuclear power plant full-range simulator big data collection method of the present invention, the script corresponding to each operation scenario includes a plurality of simulation instructions, and in step S1, includes:

[0022] According to reading and parsing simulation instructions from the simulation scenario definition script, and sending the simulation instructions to the algorithm scheduling module one by one according to the definition order in the script, before issuing a simulation instruction, it is necessary to confirm that the algorithm scheduling module has executed the previous simulation instruction.

[0023] In addition, the present invention also provides a big data collection device for a full-range simulator of a nuclear power plant, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the steps of the above-mentioned big data collection method for a full-range simulator of a nuclear power plant by calling the computer program stored in the memory.

[0024] The implementation of the nuclear power plant full-range simulator big data collection platform, method and device of the present invention has the following beneficial effects: the present invention utilizes the simulation system of the complex system, defines various operation scenarios through scripts and controls the operation of the simulation system to create various simulation operation scenarios required for diversified data collection, thereby realizing the large-scale, diverse and high-quality collection of complex system operation simulation data, solving the serious problem of complex system operation data homogeneity, so that the collected data can support the complex system to carry out operation transient analysis and fault diagnosis applications based on big data, improve the utilization rate of production data, and enhance the intelligence level of complex systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0026] Figure 1 It is a structural schematic diagram of a nuclear power plant full-range simulator big data acquisition platform provided by an embodiment of the present invention;

[0027] Figure 2 It is a schematic diagram of the structure and signal flow of a nuclear power plant full-range simulator big data acquisition platform provided by an embodiment of the present invention;

[0028] Figure 3 is a schematic diagram of a time series data file provided by an embodiment of the present invention;

[0029] Figure 4 It is a schematic flow chart of a method for collecting big data of a full-range simulator of a nuclear power plant provided by an embodiment of the present invention;

[0030] Figure 5 It is a schematic flow chart of a method for collecting big data of a full-range simulator of a nuclear power plant provided by an embodiment of the present invention;

[0031] Figure 6It is a flow chart of a big data collection method for a full-range simulator of a nuclear power plant provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific embodiments of the present invention are now described in detail with reference to the accompanying drawings. In the following description, it should be understood that the directions or positional relationships indicated by "front", "back", "up", "down", "left", "right", "longitudinal", "horizontal", "vertical", "horizontal", "top", "bottom", "inside", "outside", "head", "tail", etc. are based on the directions or positional relationships shown in the accompanying drawings, are constructed and operated in a specific direction, and are only for the convenience of describing the present technical solution, rather than indicating that the device or element referred to must have a specific direction, and therefore cannot be understood as a limitation to the present invention.

[0033] It should also be noted that, unless otherwise clearly specified and limited, the terms such as "installed", "connected", "connected", "fixed", "set" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. When an element is referred to as being "on" or "under" another element, the element can be "directly" or "indirectly" located on the other element, or there may be one or more intermediate elements. The terms "first", "second", "third", etc. are only for the convenience of describing the present technical solution, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first", "second", "third", etc. can explicitly or implicitly include one or more of the features. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.

[0034] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0035] refer to Figure 1 and Figure 2In one of the embodiments provided by the present invention, the nuclear power plant full-range simulator big data acquisition platform of this embodiment includes a simulation system, a data acquisition control program 10, a data aggregation program 40, a data acquisition program 60 and a shared memory 50, and the simulation system includes an algorithm scheduling module 20 and multiple model calculation programs 30.

[0036] The data acquisition control program 10 is used to read the simulation scenario definition script and parse the simulation scenario definition script to obtain the simulation instruction. Moreover, the simulation instruction (i.e., the simulator instruction) is sent to the algorithm scheduling module 20. The simulation scenario definition script is a script corresponding to the determined operation scenario. It can be understood that the user first determines the operation scenario requirements, and then creates a scenario corresponding script according to the operation scenario requirements, and controls the operation of the simulation system through the simulation scenario definition script. Specifically, the simulation instructions in the parsed script are sent to the simulation system to control the simulation system to operate in the corresponding operation scenario to generate the required simulation operation data for transient analysis and fault diagnosis.

[0037] It should be noted that nuclear power complex systems refer to various technical and engineering systems in nuclear power plants, which interact and are highly integrated to achieve the purpose of generating electricity safely and efficiently. These systems include but are not limited to nuclear power units, nuclear reactors, cooling systems, control systems, safety systems, waste treatment systems, etc. The complexity and tight coupling of these systems require that the operation of nuclear power plants must strictly comply with safety standards and regulatory requirements. Complex systems are the simulation targets and objects of simulation systems, and they correspond one to one.

[0038] The algorithm scheduling module 20 is used to call the corresponding model calculation program 30 according to the simulation instruction to generate the corresponding operation data, and call the data aggregation program 40 to select the required data from the operation data generated in the operation scenario and aggregate it to the exclusive area of ​​the shared memory 50. That is, the algorithm scheduling module 20 controls each model calculation program 30 to generate the corresponding operation data according to the simulation instruction sent from the data acquisition control program 10, and then the data aggregation program 40 aggregates part of all the operation data generated by each model calculation program 30 into the exclusive area of ​​the shared memory 50.

[0039] The data collection program 60 is used to collect data from the shared memory 50 according to the collection instructions issued by the algorithm scheduling module 20, and save the collected data as a time series data file. Specifically, the data aggregation program 40 selects the data to be collected through file configuration, aggregates and maps them to the shared memory 50, and the data collection program 60 saves the data in the shared memory 50 to the time series data file.

[0040] That is to say, in this embodiment, the data acquisition control program reads and parses the simulation scenario definition script to obtain simulation instructions, and sends the simulation instructions to the algorithm scheduling module. The simulation scenario definition script is a scenario definition script that generates a specific operation scenario in the simulator. The algorithm scheduling module receives the simulation instructions and schedules the corresponding model calculation program to perform simulation calculations according to the simulation instructions to generate corresponding operation data. The algorithm scheduling module calls the data aggregation program to obtain data corresponding to a specific operation scenario from the operation data and stores it in the shared memory. The data acquisition program receives and reads the data corresponding to the acquisition instruction from the shared memory according to the acquisition instruction issued by the algorithm scheduling module, and converts the data into a text format to generate a corresponding time series data file.

[0041] Exemplarily, the following is the definition form of the SAMPLING.ass file of the collected data definition and mapping example, which realizes the data selection and aggregation to the exclusive shared memory module. The file is stored in the Transfer / Assign / directory of the simulation system (simulator system) project of the simulation system.

[0042] / / Fault type

[0043] / / Source signal maps to target signal

[0044] tr_RCV012MN.imfFailure bMalf_Sample[0];

[0045] mfRCP17A.Status bMalf_Sample[1];

[0046] mfRCP18A.Status bMalf_Sample[2];

[0047] …

[0048] .

[0049] / / Fault severity

[0050] tr_RCV012MN.imvSeverity wMalf_Severity[0];

[0051] mfRCP17A.CurrValue wMalf_Severity[1];

[0052] mfRCP18A.CurrValue wMalf_Severity[2];

[0053] mfRCP19A.CurrValue wMalf_Severity[3];

[0054] …

[0055] .

[0056] It can be understood that the data collected in an operation scenario is saved in a time series data file, that is, the same time series data file includes the collected data at different times of a scenario, such as collecting once in 1s, collecting 20 times in 20 seconds, and storing the data collected 20 times in the order of collection time as a time series data file. As an option, the data acquisition program 60 can also receive and send real-time collected data to a third-party application system. The third-party application system can be a unit transient analysis system, etc. For example, the unit transient analysis system obtains a large amount of operating data in the required operation scenario such as a transient operation scenario from the acquisition platform, and carries out operation transient analysis and / or fault diagnosis applications based on big data.

[0057] It should be noted that if Figure 2 As shown, the data acquisition program 60, the data aggregation program 40 and the shared memory 50 can be integrated and embedded in the simulation system. The data acquisition program 60 is integrated with the simulation system in a plug-in manner. That is to say, in this embodiment, the data acquisition platform can be mainly composed of pure software and cooperate with the simulator system (i.e., the simulation system) to realize the corresponding functions. The present invention does not make specific limitations on this.

[0058] In some embodiments, the data acquisition platform of this embodiment also includes a data verification program, which is used to perform offline verification of the number of fields of feature variables and target variables and annotation information of the sample data collected each time in the time series data file, and output the verification result. That is to say, the data verification program obtains the time series data file, and performs offline verification on the time series data file to output the verification result. The offline verification content includes the verification of the number of fields of the feature variables in the time series data file, the verification of the number of fields of the target variables, and the verification of the annotation information. Specifically, the annotation information mainly includes scene information. It can be understood that this embodiment performs offline verification on the data under the running scene, such as the number of collections is 20 times, and 10 data (9 feature variables + 1 target variable) are collected each time. By checking whether the annotation information of each sample data is the same (the annotation information of each sample in the same scene is the same), whether the number of fields is the same, if the verification fails, it means that there is a problem with the collected data, and a reminder display can be performed.

[0059] In some embodiments, the script corresponding to each running scenario or the simulation scenario definition script includes multiple simulation instructions. The data acquisition control program 10 reads and analyzes the simulation instructions obtained from the simulation scenario definition script and their sequence, and sends the simulation instructions to the algorithm scheduling module 20 one by one. After receiving the feedback on the execution of the instructions from the algorithm scheduling module 20, it determines whether to issue the next simulation instruction according to the feedback result. It can be understood that the data acquisition control program 10 reads the simulation instructions in the simulation scenario definition script in sequence according to the preset order and sends them to the algorithm scheduling module, and ensures that the algorithm scheduling module has executed the previous simulation instruction when sending the simulation instruction to the algorithm scheduling module. In other words, the algorithm scheduling module 20 will feed back the current state to the data acquisition control program 10 in real time, and the acquisition control program determines whether to send the next instruction in the script to it according to the feedback result.

[0060] Illustratively, the following are examples of script definitions for two scenarios: Preferably, the acquisition sampling scenario is defined in a CommandFile.txt file, and CommandFile.txt is installed in the same directory as the data acquisition control program 10 .

[0061] reset-so "Books\YANGJIANG_U1\IC\001" / / Reset the simulation system to initial working condition, such as: 001 is full power.

[0062] Run / / Run the simulator.

[0063] ICM tr_RCV012MN t:3r:300f:1.2 / / Insert sensor RCV012MN fixed-point drift fault in the simulator.

[0064] Freeze / / Freeze the simulator.

[0065] reset-so"Books\YANGJIANG_U1\IC\001";

[0066] Run;

[0067] IMF mfRCP17A r:30f:5;

[0068] Freeze.

[0069] The first running scenario script and the second running scenario script each have four simulation instructions. Taking the first running scenario script as an example, the four simulation instructions are: reset the initial working condition of the simulation system, run the simulator, insert the sensor RCV012MN fixed-point drift fault in the simulator, and freeze the simulator. These four instructions are sent to the simulation system in a synchronous manner and are executed one by one by the simulation system.

[0070] refer to Figure 2 The model calculation program 30 of the simulation system includes but is not limited to a core calculation program, a thermal calculation program, a control logic calculation program, an electrical calculation program, etc. The operation data includes but is not limited to core model data, thermal model data, instrumentation and control model data, electrical model data, IO interface data, etc. In other words, the model calculation program includes a core calculation program for core calculation, a thermal calculation program for thermal calculation, a control logic calculation program for control logic calculation, an electrical calculation program for electrical calculation, etc. The operation data includes core model data generated by the operation of the core calculation program, thermal model data generated by the operation of the thermal calculation program, instrumentation and control model data generated by the operation of the control logic calculation program, electrical model data generated by the operation of the electrical calculation program, IO interface data, etc.

[0071] The present invention utilizes a high-fidelity simulation system of a complex system, defines various operation scenarios through scripts and controls the operation of the simulation system to create a variety of data collection scenarios, and automatically completes the collection, storage, transmission and verification in the simulation operation scenario, thereby realizing the large-scale, diverse and high-quality collection of complex system operation simulation data, solving the serious problem of homogeneity of complex system operation data, improving the utilization rate of production data, and enhancing the intelligence level of complex systems. By realizing the synchronous and automatic collection of complex system simulation data, the requirements of artificial intelligence applications in the field of nuclear power for large-scale, diverse and high-quality data of unit operation data are met, which makes up for the deficiency that the homogeneity of nuclear power unit operation data seriously limits the application of big data, and realizes the enhancement of unit operation data.

[0072] In addition to solving the above-mentioned problems in the prior art, the value of the present invention is also reflected in: defining the transient operation scenarios of complex systems through scripts, facilitating the setting of transient operation scenarios of complex systems and ensuring the diversity of collected data. By automatically reading and parsing the scene definition script to control the operation of the simulation system, the automation of scene control is realized and the efficiency of data collection is improved. Through the synchronization of acquisition control and data acquisition and data verification, the consistency of the simulation system state and the collected simulation data is guaranteed, and the data acquisition quality is improved. By defining transient scenarios through scripts and defining the data content to be collected through configuration files, the ease of use and flexibility of the system are guaranteed. Through the application of big data analysis of collected data, the transient analysis process of complex system operators can be simulated to realize the intelligent operation of complex systems, which will help to gradually realize the unmanned and unattended operation of complex systems.

[0073] In a specific implementation, it mainly includes: 1) Data acquisition control system and data acquisition scenario script definition: it uses the simulation command of the complex system to define the command sequence for setting the simulation state of the complex system; the data acquisition control system parses the scenario definition script and sends simulation instructions to the simulation system (simulator) to control its operation and simulate the operation data of the required scenario. It also includes a communication interface with the simulation system.

[0074] 2) Data aggregation and collection: It defines the data to be collected in the form of a configuration file, realizes data aggregation and mapping to the collection area, and realizes synchronous data collection of multi-task simulation systems. At the same time, through the data collection of scene description information (target variables), automatic data labeling at the sample data level is realized. Through the software configuration of the simulation system, the sample data collection cycle and the scene data collection sequence duration are defined.

[0075] 3) Storage and transmission of collected data: The collected sequence data is saved in an asynchronous manner (saved in csv format) to avoid affecting the real-time performance of the simulation system. The collected data of each scene is saved as a separate sequence data file, which can realize sequence-level data annotation; it provides data communication with standard protocols (HTTP protocol) and data formats (json format), and provides an integrated interface with third-party application systems. It should be noted that the specific HTTP protocol and post communication method, as well as the json data format, can refer to the existing technology and will not be repeated here.

[0076] 4) Verification of collected data: Implement offline verification of collected data (time series data files) to verify the number of fields and annotation information of feature variables and target variables in the collected samples.

[0077] The data collected for each scene is saved as an independent data file. The data file name contains the timestamp information when the data collection ends to distinguish the data collection files in different scenes. Figure 3 As shown in the figure, it is a schematic diagram of the time series data file of the collected data.

[0078] refer to Figure 4 In one of the embodiments provided by the present invention, the nuclear power plant full range simulator big data collection method of this embodiment is applied to the nuclear power plant full range simulator big data collection device, the device is communicatively connected with the simulation system, and the method comprises the following steps:

[0079] S1, read the simulation scenario definition script, parse the simulation scenario definition script to obtain simulation instructions, and send the simulation instructions to the simulation system. The simulation scenario definition script is a script corresponding to the determined operation scenario. It can be understood that the user first determines the operation scenario, and then defines the corresponding script according to the operation scenario, and controls the operation of the simulation system through the simulation scenario definition script. Specifically, the simulation instructions in the script are parsed and sent to the simulation system to control the simulation system to run in the corresponding operation scenario and generate the required simulation operation data for transient analysis and fault diagnosis.

[0080] Alternatively, the script corresponding to each running scenario includes multiple simulation instructions, including in step S1:

[0081] According to the order of simulation instructions obtained by reading and parsing from the simulation scenario definition script, the simulation instructions are sent one by one to the algorithm scheduling module 20. When receiving the instruction execution feedback from the algorithm scheduling module 20, it is determined whether to issue the next simulation instruction according to the feedback result. In other words, the algorithm scheduling module 20 will feed back the current status to the data acquisition control program 10 in real time, and the acquisition control program determines whether to send the next instruction in the script to it according to the feedback result.

[0082] S2, all the operation data generated by the simulation system executing the simulation instruction are aggregated into the shared memory 50. Specifically, the algorithm scheduling module 20 in the simulation system controls each model calculation program 30 to generate corresponding operation data according to the simulation instruction sent from the data acquisition control program 10, and then the data aggregation program 40 aggregates all the operation data generated by each model calculation program 30 into the shared memory 50.

[0083] S3. Collect data from the shared memory 50 and save the collected data as a time series data file. Specifically, the data collection program 60 maps the data to be collected (source signal) from the shared memory 50 to the target signal through a predefined mapping method, thereby forming a time series data file.

[0084] This embodiment utilizes the simulation system of the complex system to define various operation scenarios through scripts and control the operation of the simulation system to create various simulation operation scenarios required for diversified data collection, thereby realizing the large-scale, diverse and high-quality collection of complex system operation simulation data, solving the serious problem of homogeneity of complex system operation data, and enabling the collected data to support the complex system to carry out operation transient analysis and fault diagnosis applications based on big data, thereby improving the utilization rate of production data and enhancing the intelligence level of complex systems.

[0085] In some embodiments, reference Figure 5 , the operation data includes annotation information, and the method further includes:

[0086] S4. Perform offline verification on the number of fields and annotation information of the characteristic variables and target variables in the time series data file, and output the verification results. Specifically, the annotation information mainly includes the actual operation scenario corresponding to the operation data. It can be understood that this embodiment performs offline verification between data under the same operation scenario, such as collecting 20 times, collecting 10 data each time (9 characteristic variables + 1 target variable), and verifies whether the annotation information of each data is the same (such as whether the operation scenario is the same) and whether the number of fields is the same. If the verification fails, it means that there is a problem with the data, and an alarm reminder display can be performed.

[0087] In some embodiments, reference Figure 6 , the method further comprises:

[0088] S5. Receive a data acquisition instruction from a third-party application system, and transmit the time series data file to the third-party application system according to the data acquisition instruction. The third-party application system may be a unit transient analysis system, etc. For example, the unit transient analysis system obtains a large amount of operating data under the required operating scenario, such as a transient operating scenario, from the acquisition platform, so as to carry out operating transient analysis and / or fault diagnosis applications based on big data.

[0089] In one of the embodiments provided by the present invention, the nuclear power plant full range simulator big data acquisition device of this embodiment includes a memory and a processor, the memory stores a computer program, and the processor executes the steps of the nuclear power plant full range simulator big data acquisition method of the above embodiment by calling the computer program stored in the memory. It can be understood that the nuclear power plant full range simulator big data acquisition device of this embodiment can also be used as a gateway to connect the simulation system with a third-party application system (such as a nuclear power unit operation transient analysis and fault diagnosis system) that collects data, so as to realize real-time transmission of collected data.

[0090] This embodiment utilizes the simulation system of the complex system to define various operation scenarios through scripts and control the operation of the simulation system to create various simulation operation scenarios required for diversified data collection, thereby realizing the large-scale, diverse and high-quality collection of complex system operation simulation data, solving the serious problem of homogeneity of complex system operation data, and enabling the collected data to support the complex system to carry out operation transient analysis and fault diagnosis applications based on big data, thereby improving the utilization rate of production data and enhancing the intelligence level of complex systems.

[0091] The computer-readable storage medium of the present invention can be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0092] The processor of the present invention is used to provide computing and control capabilities to support the operation of the entire XXX device. It should be understood that in the embodiment of the present application, the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0093] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0094] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0095] It can be understood that the above embodiments only express the preferred implementation modes of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the patent scope of the present invention. It should be pointed out that, for ordinary technicians in this field, without departing from the concept of the present invention, the above technical features can be freely combined, and several deformations and improvements can be made, which all belong to the protection scope of the present invention. Therefore, all equivalent changes and modifications made to the scope of the claims of the present invention should belong to the scope covered by the claims of the present invention.

Claims

1. A nuclear power plant full range simulator big data acquisition platform, characterized in that: The simulation system includes an algorithm scheduling module and a plurality of model calculation programs, and the platform also includes a data acquisition control program, a data aggregation program, a data acquisition program and a shared memory; The data acquisition control program is used to read the simulation scenario definition script and parse it to obtain simulation instructions, and send the simulation instructions to the algorithm scheduling module; The simulation scenario definition script is a scenario definition script that generates a specific running scenario in the simulator; The algorithm scheduling module is used to schedule the corresponding model calculation program to perform simulation calculation according to the simulation instruction to generate corresponding operation data, and call the data aggregation program to select required data from the operation data generated in the operation scenario and aggregate them into the exclusive area of ​​the shared memory; The data acquisition program is used to read data from the shared memory according to the acquisition instruction issued by the algorithm scheduling module, and save it as a time series data file in a text format.

2. The nuclear power plant full range simulator big data acquisition platform according to claim 1, characterized in that: The platform also includes a data verification program, which is used to obtain the content of the time series data file, perform offline verification on the data format, and output the verification result; the data format includes the number of fields in each row of data.

3. The nuclear power plant full range simulator big data acquisition platform according to claim 1, characterized in that: The data acquisition program is also used to transmit the data to a third-party application system in real time through a standard network communication interface.

4. The nuclear power plant full range simulator big data acquisition platform according to claim 1, characterized in that: The script corresponding to each running scenario includes multiple simulation instructions, and the data acquisition control program is used to: According to reading simulation instructions from the simulation scenario definition script, and following the definition sequence in the script, the simulation instructions are sent one by one to the algorithm scheduling module. Before issuing a simulation instruction, it is necessary to confirm that the algorithm scheduling module has completed executing the previous simulation instruction.

5. The nuclear power plant full range simulator big data acquisition platform according to claim 1, characterized in that: The model calculation program includes a core calculation program, a thermal calculation program, a control logic calculation program, and an electrical calculation program. The operation data includes core model data, thermal model data, instrumentation and control model data, electrical model data, and IO interface data.

6. A method for collecting big data of a full-range simulator of a nuclear power plant, applied to a big data collection device of a full-range simulator of a nuclear power plant, characterized in that: The device is communicatively connected with the simulation system, and comprises the following steps: S1, reading a simulation scenario definition script, parsing it to obtain a simulation instruction, and sending the simulation instruction to a simulation system, wherein the simulation scenario definition script is a scenario definition script for generating a specific running scenario in a simulator; S2, selecting required data from the operation data generated by the simulation system executing the simulation instruction and aggregating them into a shared memory exclusive area; S3. Collect data from the shared memory exclusive area, and save the collected data as a time series data file.

7. The method for collecting big data of a full-range simulator of a nuclear power plant according to claim 6, characterized in that: The method further includes: S4. Perform offline verification on the number of fields of the characteristic variables and the target variables in the time series data file, and output the verification result.

8. The method for collecting big data of a full-range simulator of a nuclear power plant according to claim 6, characterized in that: The method further includes: S5. Transmit data to third-party application systems in real time through standard network communication interfaces.

9. The method for collecting big data of a full-range simulator of a nuclear power plant according to claim 6, characterized in that: The script corresponding to each running scenario includes multiple simulation instructions, including: According to reading and parsing simulation instructions from the simulation scenario definition script, and sending the simulation instructions to the algorithm scheduling module one by one according to the definition order in the script, before issuing a simulation instruction, it is necessary to confirm that the algorithm scheduling module has executed the previous simulation instruction.

10. A big data acquisition device for a full range simulator of a nuclear power plant, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the steps of the nuclear power plant full-range simulator big data collection method as described in any one of claims 6 to 9 by calling the computer program stored in the memory.

Images