A hyper-converged architecture intelligent control platform and method for power plants

Abstract

This application proposes a hyper-converged architecture intelligent control platform and method for power plants, the platform comprising: an intelligent operation control module, a firewall, a high-throughput load-balancing C / D network, and a hyper-converged all-in-one machine; the intelligent operation control module accesses the high-throughput load-balancing C / D network through the firewall; the hyper-converged all-in-one machine accesses the high-throughput load-balancing C / D network; the intelligent operation control module comprises: multiple intelligent operation control units, wherein the intelligent operation control units comprise an intelligent sensing and control A / B network and multiple intelligent controllers, and the intelligent controllers access the intelligent sensing and control A / B network. The technical solution proposed in this application can realize the access of large-scale intelligent sensors and the systematization of intelligent operation control of power plants, thereby improving the safety, reliability, flexibility, stability and efficiency of power plant operation control.

Description

Technical Field

[0001] The present application relates to the field of power plant control, and in particular to a hyper-converged architecture intelligent control platform and method for power plants. Background Art

[0002] In the context of energy transformation, thermal power energy needs to shoulder more tasks of high-efficiency energy saving, low-carbon environmental protection, and deep frequency and peak regulation. The application of digital intelligent technology to improve the flexibility and operating efficiency of thermal power units has strong practical significance. Intelligent operation and control technology is an important foundation for the intelligence of thermal power units. Many scientific research institutions and high-tech companies at home and abroad are conducting extensive research on how to apply this technology to improve the intelligence level of boiler combustion systems, steam-water systems, air and smoke systems, etc., in order to achieve energy saving and consumption reduction, ultra-low emissions and high flexibility operation of thermal power units. At this stage, the application of intelligent operation and control technology in the production process of power plants mainly focuses on two modes: partial algorithm optimization based on traditional DCS and plug-in optimization of the integration of industrial computers and PLCs. The following problems exist:

[0003] (1) The current intelligent operation control technology mainly focuses on "point-like breakthroughs" such as wide-load cruise, intelligent monitoring, and intelligent environmental protection islands. It is difficult to form a "blooming on the surface" situation, and there are a lot of "treating the symptoms rather than the root cause" phenomena.

[0004] (2) It has not systematically implemented all-round support for big data and artificial intelligence, cannot achieve large-scale intelligent sensor access and intelligent modeling, cannot fully meet the intelligent requirements of thermal power units in complex and harsh operating environments, and has not fully considered the systematicity and integrity of various intelligent operation and control applications, posing serious safety, stability and reliability risks.

[0005] (3) The software and hardware are severely coupled and rely on a specific brand of DCS. This often leads to customized development for each company. The development and implementation cycle of related functions is long, which increases the costs of R&D companies and users and seriously restricts the development of smart power plants.

[0006] In order to solve the relationship problems between various systems and data, site and control, management and production, upstream and downstream in the construction of smart power plants, break through the fragmentation problem in the application of smart operation and control technology, and establish a systematic solution with highly coordinated various elements, a systematic, stable, efficient, safe and reliable control platform is urgently needed. Summary of the Invention

[0007] The present application provides a hyper-converged architecture intelligent control platform and method for power plants, so as to at least solve the technical problems that the intelligent operation control technology of power plants is not systematized, has low stability, and has severe coupling between software and hardware and fragmented applications.

[0008] The first embodiment of the present application proposes a hyper-converged architecture intelligent control platform for a power plant, comprising: an intelligent operation control module, a firewall, a high-throughput load balancing C / D network, and a hyper-converged all-in-one machine;

[0009] The intelligent operation control module accesses the high-throughput load-balancing C / D network through the firewall;

[0010] The hyper-converged integrated machine is connected to the high-throughput load-balancing C / D network;

[0011] The smart operation control module includes: multiple smart operation control units, wherein the smart operation control units include an intelligent sensing and control A / B network and multiple intelligent controllers, and the intelligent controllers are connected to the intelligent sensing and control A / B network;

[0012] The hyper-converged all-in-one machine is used to learn based on the runtime data and non-time-series data of each device in the group collected by each sensor, generate a configuration container image of each application instance and derived runtime data of each device in the group, and send the configuration container image of each application instance and the derived runtime data of each device in the group to the intelligent operation control unit corresponding to each application instance;

[0013] The intelligent operation control unit is used to generate control instructions for each device in the unit based on the configuration container of each application instance and the operation timing data and derived operation timing data of each device in the unit, and control each device in the unit based on each control instruction.

[0014] Preferably, a container runtime environment is provided in the intelligent controller;

[0015] The container runtime environment deploys and runs: a data acquisition unit container, an embedded time series database container, and a configuration container;

[0016] The configuration container is obtained by running the container runtime environment after receiving the configuration container image of each application instance from the configuration container image repository;

[0017] The data acquisition unit container and the embedded time series database container are built into the container runtime environment;

[0018] The data acquisition unit container is used to collect the running time sequence data and the derived running time sequence data of the corresponding equipment in the unit, and send the running time sequence data and the derived running time sequence data of the corresponding equipment in the unit to the embedded time series database container;

[0019] The embedded time series database container is used to cache the running time series data and derived running time series data of the corresponding equipment in the unit;

[0020] The configuration container is used to generate control instructions based on the configuration container image, runtime data and derived runtime data, and apply the control instructions to the corresponding device, wherein the configuration container is selected based on the runtime data and derived runtime data.

[0021] Furthermore, the data acquisition unit container, the embedded time series database container, and the configuration container all adopt a three-copy high-availability deployment mode;

[0022] Among them, each replica uses a heartbeat mechanism to monitor each other. When the main container fails, any replica container will be randomly switched to the main container in milliseconds.

[0023] Furthermore, the hyper-converged all-in-one machine has a database, an intelligent engine module, a configuration container image repository, and a monitoring module deployed and running inside;

[0024] The database includes a time series database and a big data platform;

[0025] The embedded time series database container is further configured to send the cached runtime data and derived runtime data of the corresponding device in the unit to the time series database;

[0026] The time series database is used to store and manage the operation time series data and derived operation time series data of each device corresponding to each unit in the power plant;

[0027] The big data platform is used to store and manage data of non-time series data types;

[0028] The intelligent engine module is configured to generate updated derived runtime data and configuration container images of each application instance based on the runtime data, derived runtime data, and data of non-time series data types of each device corresponding to each unit of the power plant, and send the updated derived runtime data to the data acquisition unit container and the configuration container image of each application instance to the configuration container image repository;

[0029] The configuration container image repository is used to store and manage the configuration container images of each application instance, select the configuration container images that need to be distributed based on the operating conditions of the units in the power plant, and distribute the configuration container images to the container runtime environment of each intelligent controller;

[0030] The configuration container image repository is further used to receive the configuration container running status feedback from the container runtime environment to monitor the status of the configuration container;

[0031] The monitoring module is used to obtain real-time data and historical data of the container runtime environment, time series database, big data platform, intelligent engine module and configuration container image warehouse, and generate a graphical interface based on the real-time data and historical data of the container runtime environment, time series database, big data platform, intelligent engine module and configuration container image warehouse, and then monitor the operating status of the device and software based on the graphical interface.

[0032] Furthermore, the monitoring module is also used for power plant operators to directly intervene and input control instructions, and send the control instructions directly to the intelligent operation control module.

[0033] Furthermore, the intelligent engine module includes: a big data computing engine unit, an artificial intelligence modeling engine unit and a control algorithm configuration engine unit;

[0034] The big data computing engine unit is configured to generate derived runtime data and a big data model based on the data of the non-time series data type and the runtime data, and to generate an operator that can be directly applied by the control algorithm configuration engine unit based on the big data model;

[0035] The artificial intelligence modeling engine unit is used to perform modeling training based on the data stored in the time series database and the big data platform, and to obtain an artificial intelligence model by using deep learning and machine learning algorithms, and to generate operators based on the artificial intelligence model that can be directly applied by the control algorithm configuration engine unit;

[0036] The control algorithm configuration engine unit is used to perform algorithm configuration on the operator, containerize the configuration, generate a configuration container image, and synchronize the generated configuration container image to the configuration container image repository.

[0037] Preferably, the intelligent control platform further comprises: an intelligent engineer module, an intelligent operator module and a monitoring screen;

[0038] The intelligent engineer module is used for system configuration, maintenance and monitoring;

[0039] The intelligent operator module is used to monitor the on-site operation of the power plant and provide manual intervention in emergency situations;

[0040] The monitoring screen is used to display the operating status of the equipment in the power plant and the software in the control platform;

[0041] The intelligent engineer module, the intelligent operator module and the monitoring screen are all connected to the high-throughput load-balancing C / D network.

[0042] Preferably, the intelligent control platform further comprises: a security protection module;

[0043] The security protection module is used for terminal protection, security auditing and active defense;

[0044] Wherein, the security protection module is connected to the high-throughput load-balancing C / D network.

[0045] Preferably, the control platform further comprises: a one-way network gateway;

[0046] One end of the unidirectional gateway is connected to the high-throughput load-balancing C / D network, and the other end is connected to the three-area management network.

[0047] A second embodiment of the present application provides a hyper-converged architecture intelligent control method for a power plant, the method comprising:

[0048] Generate the configuration container image of each application instance and the derived runtime data of each device in the group based on the runtime data of each device in the group collected by each sensor;

[0049] Select each configuration container that needs to execute the control of each device according to the runtime data of each device and the derived runtime data of each device;

[0050] Based on the configuration container images corresponding to the selected configuration containers, the runtime data of each device and the derived runtime data of each device, control instructions for each device in the group are generated, and each device in the group is controlled based on the control instructions.

[0051] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0052] The present application proposes a hyper-converged architecture intelligent control platform and method for a power plant, wherein the intelligent control platform includes: an intelligent operation control module, a firewall, a high-throughput load balancing C / D network and a hyper-converged all-in-one machine; the intelligent operation control module is connected to the high-throughput load balancing C / D network through the firewall; the hyper-converged all-in-one machine is connected to the high-throughput load balancing C / D network; the intelligent operation control module includes: multiple intelligent operation control units, wherein the intelligent operation control unit includes an intelligent sensing and control A / B network, multiple intelligent controllers, and the intelligent controller is connected to the intelligent sensing and control A / B network; the The hyper-converged all-in-one machine is used to learn based on the runtime data and non-time-series data of each device in the unit collected by each sensor, generate the configuration container image of each application instance and the derived runtime data of each device in the unit, and send the configuration container image of each application instance and the derived runtime data of each device in the unit to the intelligent operation control unit corresponding to each application instance; the intelligent operation control unit is used to generate control instructions for each device in the unit based on the configuration container of each application instance and the runtime data and derived runtime data of each device in the unit, and control each device in the unit based on each control instruction. The technical solution proposed in this application realizes the access of large-scale intelligent sensors and the systematization of intelligent operation control of power plants, improving the safety, reliability, flexibility, stability and efficiency of power plant operation control.

[0053] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0055] Figure 1 This is a first hardware structure diagram of a hyper-converged architecture intelligent control platform for a power plant provided according to one embodiment of the present application;

[0056] Figure 2 A schematic diagram of software operation of a hyper-converged architecture intelligent control platform for a power plant according to one embodiment of the present application;

[0057] Figure 3 A structural diagram of an intelligent engine module provided according to one embodiment of the present application;

[0058] Figure 4 This is a second hardware structure diagram of a hyper-converged architecture intelligent control platform for a power plant provided according to one embodiment of the present application;

[0059] Figure 5 The present invention provides a flowchart of a method for intelligent control of a hyper-converged architecture for a power plant according to one embodiment of the present application.

[0060] Reference numerals

[0061] Intelligent operation control module 1, firewall 2, high-throughput load balancing C / D network 3, hyper-converged all-in-one machine 4, intelligent operation control unit 1-1, intelligent sensing and control A / B network 1-1-1, intelligent controller 1-1-2, container runtime environment 1-1-2-1, data acquisition unit container 1-1-2-1-1, embedded time series database container 1-1-2-1-2, configuration container 1-1-2-1-3, database 4-1, intelligent engine module 4-2, configuration container image repository 4-3, monitoring module 4-4, time series database 4-1-1, big data platform 4-1-2, big data computing engine unit 4-2-1, artificial intelligence modeling engine unit 4-2-2, control algorithm configuration engine unit 4-2-3, intelligent engineer module 5, intelligent operator module 6, monitoring screen 7, security protection module 8, one-way network firewall 9. DETAILED DESCRIPTION

[0062] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0063] The present application proposes a hyper-converged architecture intelligent control platform and method for a power plant, wherein the control platform includes: an intelligent operation control module, a firewall, a high-throughput load balancing C / D network and a hyper-converged all-in-one machine; the intelligent operation control module is connected to the high-throughput load balancing C / D network through the firewall; the hyper-converged all-in-one machine is connected to the high-throughput load balancing C / D network; the intelligent operation control module includes: multiple intelligent operation control units, wherein the intelligent operation control unit includes an intelligent sensing and control A / B network, multiple intelligent controllers, and the intelligent controller is connected to the intelligent sensing and control A / B network; the hyper The integrated machine is used to learn based on the runtime data and non-time-series data of each device in the unit collected by each sensor, generate the configuration container image of each application instance and the derived runtime data of each device in the unit, and send the configuration container image of each application instance and the derived runtime data of each device in the unit to the intelligent operation control unit corresponding to each application instance; the intelligent operation control unit is used to generate control instructions for each device in the unit based on the configuration container of each application instance and the runtime data and derived runtime data of each device in the unit, and control each device in the unit based on each control instruction. The technical solution proposed in this application realizes the access of large-scale intelligent sensors and the systematization of intelligent operation control of power plants, improving the safety, reliability, flexibility, stability and efficiency of power plant operation control.

[0064] The following describes a hyper-converged architecture intelligent control platform and method for a power plant according to an embodiment of the present application with reference to the accompanying drawings.

[0065] Example 1

[0066] Figure 1 This is a structural diagram of a hyper-converged architecture intelligent control platform for a power plant provided according to one embodiment of the present application, such as Figure 1 As shown, it includes: intelligent operation control module 1, firewall 2, high throughput load balancing C / D network 3 and hyper-converged all-in-one machine 4;

[0067] The intelligent operation control module 1 is connected to the high-throughput load-balancing C / D network 3 through the firewall 2;

[0068] The hyper-converged integrated machine 4 is connected to the high-throughput load-balancing C / D network 3;

[0069] The smart operation control module 1 includes: multiple smart operation control units 1-1, wherein the smart operation control units include an intelligent sensing and control A / B network 1-1-1 and multiple intelligent controllers 1-1-2, and the intelligent controllers 1-1-2 are connected to the intelligent sensing and control A / B network 1-1-1;

[0070] The hyper-converged all-in-one machine 4 is configured to learn based on the runtime data and non-time-series data of each device in the group collected by each sensor, generate a configuration container image of each application instance and derived runtime data of each device in the group, and send the configuration container image of each application instance and derived runtime data of each device in the group to the intelligent operation control unit 1-1;

[0071] The intelligent operation control unit 1-1 is used to generate control instructions for each device in the unit based on the configuration container of each application instance and the operation timing data and derived operation timing data of each device in the unit, and control each device in the unit based on each control instruction.

[0072] In the embodiment of the present disclosure, Figure 2 As shown, the intelligent controller 1-1-2 is provided with a container runtime environment 1-1-2-1;

[0073] The container runtime environment 1-1-2-1 deploys and runs: a data acquisition unit container 1-1-2-1-1, an embedded time series database container 1-1-2-1-2, and a configuration container 1-1-2-1-3;

[0074] The configuration container is obtained by running the container runtime environment after receiving the configuration container image of each application instance from the configuration container image repository;

[0075] The data acquisition unit container and the embedded time series database container are built into the container runtime environment;

[0076] The data acquisition unit container 1-1-2-1-1 is used to collect the running time data and derived running time data of the corresponding equipment in the unit, and send the running time data and derived running time data of the corresponding equipment in the unit to the embedded time series database container 1-1-2-1-2;

[0077] The data acquisition unit container 1-1-2-1-1 can provide a real-time data interface to the outside world;

[0078] The embedded time series database container 1-1-2-1-2 is used to cache the running time series data and derived running time series data of the corresponding equipment in the unit;

[0079] The configuration container 1-1-2-1-3 is used to generate a control instruction based on the configuration container image, the runtime data and the derived runtime data, and to apply the control instruction to the corresponding device, wherein the configuration container 1-1-2-1-3 is selected based on the runtime data and the derived runtime data;

[0080] For example, the configuration container 1-1-2-1-3 is used to run various control algorithms, and the instructions generated by the execution of the control algorithms directly act on the field devices.

[0081] The generating of control instructions based on the configuration container image, the runtime data, and the derived runtime data includes:

[0082] Select each configuration container that needs to execute the control of each device according to the runtime data of each device and the derived runtime data of each device;

[0083] Based on the configuration container images corresponding to the selected configuration containers, the runtime data of each device and the derived runtime data of each device, control instructions for each device in the group are generated, and each device in the group is controlled based on the control instructions.

[0084] Furthermore, the data acquisition unit container 1-1-2-1-1, the embedded time series database container 1-1-2-1-2, and the configuration container 1-1-2-1-3 all adopt a three-copy high-availability deployment mode;

[0085] Among them, each replica uses a heartbeat mechanism to monitor each other. When the main container fails, any replica container will be randomly switched to the main container in milliseconds.

[0086] In the embodiment of the present disclosure, Figure 2 As shown, the hyper-converged machine 4 has a database 4-1, an intelligent engine module 4-2, a configuration container image repository 4-3 and a monitoring module 4-4 deployed and running in the built-in manner;

[0087] The database 4-1 includes a time series database 4-1-1 and a big data platform 4-1-2;

[0088] The embedded time series database container 1-1-2-1-2 is further used to send the cached runtime data and derived runtime data of the corresponding device in the group to the time series database 4-1-1;

[0089] The time series database 4-1-1 is used to store and manage the operation time series data and derived operation time series data of each device corresponding to each unit of the power plant, wherein the time series database 4-1-1 can provide a unified data interface to the outside;

[0090] The big data platform 4-1-2 is used to store and manage data of non-time series data type, which may be data of non-time series data type collected from various devices in the unit, such as images, videos, texts and other non-time series data;

[0091] The big data platform 4-1-2 can provide a unified data interface to the outside world;

[0092] The intelligent engine module 4-2 is configured to generate updated derived runtime data and configuration container images of each application instance based on the runtime data, derived runtime data, and non-time-series data of each device corresponding to each unit of the power plant, and send the updated derived runtime data to the data acquisition unit container 1-1-2-1-1, and send the configuration container image of each application instance to the configuration container image warehouse 4-3;

[0093] The configuration container image warehouse 4-3 is used to store and manage the configuration container images of each application instance, select the configuration container images that need to be distributed based on the operating conditions of the units in the power plant, and distribute the configuration container images to the container runtime environment 1-1-2-1 of each intelligent controller 1-1-2;

[0094] The configuration container image repository 4-3 is further configured to receive the running status of the configuration container 1-1-2-1-3 fed back by the container runtime environment 1-1-2-1, so as to monitor the status of the configuration container 1-1-2-1-3;

[0095] The configuration container image repository 4-3 can also provide a standard interface for container operation status to the outside world.

[0096] The configuration container image repository 4-3 can deliver the configuration container image to the container runtime environment 1-1-2-1 according to actual project requirements, and receive the configuration container operation status feedback from the container runtime environment 1-1-2-1 to monitor the status of all configuration containers in the entire power plant.

[0097] The monitoring module 4-4 is used to obtain real-time data and historical data of the container runtime environment 1-1-2-1, the time series database 4-1-1, the big data platform 4-1-2, the intelligent engine module 4-2 and the configuration container image warehouse 4-3, and generate a graphical interface based on the real-time data and historical data of the container runtime environment 1-1-2-1, the time series database 4-1-1, the big data platform 4-1-2, the intelligent engine module 4-2 and the configuration container image warehouse 4-3, and then monitor the operating status of the equipment and software based on the graphical interface.

[0098] It should be noted that the monitoring module 4-4 uses the real-time and historical data of the on-demand container runtime environment 1-1-2-1, the time series database 4-1-1, the big data platform 4-1-2, the intelligent engine module 4-2 and the configuration container image repository 4-3 through the standard interface, monitors the real-time and historical operating status of the on-site equipment and software through a graphical interface, and can directly send control instructions to the configuration container 1-1-2-1-3 to directly control the equipment.

[0099] Further, such as Figure 2 As shown, the monitoring module 4 - 4 is also used for power plant operators to directly intervene and input control instructions, and send the control instructions directly to the smart operation control module 1 .

[0100] It should be noted that if Figure 3 As shown, the intelligent engine module 4-2 includes: a big data computing engine unit 4-2-1, an artificial intelligence modeling engine unit 4-2-2 and a control algorithm configuration engine unit 4-2-3;

[0101] The big data computing engine unit 4-2-1 is used to generate derived runtime data and a big data model based on the data of the non-time series data type and the runtime data, and to generate an operator that can be directly applied by the control algorithm configuration engine unit based on the big data model;

[0102] The artificial intelligence modeling engine unit 4-2-2 is used to perform modeling training based on the data stored in the time series database and the big data platform, and use deep learning and machine learning algorithms to obtain an artificial intelligence model, and generate operators based on the artificial intelligence model that can be directly applied by the control algorithm configuration engine unit 4-2-3;

[0103] The control algorithm configuration engine unit 4-2-3 is used to perform algorithm configuration on the operator, containerize the configuration, generate a configuration container image, and synchronize the generated configuration container image to the configuration container image warehouse 4-3.

[0104] It should be noted that the hyper-converged appliance 4 uses general-purpose technology and a 7-node configuration, providing computing and storage capabilities for 100TB of data. The hyper-converged appliance 4 is deployed and runs by default with the following components: a container image repository 4-3, an intelligent engine module 4-2, a time series database 4-1-1, a big data platform 4-1-2, and monitoring software, namely, a monitoring module 4-4. All software deployed and running on the hyper-converged appliance 4 uses a B / S architecture.

[0105] In the embodiment of the present disclosure, Figure 4 As shown, the control platform also includes: an intelligent engineer module 5, an intelligent operator module 6 and a monitoring screen 7;

[0106] The intelligent engineer module 5 is used for system configuration, maintenance and monitoring;

[0107] The intelligent operator module 6 is used to monitor the on-site operation of the power plant and to perform manual intervention in emergency situations;

[0108] The monitoring screen 7 is used to display the operating status of the equipment in the power plant and the software in the control platform;

[0109] Among them, the intelligent engineer module 5, the intelligent operator module 6 and the monitoring screen 7 are all connected to the high-throughput load-balancing C / D network 3, and the intelligent engineer module 5 and the intelligent operator module 6 are used independently through strict permission configuration, and the software provided by the present invention is called through the browser to complete related work.

[0110] In the embodiment of the present disclosure, Figure 4 As shown, the control platform further includes: a security protection module 8;

[0111] The security protection module 8 is used for terminal protection, security auditing and active defense, wherein terminal protection, security auditing and active defense adopt common technologies;

[0112] The security protection module 8 is connected to the high-throughput load-balancing C / D network 3 .

[0113] In the embodiment of the present disclosure, Figure 4 As shown, the control platform further includes: a one-way network gate 9;

[0114] One end of the one-way network switch 9 is connected to the high-throughput load-balancing C / D network 3, and the other end is connected to the three-area management network. The one-way network switch 9 adopts a power-specific 100M forward network switch.

[0115] It should be noted that this embodiment provides two layered networks: the intelligent sensing and control A / B network 1-1-1 and the high-throughput load-balancing C / D network 3 (hereinafter referred to as the A / B network and the C / D network). The A / B network is used to support the intelligent sensor access and real-time control of a single unit. Each unit has an independent network, and each A / B network is independent of each other to ensure high reliability of local control of each level; the C / D network is used for plant-wide management and control and big data artificial intelligence applications, with one network for the entire plant. Each A / B network is connected in series to the C / D network through a primary and standby redundant firewall 2, and all communications between different networks must be whitelisted. Each unit deploys several pairs of primary and standby redundant intelligent controllers 1-1-2 on A / B according to demand. The intelligent controllers 1-1-2 are connected to the unit's local equipment and various intelligent sensors through the A / B network.

[0116] The A / B network is composed of Gigabit Ethernet switches and I / O modules. All on-site devices are connected to the Gigabit Ethernet switch after being connected to the IO module. Intelligent sensors such as infrared temperature measurement are directly connected to the Gigabit Ethernet switch, and all transmission media are optical fiber. The C / D network is composed of 10 Gigabit Ethernet switches, Gigabit Ethernet switches, and load balancers, arranged in a star structure. The core area uses four 10 Gigabit switches for high availability, and other nodes are deployed with dual-machine high availability on demand for 10 Gigabit or Gigabit switches. The load balancer is deployed in serial redundancy on the hyper-converged all-in-one machine and the C / D network core switch, and all transmission media are optical fiber. From a horizontal dimension, nodes on the A / B network of a single unit can communicate directly, while nodes on the A / B networks of different units must be authenticated by the firewall before communicating through the C / D network. Nodes on the C / D network can communicate directly; from a vertical dimension, each node on the A / B network and each node on the C / D network must be authenticated by the firewall before communicating.

[0117] In summary, the hyper-converged architecture intelligent control platform for power plants proposed in this embodiment fundamentally establishes an effective communication mechanism and a complete and stable system architecture for various smart applications related to production and operation of the power plant, making the division of labor among applications more reasonable, the grouping more coordinated, and the cooperation closer, ultimately achieving global optimization, thereby realizing the access of large-scale smart sensors and the systematization of power plant control, and improving the safety, reliability, flexibility, stability and efficiency of power plant control.

[0118] Example 2

[0119] Figure 5 This is a flow chart of a hyper-converged architecture intelligent control method for a power plant according to one embodiment of the present application, as shown in FIG. Figure 5 As shown, the method includes:

[0120] Step 1: Generate the configuration container image of each application instance and the derived runtime data of each device in the group based on the runtime data of each device in the group collected by each sensor;

[0121] Step 2: Select each configuration container that needs to execute the control of each device based on the runtime data of each device and the derived runtime data of each device;

[0122] Step 3: Generate control instructions for each device in the group based on the configuration container image corresponding to each selected configuration container, the runtime data of each device, and the derived runtime data of each device, and control each device in the group based on the control instructions.

[0123] In summary, the hyper-converged architecture intelligent control method for power plants proposed in this embodiment can realize the access of large-scale intelligent sensors and the systematization of power plant control, thereby improving the safety, reliability, flexibility, stability and efficiency of power plant control.

[0124] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0125] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0126] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A hyper-converged intelligent control platform for power plants, characterized by: include: Intelligent operation control module, firewall, high-throughput load balancing C / D network and hyper-converged all-in-one machine; The intelligent operation control module accesses the high-throughput load-balancing C / D network through the firewall; The hyper-converged integrated machine is connected to the high-throughput load-balancing C / D network; The smart operation control module includes: multiple smart operation control units, wherein the smart operation control units include an intelligent sensing and control A / B network and multiple intelligent controllers, and the intelligent controllers are connected to the intelligent sensing and control A / B network; The hyper-converged all-in-one machine is used to learn based on the runtime data and non-time-series data of each device in the group collected by each sensor, generate a configuration container image of each application instance and derived runtime data of each device in the group, and send the configuration container image of each application instance and the derived runtime data of each device in the group to the intelligent operation control unit corresponding to each application instance; The intelligent operation control unit is used to generate control instructions for each device in the unit based on the configuration container of each application instance and the operation timing data and derived operation timing data of each device in the unit, and control each device in the unit based on each control instruction.

2. The intelligent control platform according to claim 1, characterized in that: The intelligent controller is provided with a container runtime environment; The container runtime environment deploys and runs: a data acquisition unit container, an embedded time series database container, and a configuration container; The configuration container is obtained by running the container runtime environment after receiving the configuration container image of each application instance from the configuration container image repository; The data acquisition unit container and the embedded time series database container are built into the container runtime environment; The data acquisition unit container is used to collect the running time sequence data and the derived running time sequence data of the corresponding equipment in the unit, and send the running time sequence data and the derived running time sequence data of the corresponding equipment in the unit to the embedded time series database container; The embedded time series database container is used to cache the running time series data and derived running time series data of the corresponding equipment in the unit; The configuration container is used to generate control instructions based on the configuration container image, runtime data and derived runtime data, and apply the control instructions to the corresponding device, wherein the configuration container is selected based on the runtime data and derived runtime data.

3. The intelligent control platform according to claim 2, characterized in that: The data acquisition unit container, the embedded time series database container, and the configuration container all adopt a three-copy high-availability deployment mode; Among them, each replica uses a heartbeat mechanism to monitor each other. When the main container fails, any replica container will be randomly switched to the main container in milliseconds.

4. The intelligent control platform according to claim 2, characterized in that: The hyper-converged all-in-one machine has a database, an intelligent engine module, a configuration container image repository and a monitoring module deployed and running in the built-in manner; The database includes a time series database and a big data platform; The embedded time series database container is further configured to send the cached runtime data and derived runtime data of the corresponding device in the unit to the time series database; The time series database is used to store and manage the operation time series data and derived operation time series data of each device corresponding to each unit in the power plant; The big data platform is used to store and manage data of non-time series data types; The intelligent engine module is configured to generate updated derived runtime data and configuration container images of each application instance based on the runtime data, derived runtime data, and data of non-time series data types of each device corresponding to each unit of the power plant, and send the updated derived runtime data to the data acquisition unit container and the configuration container image of each application instance to the configuration container image repository; The configuration container image repository is used to store and manage the configuration container images of each application instance, select the configuration container images that need to be distributed based on the operating conditions of the units in the power plant, and distribute the configuration container images to the container runtime environment of each intelligent controller; The configuration container image repository is further used to receive the configuration container running status feedback from the container runtime environment to monitor the status of the configuration container; The monitoring module is used to obtain real-time data and historical data of the container runtime environment, time series database, big data platform, intelligent engine module and configuration container image warehouse, and generate a graphical interface based on the real-time data and historical data of the container runtime environment, time series database, big data platform, intelligent engine module and configuration container image warehouse, and then monitor the operating status of the device and software based on the graphical interface.

5. The intelligent control platform according to claim 4, characterized in that: The monitoring module is also used for power plant operators to directly intervene and input control instructions, and directly send the control instructions to the intelligent operation control module.

6. The intelligent control platform according to claim 5, characterized in that: The intelligent engine module includes: a big data computing engine unit, an artificial intelligence modeling engine unit and a control algorithm configuration engine unit; The big data computing engine unit is configured to generate derived runtime data and a big data model based on the data of the non-time series data type and the runtime data, and to generate an operator that can be directly applied by the control algorithm configuration engine unit based on the big data model; The artificial intelligence modeling engine unit is used to perform modeling training based on the data stored in the time series database and the big data platform, and to obtain an artificial intelligence model by using deep learning and machine learning algorithms, and to generate operators based on the artificial intelligence model that can be directly applied by the control algorithm configuration engine unit; The control algorithm configuration engine unit is used to perform algorithm configuration on the operator, containerize the configuration, generate a configuration container image, and synchronize the generated configuration container image to the configuration container image repository.

7. The intelligent control platform according to claim 1, characterized in that: The control platform also includes: an intelligent engineer module, an intelligent operator module and a monitoring screen; The intelligent engineer module is used for system configuration, maintenance and monitoring; The intelligent operator module is used to monitor the on-site operation of the power plant and provide manual intervention in emergency situations; The monitoring screen is used to display the operating status of the equipment in the power plant and the software in the control platform; The intelligent engineer module, the intelligent operator module and the monitoring screen are all connected to the high-throughput load-balancing C / D network.

8. The intelligent control platform according to claim 1, wherein: The control platform also includes: a security protection module; The security protection module is used for terminal protection, security auditing and active defense; Wherein, the security protection module is connected to the high-throughput load-balancing C / D network.

9. The intelligent control platform according to claim 1, characterized in that: The control platform also includes: a one-way network gatekeeper; One end of the unidirectional gateway is connected to the high-throughput load-balancing C / D network, and the other end is connected to the three-area management network.

10. A control method for a hyper-converged architecture intelligent control platform for a power plant based on any one of claims 1 to 9, characterized in that: The method comprises: Generate the configuration container image of each application instance and the derived runtime data of each device in the group based on the runtime data of each device in the group collected by each sensor; Select each configuration container that needs to execute the control of each device according to the runtime data of each device and the derived runtime data of each device; Based on the configuration container images corresponding to the selected configuration containers, the runtime data of each device and the derived runtime data of each device, control instructions for each device in the group are generated, and each device in the group is controlled based on the control instructions.

Images