5G-based thermal power plant system control method, device and system

Abstract

The invention relates to the technical field of industrial Internet of Things and smart energy, in particular to a 5G-based thermal power plant system control method, device and system, the method is applied to an edge computing gateway of a thermal power plant system, and the thermal power plant system is in communication connection with a cloud platform through a 5G network; the method comprises the following steps: collecting multi-source heterogeneous data in the operation process of a thermal power plant system; according to the application, firstly, differential transmission guarantee is provided for multi-source heterogeneous data of a thermal power plant through a 5G network slicing technology, and the reliability and real-time performance of key data are ensured; in combination with a powerful intelligent analysis engine of the cloud platform, mass data is deeply fused and mined, and accurate combustion optimization, fault early warning and environmental protection management strategies are generated; finally, closed-loop control is formed through cloud-side cooperation, and collaborative optimization and comprehensive improvement of the thermal power plant in the aspects of operation efficiency, equipment reliability and environmental protection compliance are integrally achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial Internet of Things and smart energy, and in particular to a control method, device and system for a thermal power plant system based on 5G. BACKGROUND

[0002] Thermal power plant operation data is scattered in multiple independent systems (such as DCS, SIS, and environmental protection monitoring systems), lacks unified integration, and results in low data utilization. Traditional wired communication is stable but has high wiring costs; while 4G communication is convenient but has problems of insufficient bandwidth and high latency, and is difficult to meet the real-time monitoring requirements (such as second-level updating of flue gas component data). SUMMARY

[0003] Therefore, the present application aims to provide a control method, device and system for a thermal power plant system based on 5G.

[0004] In a first aspect, the present application provides a control method for a thermal power plant system based on 5G, which is applied to an edge computing gateway of the thermal power plant system, and the thermal power plant system is connected to a cloud platform through a 5G network; the method comprises the following steps: Collecting multi-source heterogeneous data in the operation process of the thermal power plant system; For each piece of data in the multi-source heterogeneous data, matching a target slice channel for the data based on the type of the data; Uploading the data from the target slice channel to the cloud platform through the 5G network; Receiving a control strategy fed back by the cloud platform; Controlling the operation of the thermal power plant system based on the control strategy; The multi-source heterogeneous data at least includes flue gas component data from the outlet of a separator in the thermal power plant system, unit operation data from a DCS system, and pollutant emission data from an environmental protection monitoring system.

[0005] In combination with the first aspect, after the step of collecting multi-source heterogeneous data in the operation process of the thermal power plant system, the method further comprises the following steps: Performing data compression and outlier filtering processing on the multi-source heterogeneous data.

[0006] In combination with the first aspect, the flue gas component data includes concentration data of carbon monoxide, nitrogen oxides, sulfur dioxide and oxygen.

[0007] In combination with the first aspect, for each piece of data in the multi-source heterogeneous data, the step of matching the data to a target slice channel based on the type of the data comprises: parsing a data attribute feature of the data, the data attribute feature comprising at least one of a data source, a data representation symbol, data content, data size, and frequency; determining a service type to which the data belongs and a quality of service requirement of the data according to a predefined policy library; querying a preset 5G network slice mapping table based on the service type and / or the quality of service requirement to determine the target slice channel; labeling the data with a network slice identifier of the target slice channel and sending the data to a corresponding transmission queue.

[0008] The second aspect of the application provides a control method of a 5G-based thermal power plant system, applied to a cloud platform of the thermal power plant system, the cloud platform being in communication connection with an edge computing gateway deployed in the thermal power plant system through a 5G network; the method comprises: receiving multi-source heterogeneous data uploaded by the edge computing gateway deployed in the local thermal power plant through the 5G network; storing real-time monitoring data in the multi-source heterogeneous data into a time series database, and storing accident reports and operation logs in the multi-source heterogeneous data into a relational database; calling an intelligent analysis engine to perform data processing on the multi-source heterogeneous data to generate a control strategy; feeding back the control strategy to the edge computing gateway through the 5G network.

[0009] In combination with the second aspect, the step of calling the intelligent analysis engine to perform data processing on the multi-source heterogeneous data to generate a control strategy comprises: inputting unit operation data in the multi-source heterogeneous data into a preset long short-term memory network to output predicted boiler efficiency and generate a combustion optimization strategy; based on an Apriori association rule mining algorithm, performing correlation analysis on the stored historical accident data and the collected real-time operation data to generate fault warning information; based on pollutant emission data in the multi-source heterogeneous data, calculating total emissions and automatically generating an environmental protection supervision report; based on at least one of the combustion optimization strategy, the fault warning information, and the environmental protection supervision report, generating the control strategy.

[0010] The third aspect of the embodiment of the application further provides a control device of a 5G-based thermal power plant system, applied to an edge computing gateway of the thermal power plant system, the thermal power plant system being in communication connection with a cloud platform through a 5G network; the device comprises: a collection module for collecting multi-source heterogeneous data in the operation process of the thermal power plant system; The matching module is configured to match, for each piece of data in the multi-source heterogeneous data, a target slice channel for the data based on a type of the data; The uploading module is configured to upload the data from the target slice channel to the cloud platform through the 5G network; The receiving module is configured to receive a control strategy fed back by the cloud platform; The control module is configured to control the operation of the thermal power plant system based on the control strategy; The multi-source heterogeneous data includes flue gas component data from an outlet of a separator in the thermal power plant system, unit operation data from a DCS system, and pollutant emission data from an environmental protection monitoring system.

[0011] The fourth aspect of the embodiments of the present application further provides a control device of a thermal power plant system based on 5G, which is applied to a cloud platform of the thermal power plant system, and the cloud platform is in communication connection with an edge computing gateway deployed in the thermal power plant system through a 5G network; the device comprises: The data receiving module is configured to receive multi-source heterogeneous data uploaded by the edge computing gateway deployed in the local thermal power plant through the 5G network; The data storage module is configured to store real-time monitoring data in the multi-source heterogeneous data into a time series database, and store accident reports and operation logs in the multi-source heterogeneous data into a relational database; The data analysis module is configured to call an intelligent analysis engine to perform data processing on the multi-source heterogeneous data, and generate a control strategy; The strategy feedback module is configured to feed back the control strategy to the edge computing gateway through the 5G network.

[0012] The fifth aspect of the embodiments of the present application further provides a control system of a thermal power plant system based on 5G, which comprises an edge computing gateway deployed in a local thermal power plant and a remote cloud platform; the edge computing gateway is in communication connection with the cloud platform through a 5G network; the edge computing gateway is in communication connection with a data acquisition module in the thermal power plant system, and is configured to execute the method provided in the first aspect, and the cloud platform is configured to execute the method provided in the second aspect.

[0013] In combination with the fifth aspect, the cloud platform comprises: The data warehouse module is configured to store the received real-time monitoring data into a time series database, and store accident reports and operation logs into a relational database; The intelligent analysis engine module is configured to call data in the data warehouse module to perform fusion analysis; The intelligent analysis engine module comprises: The operation optimization unit is configured to generate a combustion optimization strategy based on the unit operation data; The accident warning unit is configured to generate fault warning information based on correlation analysis of historical and real-time data; The environmental protection supervision unit is configured to generate an environmental protection supervision report based on the pollutant emission data; The intelligent decision support module is configured to make a comprehensive decision based on at least one of the combustion optimization strategy, the fault early warning information and the environmental protection supervision report output by the intelligent analysis engine module, and generate a control strategy.

[0014] The application provides a control method of a thermal power plant system based on 5G, which is applied to an edge computing gateway of the thermal power plant system, and the thermal power plant system and a cloud platform are connected in communication through a 5G network. The method comprises the following steps: collecting multi-source heterogeneous data in a running process of the thermal power plant system; for each piece of data in the multi-source heterogeneous data, matching a target slice channel for the data based on the type of the data; uploading the data from the target slice channel to the cloud platform through the 5G network; receiving a control strategy fed back by the cloud platform; and controlling the running of the thermal power plant system based on the control strategy. The multi-source heterogeneous data at least comprises flue gas component data from an outlet of a separator in the thermal power plant system, unit running data from a DCS system and pollutant emission data from an environmental protection monitoring system.

[0015] The application first provides differentiated transmission guarantee for multi-source heterogeneous data of the thermal power plant through 5G network slicing technology, ensures the reliability and real-time performance of key data, combines the powerful intelligent analysis engine of the cloud platform, deeply fuses and mines massive data, generates accurate combustion optimization, fault early warning and environmental protection management strategies, and finally forms a closed-loop control through cloud-edge collaboration, and the running efficiency, equipment reliability and environmental protection compliance of the thermal power plant are overall optimized and improved.

[0016] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the description and claims of the present application.

[0017] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described in detail as follows. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0019] Figure 1A control method schematic diagram of a 5G-based thermal power plant system provided for Embodiment 1 is shown in the figure; Figure 2 A control method schematic diagram of a 5G-based thermal power plant system provided for Embodiment 2 is shown in the figure; Figure 3 A control device schematic diagram of a 5G-based thermal power plant system provided for Embodiment 3 is shown in the figure; Figure 4 A control device schematic diagram of a 5G-based thermal power plant system provided for Embodiment 4 is shown in the figure; Figure 5 A control system schematic diagram of a 5G-based thermal power plant system provided for Embodiment 5 is shown in the figure; Figure 6 An electronic device structure schematic diagram provided for the embodiment of the present application is shown in the figure.

[0020] Reference signs: 10 - collection module, 20 - matching module, 30 - upload module, 40 - receiving module, 50 - control module; 60 - data receiving module, 70 - data storage module, 80 - data analysis module, 90 - strategy feedback module; 130 - processor, 131 - memory, 132 - bus, 133 - communication interface. DETAILED DESCRIPTION

[0021] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0022] To facilitate the understanding of the present embodiment, the application scenario and design idea of the present application embodiment will be briefly introduced below.

[0023] The traditional thermal power plant data monitoring system has many shortcomings, such as high data transmission delay, limited storage capacity, and difficult multi-source data integration, which leads to insufficient real-time and accuracy of operation optimization and fault warning.

[0024] Based on this, the present application provides a control method, device and system of a 5G-based thermal power plant system.

[0025] Embodiment 1 The present application provides a control method of a 5G-based thermal power plant system, which is applied to an edge computing gateway of a thermal power plant system, and the thermal power plant system is in communication connection with a cloud platform through a 5G network. Figure 1 As shown in the figure, the method comprises: S110, collect multi-source heterogeneous data in a running process of a thermal power plant system.

[0026] S120, for each piece of data in the multi-source heterogeneous data, match a target slice channel for the data based on a type of the data.

[0027] S130, upload the data from the target slice channel to a cloud platform through a 5G network.

[0028] S140, receive a control strategy fed back by the cloud platform.

[0029] S150, control the running of the thermal power plant system based on the control strategy.

[0030] The multi-source heterogeneous data includes flue gas component data at an outlet of a separator in the thermal power plant system, unit operation data from a DCS system, and pollutant emission data from an environmental protection monitoring system.

[0031] The control method of the thermal power plant system based on 5G provided in the application utilizes the synergistic effect of the slice technology of the 5G network and the edge computing gateway to efficiently and reliably transmit the collected multi-source heterogeneous data to the cloud platform, so as to solve the problem of efficient, reliable and real-time transmission of massive and diverse (multi-source heterogeneous) data of the thermal power plant, and then generate an optimal control strategy that can achieve both economic benefits (high-efficiency power generation) and environmental protection requirements (low-cost compliance) based on the system analysis of the multi-source heterogeneous data by the cloud platform. The method solves the possible contradiction between "operation" and "environmental protection" in the traditional control, so as to realize the closed loop of intelligent decision and precise on-site control, and finally improve the intelligent level, efficiency and environmental protection performance of the thermal power plant. The thermal power plant system is the object to be controlled, and usually includes a boiler, a steam turbine, a generator, environmental protection equipment (such as a desulfurization and denitrification device), etc.

[0032] In step S110, the "separator" refers to a cyclone separator, which is a core equipment of a circulating fluidized bed boiler, and is usually arranged at the outlet of the furnace for separating solid particles (mostly unburned coal particles and bed materials) entrained by high-temperature flue gas from the furnace, and continuously feeding the separated high-temperature solid particles back to the bottom of the furnace through a return feeder for continuous combustion and circulation. In the power plant system, the cyclone separator improves the combustion efficiency and heat transfer efficiency, and ensures the maximum energy input on the boiler side. The stable operation of the cyclone separator is a prerequisite for the stable operation of the circulating fluidized bed boiler. If the separator fails, the bed material will be quickly lost, resulting in the extinguishing of the boiler. The existing environmental protection monitoring system of the circulating fluidized bed boiler usually arranges the flue gas sampling point at the tail flue or the flue inlet of the chimney. This arrangement has obvious measurement time lag, and it is difficult to effectively guide the operation adjustment in time, especially in the process of achieving ultra-low emission. Excessive injection of denitration reducing agent and in-furnace desulfurizer is prone to occur. Excessive ammonia injection not only causes an increase in escaped ammonia, but also may cause blockage of the tail flue heating surface. When the load changes, such configuration is also prone to cause sharp fluctuations in environmental protection parameters and operation control indicators, affecting the safety, environmental protection and economy of the boiler operation.

[0033] In addition, most of the current gas component measurement points use tail flue symmetrical arrangement or chimney inlet single point arrangement. At this time, the flue gas has been mixed to a certain extent, and the measurement results can only reflect the average state after combustion, and cannot reflect the differences in combustion characteristics, pollutant generation and removal in different regions of the furnace, so it is difficult to achieve targeted operation adjustment. In the current combustion adjustment and ultra-low emission control of the circulating fluidized bed boiler, the operation personnel have limited operation means. Combustion adjustment is mostly dependent on macro parameters such as bed temperature, coal supply and oxygen content for rough adjustment; in terms of pollutant control, it is common to improve the calcium-sulfur molar ratio and the ammonia-nitrogen molar ratio to strengthen the desulfurization and denitrification effect, especially under low load, variable load or uneven combustion conditions. Although many enterprises have made many technical transformations and optimization tests in the aspects of air cap transformation, installation of desulfurization and denitrification devices in the secondary air area, and multi-point ammonia injection at the separator outlet, they try to seek a more optimal operation mode, but they tend to monitor in the mixed and uniform tail flue, thus ignoring the value of zoned monitoring, resulting in limited effect and poor promotion. The fundamental reason is that there is a serious shortage of key parameters reflecting the combustion state in the furnace, and the traditional method relying on long-term operation data and experience accumulation cannot systematically achieve fine optimization.

[0034] The embodiment of the present application sets the gas component sampling point at the outlet of the separator, can obtain the flue gas data of each area before the full mixing, and can reflect the combustion and pollutant generation characteristics of different areas in the furnace more than setting at the tail flue or other downstream positions. Accordingly, the differentiated regulation based on the partition data can be realized, the potential of the existing system in the combustion and pollution control can be fully tapped, the ambiguous problems in the operation can be clarified, and a new way for the deep optimization of the circulating fluidized bed boiler is provided.

[0035] The "DCS system" is a corresponding distributed control system of the power plant system, the DCS controls the entire unit (boiler, steam turbine, generator) and its auxiliary system as a whole, mainly including: a data acquisition system (DAS) for acquiring data of all measuring points, an analog control system (MCS) for automatically adjusting combustion, water supply, temperature, pressure, etc. (such as automatic water supply of the boiler, automatic main steam temperature, automatic combustion), a sequence control system (SCS) for controlling the start and stop and interlocking of the fan, water pump, valve and other equipment, a boiler furnace safety monitoring system (FSSS) for managing and protecting the safety of the boiler burner, an electrical control system (ECS) for controlling the generator, excitation system, and auxiliary power system, and a digital electro-hydraulic control system (DEH) of the steam turbine. The "unit operation data of the DCS system" at least includes one of the boiler temperature, pressure, steam turbine speed, load, water supply amount, and fuel amount.

[0036] The "pollutant emission data of the environmental protection monitoring system" at least includes one of the real-time concentrations of SO2, NOx, and dust particulate matters in the flue gas.

[0037] In the present application, based on the massive data provided by the DCS and the like, the edge computing gateway and the cloud platform perform large-scale, long-period, and complex model optimization calculation (the calculation period can be minutes, hours or even longer), and generate more optimal set values or strategies. It is the "decision maker" and "brain" of control optimization. The architecture forms a "cloud-edge-end" cooperation, the cloud platform is used for global optimization and AI decision, the edge gateway is used for data aggregation, protocol conversion, instruction issuing, the end (i.e. the DCS system and the unit equipment) is used for real-time control and safe execution based on the issued instructions.

[0038] It can be understood that the 5G network slice allows multiple independent and logically isolated dedicated network channels to be virtually created on the same physical 5G network, and each channel can customize different network characteristics (such as bandwidth, latency, and reliability) according to business needs. Therefore, step S120 classifies data based on the format, protocol, or communication structure of each data in the multi-source heterogeneous data, and matches each data with a "target slice channel", that is, matches different business needs with appropriate network resources. For example, for "monitoring data" such as flue gas component data or unit operation data, it is very important. At this time, the business requirement (i.e. the requirement for information transmission) is low latency and high reliability. At this time, URLLC slice or high-priority eMBB slice is used. It can be understood that critical real-time data needs to be uploaded with low latency for analysis. If used for closed-loop control, URLLC must be used. For example, for the pollutant emission data of the environmental monitoring system, the data is generally important, and the periodic reporting of data is sufficient. At this time, the business requirement is periodic transmission and medium reliability. At this time, high-reliability eMBB or mMTC slice is used, indicating that the data is important, but the real-time requirement is slightly lower than the control instruction, and it is necessary to ensure that the data is not lost.

[0039] Subsequent step S130 transmits data to the cloud platform through the matched target slice channel, waits for the control strategy fed back by the cloud platform after processing the data transmitted by each target slice channel, and regulates the operation state of the thermal power plant system based on the control strategy in step S150.

[0040] In combination with the first aspect, after step S110, it further includes: S111, data compression and outlier filtering processing is performed on the multi-source heterogeneous data.

[0041] It can be understood that although the 5G bandwidth is large, it is not unlimited. Thermal power plants generate a large amount of data per second (especially high-frequency vibration, image video, etc.), and uploading all raw data will occupy a large amount of valuable network slice resources, which may cause network congestion. "Data compression" is used to reduce the amount of data transmitted over the network, save bandwidth resources, and reduce transmission latency and cost. After "data compression", more bandwidth can be left for businesses that truly need high speed (such as video monitoring).

[0042] In addition, if the data received by the cloud platform contains a large number of abnormal values generated by sensor failure, electromagnetic interference, etc., the AI model trained based on these data or the optimization decision made will be unreliable or even dangerous, and through "outlier filtering", the abnormal values (noise, glitches, incorrect data) in the data are identified and processed, and the abnormal data are intercepted on the edge side, avoiding the storage and calculation of invalid data in the cloud, saving valuable cloud computing resources, improving the data quality uploaded to the cloud platform, and ensuring the accuracy of cloud AI analysis and decision-making. Usually, the outlier filtering process is based on preset rules, statistical methods or machine learning patterns. The preset rule can be that data exceeding the set threshold range is considered abnormal data; the statistical method can be Z-Score, interquartile range, etc. to identify abnormal data that deviate significantly from the statistical distribution of the data.

[0043] Through "data compression" and "outlier filtering processing", the data stream can be more concise and of higher quality, which means that when URLLC slice transmission control instructions are transmitted, the delay is lower and more reliable, when eMBB slice video is transmitted, more bandwidth is saved, more videos can be transmitted, and when mMTC slice sensor data is transmitted, the connection capacity is larger, thereby obtaining a qualitative change from quantitative change in technical improvement, maximizing the value of 5G network slicing, and further optimizing the entire process from data generation to intelligent decision-making.

[0044] In combination with the first aspect, the flue gas component data includes concentration data of carbon monoxide, nitrogen oxides, sulfur dioxide and oxygen.

[0045] The concentration of oxygen is used to reflect the combustion air distribution of the boiler and the combustion sufficiency. If the concentration value is too high, it indicates that the air volume is too large, which will increase the exhaust heat loss and reduce the thermal efficiency of the boiler. If the concentration value is too low, it indicates that the air volume is insufficient, which will cause incomplete combustion of the fuel and produce more carbon monoxide (CO), even black smoke, which will also reduce the efficiency and pollute the environment. The concentration of oxygen is one of the most core parameters to be adjusted in the automatic combustion control system. The DCS system dynamically adjusts the damper opening of the air supply fan according to the oxygen value to find the best excess air coefficient to achieve the most efficient combustion.

[0046] The concentration of carbon monoxide is used to directly reflect the degree of complete combustion of the fuel (combustion efficiency). If the CO concentration is high, it indicates that the fuel is not completely combusted, causing chemical incomplete combustion heat loss. In the control process, the CO concentration is used as an auxiliary and optimization parameter for O2 control. Abnormal increase of the CO concentration is an early warning signal of combustion deterioration (such as coal mill failure, serious imbalance of air-coal ratio).

[0047] Similarly, the concentration of nitrogen oxides and the concentration of sulfur dioxide are also important indicators in the combustion process. Traditional DCS may only perform local, single-target control (for example, only adjusting the air according to O2). In the present application, the two core goals of "high-efficiency power generation" (optimizing combustion through O2 and CO) and "clean and environmentally friendly" (controlling emissions through NOx and SO2) are closely linked, and multi-objective collaborative optimization is performed through 5G and cloud-edge collaboration technology to find a global optimal operation scheme that can simultaneously satisfy "highest thermal efficiency, lowest NOx generation, and best SO2 removal", and then the scheme is issued to the edge gateway and DCS for execution. This is something that traditional control cannot achieve. In addition, through trend analysis of historical flue gas data, the cloud platform can predict problems such as catalyst performance degradation and ammonia injection nozzle blockage, thereby achieving predictive maintenance.

[0048] In combination with the first aspect, step S120 comprises: S121, analyzing data attribute features of the data, the data attribute features including at least one of data source, data symbol, data content, data size and frequency.

[0049] It can be understood that the edge computing gateway has a built-in data analysis engine to deconstruct the data to extract key features for subsequent decision-making. The data source is used to identify whether the data comes from the DCS system, the environmental protection monitoring system, or a specific flue gas component sensor. The data identifier is obtained by reading the data point tag (Tag), such as BTU101.TEMP (boiler No. 1 temperature point) and ESP.OUT.NOx (static precipitator outlet nitrogen oxide concentration). The data content is obtained by analyzing the data value itself and its unit (e.g., 550℃, 45.7 mg / m 3 ). The data size and frequency are determined by judging whether the data is a high-frequency sampled real-time stream or a low-frequency reported intermittent data.

[0050] S122, determining the service type to which the data belongs and the quality of service requirement thereof according to a pre-defined policy library.

[0051] It can be understood that the edge computing gateway has a built-in data analysis engine to deconstruct the data to extract key features for subsequent decision-making. The data source is used to identify whether the data comes from the DCS system, the environmental protection monitoring system, or a specific flue gas component sensor. The data identifier is obtained by reading the data point tag (Tag), such as BTU101.TEMP (boiler No. 1 temperature point) and ESP.OUT.NOx (static precipitator outlet nitrogen oxide concentration). The data content is obtained by analyzing the data value itself and its unit (e.g., 550℃, 45.7 mg / m 3 ). The data size and frequency are determined by judging whether the data is a high-frequency sampled real-time stream or a low-frequency reported intermittent data.

[0052] As an example, in the embodiment, the predefined service types can have a real-time control class (such as a downlink control instruction from a cloud platform, a safety signal requiring extremely fast interlocking between DCS systems), a key telemetry class (such as separator outlet flue gas components (O2, CO, NOx), steam turbine speed, bearing vibration signals), a large bandwidth uplink class (such as high-definition video monitoring streams, accident recall files, and device high-frequency vibration waveform data), and a massive connection class (such as status data periodically reported by thousands of temperature, pressure, and humidity sensors in a plant). It can be understood that the predefined service types can be increased, reduced, or replaced according to actual needs, and here are only examples and are not limited.

[0053] It can be understood that different service types correspond to specific quality of service requirements. In combination with the above examples, the service quality requirements corresponding to the real-time control class are: extremely low latency (<10 ms) and ultra-high reliability (99.999%); the service quality requirements corresponding to the key telemetry class are: low latency (<50 ms) and high reliability; the service quality requirements corresponding to the large bandwidth uplink class are: high throughput and large bandwidth (>100 Mbps); and the service quality requirements corresponding to the massive connection class are: massive connections, low power consumption, and small data packets.

[0054] It can be understood that the predefined service types and the mapping relationship between the service types and the quality of service requirements can be increased, reduced, or replaced according to actual needs, and here are only examples and are not limited.

[0055] S123, querying a preset 5G network slice mapping table based on the service type and / or the quality of service requirement to determine a target slice channel.

[0056] It can be understood that the network slice mapping table is stored in the policy library of the edge computing gateway, so that one or more conditions in the service type and the quality of service requirement in the network slice mapping table are used to find a corresponding target slice channel.

[0057] For example, the data “flue gas components (O2, NOx) and unit core parameters” correspond to the service type “key telemetry”, based on the preset mapping relationship between the service type and the quality of service requirement, it is determined that the quality of service requirement is: low latency and high reliability; and then based on the determined quality of service requirement, the network slice mapping table is searched to find that the target slice channel corresponding to “low latency and high reliability” is “high-priority eMBB slice or URLLC slice”, so that the target slice channel matching the data “flue gas components (O2, NOx) and unit core parameters” is determined to be “high-priority eMBB slice” or “URLLC slice”.

[0058] S124, marking the data with a network slice identifier of the target slice channel and sending the data into a corresponding transmission queue.

[0059] Based on the matching result of step S123, the identifier of the target slice is marked in the protocol header of the data packet corresponding to the data, and then the data packet is sent to the dedicated network transmission queue reserved for the slice channel. Thus, the best network path is adaptively selected for it, the network resources are finely managed and allocated on demand, the problem that high-priority key data is blocked by large-flow low-priority data is avoided, the timely and reliable transmission of production control and safety instructions is ensured, and the safety of the system is greatly improved.

[0060] As a preferred, a strict scheduling algorithm is used for the queues of different priorities to ensure that the control data of high priority is always transmitted preferentially.

[0061] Embodiment 2 In a second aspect, the application provides a control method of a 5G-based thermal power plant system, which is applied to a cloud platform of the thermal power plant system, and the cloud platform is in communication connection with an edge computing gateway deployed in the thermal power plant system through a 5G network. As shown in the figure, the method comprises the following steps. Figure 2 S210, receiving multi-source heterogeneous data uploaded by the edge computing gateway deployed in the local thermal power plant through the 5G network.

[0062] S220, storing real-time monitoring data in the multi-source heterogeneous data into a time series database, and storing accident reports and operation logs in the multi-source heterogeneous data into a relational database.

[0063] S230, calling an intelligent analysis engine to process the multi-source heterogeneous data to generate a control strategy.

[0064] S240, feeding back the control strategy to the edge computing gateway through the 5G network.

[0065] Firstly, the cloud platform receives data collected by one or more power plants and multiple edge computing gateways through a 5G network interface. It can be understood that the data is preliminarily classified and slice-matched by the edge computing gateway, which ensures that key data (such as flue gas components and alarm signals) reaches the cloud platform preferentially and reliably.

[0066] ​Subsequently, different databases are stored based on different data types, and a time series database is optimized for processing data generated in chronological order, high write-throughput, and rarely updated. It supports efficient data compression and fast aggregation queries for time windows (such as "Query No. 1 boiler for the average efficiency of every 5 minutes in the past 24 hours"), and is very suitable for storing massive amounts of device monitoring data, so it is suitable for storing real-time monitoring data such as flue gas temperature, pressure, O2, NOx concentration, unit load, steam flow, etc. collected every second; and the transactional, consistent (ACID feature) and powerful correlation query capability of the relational database is very suitable for managing business logic data (data with complex correlation relationships, such as an incident associated with multiple alarms, multiple operators, and multiple devices), so it can store accident reports, operation logs, operation records, and equipment account books.

[0067] Subsequently, step S230 performs collaborative processing of data to find the best balance point between multiple targets given by the user, and generates a globally optimal control strategy. The control strategy issued in step S240 is executed by the edge computing gateway in S150, wherein the downlink transmission of the control strategy is the service with the highest requirements for latency and reliability, and must use URLLC (Ultra-Reliable Low-Latency Communication) slices to ensure that the optimization strategy can be delivered to the production site without delay and stably and reliably.

[0068] In combination with the second aspect, step S230 includes: S231, input the unit operation data in the multi-source heterogeneous data into a preset long short-term memory network, output the predicted boiler efficiency, and generate a combustion optimization strategy.

[0069] It can be understood that the operation data of the thermal power plant is typical time series data, and therefore the collected unit operation data is also time series data. The long short-term memory network (LSTM) is very suitable for processing and predicting long-term dependencies in time series data, and therefore in this application, the input unit operation data (such as load, main steam temperature, main steam pressure, coal supply, air volume, flue gas content O2, CO, NOx, etc.) is processed based on the long short-term memory network (LSTM) to learn the complex mapping relationship between the operation parameters and the boiler efficiency (which usually needs to be calculated) in the historical data, so as to be able to predict the current and future efficiency in real time according to the real-time data. At the same time, reverse optimization is performed to find the optimal operation parameter combination (such as secondary air damper opening, combustion air ratio, oxygen set value, etc.) that can make the predicted efficiency the highest and the NOx generation the lowest under the given current load and coal quality, thereby generating a specific optimization strategy (such as "suggest adjusting the A layer secondary air damper opening from 45% to 50%").

[0070] Thus, the data analysis capability of the learning model is used to calculate the optimization strategy, replacing manual experience optimization, to achieve more accurate and effective control adjustment.

[0071] In S232, based on the Apriori association rule mining algorithm, the stored historical accident data and the collected real-time operation data are associated and analyzed to generate fault early warning information.

[0072] The Apriori algorithm is a classic association rule mining algorithm used to discover interesting association relationships between large data item sets. By analyzing massive historical accident data, frequent patterns leading to specific faults (such as "high vibration of fan jump") are found, and real-time operation data is matched with these "association rules" mined. Once the combination of multiple parameters in the real-time data stream meets the characteristics of a certain rule before the fault occurs, the system immediately triggers early warning, rather than waiting for the device parameters to exceed the limit to alarm. In this way, signals can be sent at the embryonic stage of the fault, providing valuable processing time windows for operation and maintenance personnel, achieving predictive maintenance and early warning.

[0073] In S233, based on the pollutant emission data in the multi-source heterogeneous data, the total emission amount is calculated and an environmental protection supervision report is automatically generated.

[0074] By automatically integrating real-time pollutant (SO2, NOx, dust) concentration and flue gas flow data, the cumulative total emission amount is calculated on a hourly, daily, monthly, etc. basis, and compared with the total emission permit issued by the state to determine whether it meets environmental protection requirements. At the same time, based on the stored data and calculation results, the system can automatically generate daily, monthly, and annual reports that meet the requirements of the environmental protection department. The report content can be automatically filled, greatly reducing the workload of manual transcription, calculation, and tabulation, and avoiding human errors. This improves environmental management from passive monitoring to active and refined management, ensuring that the enterprise operates in compliance with regulations and avoids environmental penalties.

[0075] In S234, at least one of the combustion optimization strategy, the fault early warning information, and the environmental protection supervision report is used to generate a control strategy.

[0076] The economic target corresponding to the combustion optimization strategy, the safety target corresponding to the fault early warning information, and the compliance target corresponding to the environmental protection supervision report. These targets are sometimes contradictory (for example, pursuing the highest efficiency may cause NOx to rise), so multi-objective optimization is needed to generate a globally optimal final control strategy that balances economy, safety, and environmental protection.

[0077] Embodiment 3 A control device for a thermal power plant system based on 5G, characterized by an edge computing gateway applied to a thermal power plant system, wherein the thermal power plant system is in communication connection with a cloud platform through a 5G network;Figure 3 As shown, the device comprises a collection module 10, a matching module 20, an uploading module 30, a receiving module 40 and a control module 50.

[0078] The collection module 10 is configured to collect multi-source heterogeneous data in the operation process of the thermal power plant system.

[0079] The matching module 20 is configured to match a target slice channel for each piece of data in the multi-source heterogeneous data based on the type of the data.

[0080] The uploading module 30 is configured to upload the data from the target slice channel to the cloud platform through a 5G network.

[0081] The receiving module 40 is configured to receive a control strategy fed back by the cloud platform.

[0082] The control module 50 is configured to control the operation of the thermal power plant system based on the control strategy.

[0083] The multi-source heterogeneous data comprises flue gas component data from the outlet of a separator in the thermal power plant system, unit operation data from a DCS system and pollutant emission data from an environmental protection monitoring system.

[0084] Embodiment 4 The embodiment of the present application provides a control device for a thermal power plant system based on 5G, which is applied to a cloud platform of the thermal power plant system. The cloud platform is in communication connection with an edge computing gateway deployed in the thermal power plant system through a 5G network. In combination with Figure 4 As shown, the device comprises a data receiving module 60, a data storage module 70, a data analysis module 80 and a strategy feedback module 90.

[0085] The data receiving module 60 is configured to receive multi-source heterogeneous data uploaded by the edge computing gateway deployed in the local thermal power plant through a 5G network.

[0086] The data storage module 70 is configured to store real-time monitoring data in the multi-source heterogeneous data into a time series database, and at the same time, store accident reports and operation logs in the multi-source heterogeneous data into a relational database.

[0087] The data analysis module 80 is configured to call an intelligent analysis engine to process the multi-source heterogeneous data, and generate a control strategy.

[0088] The strategy feedback module 90 is configured to feed back the control strategy to the edge computing gateway through a 5G network.

[0089] Embodiment 5 This application provides a control system for a 5G-based thermal power plant system. The system includes an edge computing gateway deployed locally at the power plant and a remote cloud platform. The edge computing gateway and the cloud platform are connected via a 5G network. The edge computing gateway is connected to a data acquisition module within the power plant system to execute the method described in Example 1, and the cloud platform is used to execute the method described in Example 2. Figure 5 The arrows shown indicate the direction of data flow.

[0090] In conjunction with the fifth aspect, the cloud platform also includes: The data warehouse module is used to store the received real-time monitoring data into a time-series database and to store accident reports and operation logs into a relational database. The intelligent analysis engine module is used to call the data in the data warehouse module to perform the fusion analysis; The intelligent analysis engine module includes: The operation optimization unit is used to generate combustion optimization strategies based on unit operation data; The accident early warning unit is used to generate fault early warning information based on the correlation analysis of historical and real-time data; Environmental monitoring unit, used to generate environmental monitoring reports based on pollutant emission data; The intelligent decision support module is used to make comprehensive decisions based on at least one of the combustion optimization strategy, fault warning information and environmental supervision report output by the intelligent analysis engine module, and generate the control strategy.

[0091] Sixthly, embodiments of this application provide an electronic device, combined with Figure 6 As shown, the electronic device includes a memory 131 and a processor 130. The memory 131 stores a computer program, and the processor 130 runs the computer program to make the electronic device perform the above-described method.

[0092] Furthermore, combined Figure 6 The electronic device shown also includes a bus 132 and a communication interface 133, with the processor 130, the communication interface 133 and the memory 131 connected via the bus 132.

[0093] The memory 131 can include a high-speed random access memory (RAM) and can also include a non-volatile memory such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 133 (which can be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. can be used. The bus 132 can be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used to represent the system network element and at least one other network element in the above method, but it does not mean that there is only one bus or one type of bus.

[0094] The processor 130 can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor 130 or the instructions in the form of software. The processor 130 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block disclosed in the embodiment of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiment of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 131, and the processor 130 reads the information in the memory 131 and combines the hardware to complete the steps of the method of the above embodiment.

[0095] In a fourth aspect, the embodiments of the present application provide a readable storage medium, and the readable storage medium stores computer program instructions. When the computer program instructions are read and run by a processor, the above method is executed.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0097] In addition, in the description of the embodiments of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood in a broad sense, for example, can be fixedly connected, can also be detachably connected, or integrally connected; can be mechanically connected, can also be electrically connected; can be directly connected, can also be indirectly connected through an intermediate medium, can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0098] If the function is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application which essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0099] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0100] Finally, it should be noted that the above examples are merely specific embodiments of the present application, and are used to illustrate the technical solutions of the present application, but are not intended to limit the present application. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that any person skilled in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing examples, or make equivalent replacements to some of the technical features, within the technical range disclosed by the present application. These modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method for a 5G-based thermal power plant system, characterized in that, An edge computing gateway for use in a thermal power plant system, wherein the thermal power plant system is connected to a cloud platform via a 5G network; the method includes: Collect multi-source heterogeneous data during the operation of thermal power plant systems; For each piece of data in the multi-source heterogeneous data, a target slice channel is matched to the data based on the data type; The data is uploaded to the cloud platform via the target slice channel through the 5G network. Receive control strategies fed back from the cloud platform; The operation of the thermal power plant system is controlled based on the aforementioned control strategy; The multi-source heterogeneous data includes at least flue gas composition data from the separator outlet of the thermal power plant system, unit operation data from the DCS system, and pollutant emission data from the environmental monitoring system.

2. The method according to claim 1, characterized in that, Following the steps of collecting multi-source heterogeneous data during the operation of a thermal power plant system, the following are also included: The multi-source heterogeneous data is subjected to data compression and outlier filtering.

3. The method according to claim 1, characterized in that, The flue gas component data includes concentration data for carbon monoxide, nitrogen oxides, sulfur dioxide, and oxygen.

4. The method according to claim 1, characterized in that, For each piece of data in the multi-source heterogeneous data, the step of matching the target slice channel to the data based on the data type includes: The data attribute characteristics of the data are analyzed, and the data attribute characteristics include at least one of the following: data source, data identifier, data content, data size and frequency; Based on a predefined policy library, determine the business type to which the data belongs and its service quality requirements; Based on the service type and / or quality of service requirements, query the preset 5G network slice mapping table to determine the target slice channel; The data is tagged with the network slice identifier of the target slice channel and sent to the corresponding transmission queue.

5. A control method for a 5G-based thermal power plant system, characterized in that, A cloud platform applied to a thermal power plant system, wherein the cloud platform is connected to an edge computing gateway deployed in the thermal power plant system via a 5G network; the method includes: Receive multi-source heterogeneous data uploaded via a 5G network from an edge computing gateway deployed locally at the thermal power plant; The real-time monitoring data from the multi-source heterogeneous data is stored in a time-series database, and the accident reports and operation logs from the multi-source heterogeneous data are stored in a relational database. The intelligent analysis engine is invoked to process the multi-source heterogeneous data and generate a control strategy. The control strategy is fed back to the edge computing gateway via the 5G network.

6. The method according to claim 5, characterized in that, The steps of calling the intelligent analysis engine to process the multi-source heterogeneous data and generate a control strategy include: The unit operation data from the multi-source heterogeneous data is input into a preset long short-term memory network, and the output is a predicted boiler efficiency and a combustion optimization strategy is generated. Based on the Apriori association rule mining algorithm, the stored historical accident data and the collected real-time operation data are correlated and analyzed to generate fault early warning information. Based on the pollutant emission data in the multi-source heterogeneous data, the total emissions are calculated and an environmental supervision report is automatically generated. The control strategy is generated based on at least one of the combustion optimization strategy, the fault warning information, and the environmental regulatory report.

7. A control device for a 5G-based thermal power plant system, characterized in that, An edge computing gateway for use in a thermal power plant system, wherein the thermal power plant system is connected to a cloud platform via a 5G network; the device includes: The data acquisition module is used to collect multi-source heterogeneous data during the operation of thermal power plant systems. The matching module is used to match a target slice channel for each piece of data in the multi-source heterogeneous data based on the type of the data. An upload module is used to upload the data from the target slice channel to the cloud platform via the 5G network; The receiving module is used to receive the control strategy fed back by the cloud platform; The control module is used to control the operation of the thermal power plant system based on the control strategy; The multi-source heterogeneous data includes flue gas composition data from the separator outlet of the thermal power plant system, unit operation data from the DCS system, and pollutant emission data from the environmental monitoring system.

8. A control device for a 5G-based thermal power plant system, characterized in that, A cloud platform for use in thermal power plant systems, wherein the cloud platform is connected to an edge computing gateway deployed in the thermal power plant system via a 5G network; the device includes: The data receiving module is used to receive multi-source heterogeneous data uploaded by the edge computing gateway deployed locally in the thermal power plant via the 5G network; The data storage module is used to store real-time monitoring data from the multi-source heterogeneous data into a time-series database, and simultaneously store accident reports and operation logs from the multi-source heterogeneous data into a relational database. The data analysis module is used to call the intelligent analysis engine to process the multi-source heterogeneous data and generate control strategies; The policy feedback module is used to feed back the control policy to the edge computing gateway via the 5G network.

9. A control system for a 5G-based thermal power plant system, characterized in that, The system includes a data transmission layer, a 5G transmission layer, a cloud platform layer, and an application layer. The 5G transmission layer includes an edge computing gateway deployed locally at the thermal power plant. The edge computing gateway is connected to the cloud platform via a 5G network. The edge computing gateway is also connected to a data acquisition module in the thermal power plant system to perform the method as described in any one of claims 1-4. The cloud platform is used to perform the method as described in any one of claims 5-6.

10. The system according to claim 9, characterized in that, The cloud platform includes: The data warehouse module is used to store the received real-time monitoring data into a time-series database and to store accident reports and operation logs into a relational database. The intelligent analysis engine module is used to call the data in the data warehouse module to perform fusion analysis; The intelligent analysis engine module includes: The operation optimization unit is used to generate combustion optimization strategies based on unit operation data; The accident early warning unit is used to generate fault early warning information based on the correlation analysis of historical and real-time data; Environmental monitoring unit, used to generate environmental monitoring reports based on pollutant emission data; The intelligent decision support module is used to make comprehensive decisions based on at least one of the combustion optimization strategy, fault warning information and environmental regulatory reports output by the intelligent analysis engine module, and generate the control strategy.

Images