Thermal control equipment control system and thermal control equipment control method

Abstract

The invention discloses a thermal control equipment control system and a thermal control equipment control method. The thermal control equipment control system comprises a data acquisition module, a data analysis module and an equipment control module, the data acquisition module is used for acquiring operation data of thermal control equipment; the data analysis module is used for performing data analysis according to the operation data of the thermal control equipment to obtain operation parameters, predicted life and a fault repair scheme of the thermal control equipment; and the equipment control module is used for carrying out operation parameter adjustment and fault repair on the thermal control equipment. According to the thermal control equipment control system, all-directional remote control and management of the thermal control equipment can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to a control system for thermal control equipment and a control method for thermal control equipment. Background Art

[0002] As an important energy supply facility, thermal power plants play a core role in the power system. The operation management of thermal control equipment in traditional thermal power plants highly relies on manual operation and experience judgment, resulting in problems such as low efficiency and lagging fault handling. With the development of the Internet of Things technology, there is an urgent need for an intelligent, comprehensive, and complete control solution for thermal control equipment to achieve remote operation and maintenance management of thermal control equipment in thermal power plants. Summary of the Invention

[0003] The present invention provides a control system for thermal control equipment and a control method for thermal control equipment to achieve all-round remote control and management of thermal control equipment.

[0004] In a first aspect, an embodiment of the present invention provides a control system for thermal control equipment, which includes a data acquisition module, a data analysis module, and an equipment control module;

[0005] The data acquisition module is used to acquire the operation data of the thermal control equipment;

[0006] The data analysis module is used to perform data analysis based on the operation data of the thermal control equipment to obtain the operation parameters, predicted life, and fault repair solutions of the thermal control equipment;

[0007] The equipment control module is used to adjust the operation parameters and repair faults of the thermal control equipment.

[0008] In a second aspect, an embodiment of the present invention further provides a control method for thermal control equipment, which includes:

[0009] Determine the operation data of the thermal control equipment;

[0010] Based on the operation data of the thermal control equipment, determine the operation parameters of the thermal control equipment when the reward function is maximized through a reinforcement learning model;

[0011] Wherein, the reinforcement learning environment of the reinforcement learning model is the operation environment of the thermal control equipment, the state space is the operation data of the thermal control equipment, and the action space is the operation parameters of the thermal control equipment;

[0012] Based on the operation parameters of the thermal control equipment when the reward function is maximized, control the thermal control equipment to adjust the operation parameters.

[0013] In a third aspect, an embodiment of the present invention further provides a control method for thermal control equipment, which includes:

[0014] Determine the operation data of the thermal control equipment;

[0015] If it is determined that the operation data includes timing characteristics, input the operation data into the first equipment life prediction model to obtain the predicted life of the thermal control equipment output by the first equipment life prediction model;

[0016] Among them, the first equipment life prediction model includes a long short-term memory network module;

[0017] Otherwise, determine the time series characteristics of the operation data of the thermal control equipment through the long short-term memory network algorithm;

[0018] Input the time series characteristics of the operation data into the second equipment life prediction model to obtain the predicted life of the thermal control equipment output by the second equipment life prediction model;

[0019] Perform a fault warning on the thermal control equipment according to the predicted life of the thermal control equipment.

[0020] Fourthly, an embodiment of the present invention further provides a thermal control equipment control method, and this method includes:

[0021] Determine the current operation data, current structure data, and historical data of the thermal control equipment;

[0022] Through digital twin technology, based on the current operation data, current structure data, and historical data of the thermal control equipment, perform a state simulation of the thermal control equipment to obtain the simulated fault data of the thermal control equipment;

[0023] Based on the simulated fault data, determine a fault repair plan, and control the thermal control equipment to perform fault repair based on the fault repair plan.

[0024] The technical solution of the embodiment of the present invention, by setting a data acquisition module, a data analysis module, and an equipment control module in the thermal control equipment control system, collects the operation data of the thermal control equipment through the data acquisition module, performs data analysis on the operation data of the thermal control equipment through the data analysis module to obtain the operation parameters, predicted life, and fault repair plan of the thermal control equipment, and adjusts the operation parameters and performs fault repair on the thermal control equipment through the equipment control module. It realizes the optimization of the operation parameters, life prediction, and fault repair of the thermal control equipment, and realizes the full-range remote control and management of the thermal control equipment.

[0025] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. Description of the Drawings

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0027] Figure 1 It is a schematic structural diagram of a thermal control device control system provided in Embodiment 1 of the present invention;

[0028] Figure 2 It is a flowchart of a thermal control device control method provided in Embodiment 2 of the present invention;

[0029] Figure 3 It is a flowchart of another thermal control device control method provided in Embodiment 3 of the present invention;

[0030] Figure 4 It is a flowchart of yet another thermal control device control method provided in Embodiment 4 of the present invention. Detailed implementation manners

[0031] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device comprising a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices. In the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solutions of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0033] In the technical solution of this application, the acquisition, transmission, storage, use, processing, etc. of data all comply with the relevant provisions of national laws and regulations.

[0034] Embodiment 1

[0035] Figure 1 FIG. 1 is a schematic structural diagram of a thermal control equipment control system provided in Embodiment 1 of the present invention. The thermal control equipment control system is deployed in a thermal power plant management system. The thermal power plant management system adopts a hierarchical design based on the Internet of Things architecture, which is divided into a device layer, a network layer, a data layer, an application layer, and a user layer to achieve efficient data transmission and management from the underlying devices to the upper-layer applications.

[0036] Among them, the device layer includes various thermal control devices (such as sensors, controllers, actuators, etc.). Through intelligent sensors and communication modules, data collection and transmission of thermal control devices are realized. The communication module can include NB-IoT (Narrow Band Internet of Things), LoRa (Long Range Radio), 4G / 5G, etc. The multi-mode communication module can realize the ubiquitous interconnection of thermal control devices and support the access of heterogeneous devices.

[0037] The network layer is used for communication between the device layer and the data layer, supports multiple communication protocols (such as TCP (Transmission Control Protocol) / IP (Internet Protocol), MQTT (Message Queuing Telemetry Transport Protocol), CoAP (Constrained Application Protocol), etc.), supports low-bandwidth and high-reliability data transmission, and ensures the real-time performance and stability of data.

[0038] The data layer can further include a data acquisition server, a database management system, and a data processing module, which are used to store the operation data, historical data, and analysis results of thermal control devices, etc. The data processing module can preprocess the operation data of thermal control devices through edge computing technology to reduce the data transmission volume, reduce the load, and improve the real-time performance. The database management system adopts a data backup mechanism to regularly back up the operation data of thermal control devices, operation parameter optimization records, life prediction records, and fault repair records, etc., to ensure the integrity and recoverability of data.

[0039] The application layer includes the thermal control equipment control system in this embodiment, which provides functions such as operation parameter optimization, life prediction, and fault repair.

[0040] The user layer provides functions such as real-time display of the operating data of thermal control devices, an operation interface, and alarm prompts through a web-based or mobile application.

[0041] Through the deep integration of the hierarchical architecture and Internet of Things technology, the thermal power plant management system has greatly improved system compatibility and data transmission efficiency, and supports the dynamic access of a large number of thermal control devices. At the same time, through technologies such as firewalls, intrusion detection systems, and data encryption, the security of the Internet of Things architecture and the thermal control device control system is ensured, preventing data leakage and malicious attacks. In addition, the redundant design and distributed architecture of the thermal power plant management system can ensure that the system can still operate normally when some thermal control devices or network failures occur, improving the reliability and stability of the thermal power plant management system.

[0042] Such as Figure 1 As shown, the thermal control device control system includes a data acquisition module, a data analysis module, and a device control module; the data acquisition module is used to acquire the operating data of thermal control devices; the data analysis module is used to perform data analysis based on the operating data of thermal control devices to obtain the operating parameters, predicted life, and fault repair solutions of thermal control devices; the device control module is used to adjust the operating parameters and repair faults of thermal control devices.

[0043] Among them, the operating data of thermal control devices may include vibration data, temperature data, current data, pressure data, etc. of thermal control devices. This embodiment does not limit the type and specific content of the operating data.

[0044] The operating parameter refers to the parameter that needs to be optimized for thermal control devices. Exemplarily, taking the thermal control device as a boiler, the operating parameter may be the opening degree of the burner damper. It can be understood that by adjusting the operating parameters, the real-time operating data of thermal control devices will be affected.

[0045] The predicted life can be represented by the attenuation trend of the life of thermal control devices over time. Based on the predicted life, possible faults of thermal control devices can be predicted in advance, realizing preventive maintenance of thermal control devices and reducing the downtime of thermal control devices.

[0046] The fault repair solution is usually generated when a thermal control device fails or when the probability of a predicted fault of a thermal control device is relatively high (greater than a pre-set probability threshold), and may include the type, location, severity level of the fault (or predicted fault) of the thermal control device, the object to be adjusted (thermal control device, component, operating parameter, etc.).

[0047] The thermal control equipment control system in this embodiment provides multi-dimensional data analysis functions, including equipment operation parameter optimization, life prediction, and fault repair. Compared with the conventional thermal control equipment management system for data monitoring, collection, and display of thermal control equipment, it further expands the remote operation and maintenance management function and realizes the full-range intelligent control and management of thermal control equipment.

[0048] Furthermore, the data analysis module includes an equipment operation parameter determination unit;

[0049] The equipment operation parameter determination unit is used to determine the operation parameters of the thermal control equipment when the reward function is maximized based on the operation data of the thermal control equipment through a reinforcement learning model;

[0050] Among them, the reinforcement learning environment of the reinforcement learning model is the operation environment of the thermal control equipment, the state space is the operation data of the thermal control equipment, and the action space is the operation parameters of the thermal control equipment.

[0051] Reinforcement learning is a class of machine learning algorithms. An agent learns the optimal behavior strategy according to the reward signal feedback from the environment by interacting with the environment. The reinforcement learning algorithm adopted in this embodiment can be DQN (Deep Q–Network), PPO (Proximal Policy Optimization Algorithm), etc. This embodiment does not limit this.

[0052] The reinforcement learning model is an algorithm architecture for an agent to learn and make decisions. Its core goal is to find an optimal strategy by interacting with the environment so that the agent can obtain the maximum cumulative reward in the long term. The reinforcement learning environment is the external world where the agent is located. It contains various state information that the agent can perceive, as well as various results and feedback generated by the agent's actions. In this embodiment, the operation environment of the thermal control equipment is modeled as the reinforcement learning environment. The state space refers to the set of all possible states that the agent can be in the environment. In this embodiment, the operation data of the thermal control equipment is used as the state space. The action space is the set of all possible actions that the agent can take in each state. In this embodiment, the operation parameters of the thermal control equipment are used as the action space.

[0053] In a specific example, taking a thermal control device as a boiler, the operation data may include fuel flow rate, air volume, temperature, pressure, etc., and the operation parameter may be the adjustment amount of the burner damper opening. Further, through edge computing technology, the operation data can be preprocessed, including data cleaning, noise reduction, feature extraction, etc., to obtain a feature vector that can be used for optimization. The boiler operation environment is modeled as a reinforcement learning environment, where the state space is the boiler operation parameters and the action space is the adjustment amount of the burner damper opening. The reward function reflects the change in the boiler combustion efficiency. For example, the ratio of fuel consumption to heat production can be used as the reward function. A deep reinforcement learning algorithm is used to train the agent to learn to adjust the burner damper opening in different states to maximize the reward function. The trained agent predicts the optimal adjustment amount of the burner damper opening according to the current operation data.

[0054] The adaptive optimization algorithm based on reinforcement learning realizes the real-time optimization adjustment of the operation parameters of the thermal control device, thereby optimizing the operation of the thermal control device. Taking the above boiler as an example, the combustion efficiency is optimized, and the fuel consumption and pollutant emissions are reduced.

[0055] Further, the device control module includes an operation parameter adjustment unit;

[0056] The operation parameter adjustment unit is used to adjust the operation parameters of the thermal control device based on the operation parameters of the thermal control device determined by the device operation parameter determination unit;

[0057] Or, in response to the operation parameter adjustment instruction of the thermal control device sent by the user interface, the operation parameters of the thermal control device are adjusted.

[0058] In this embodiment, after analyzing and obtaining the optimal operation parameters of the thermal control device through the operation parameter adjustment unit in the data analysis module, the operation parameter adjustment unit in the device control module can be used to control the thermal control device to adjust the operation parameters, so as to realize the automatic and intelligent remote optimization control of the thermal control device.

[0059] In this embodiment, it also supports adjusting the operation parameters of the thermal control device through the user interface. Specifically, the operation and maintenance entity of the thermal control device selects the thermal control device and operation parameters to be adjusted through the window or button of the user interface, etc., so as to generate an operation parameter adjustment instruction for the thermal control device. After the operation parameter adjustment unit detects the operation parameter adjustment instruction of the thermal control device sent by the user interface, it performs automatic operation parameter adjustment.

[0060] Further, the data analysis module further includes a first device life prediction unit;

[0061] The first equipment life prediction unit is configured to determine the predicted life of the thermal control equipment based on the operation data of the thermal control equipment through the first equipment life prediction model;

[0062] Among them, the first equipment life prediction model includes a long short-term memory network module.

[0063] This embodiment provides two equipment life prediction methods. Among them, a long short-term memory (LSTM) module can be directly deployed in the first equipment life prediction model to perform time series analysis on the operation data of the thermal control equipment input to the first equipment life prediction model and predict the equipment life decay trend.

[0064] The advantage of this method is that it can make full use of the advantages of the LSTM model in time series analysis to capture the laws of changes in equipment operation parameters over time.

[0065] Furthermore, the data analysis module further includes a second equipment life prediction unit;

[0066] The second equipment life prediction unit is configured to determine the time series characteristics of the operation data of the thermal control equipment through the long short-term memory network algorithm;

[0067] Through the second equipment life prediction model, based on the time series characteristics of the operation data of the thermal control equipment, determine the predicted life of the thermal control equipment.

[0068] The time series characteristics may include the change trend of the operation data over time, the periodic change of the operation data over time, and the correlation between the operation data, etc.

[0069] In this embodiment, the long short-term memory network algorithm can also be used to perform time series analysis on the operation data of the thermal control equipment to obtain the time series characteristics of the operation data, and then input them into the second equipment life prediction model.

[0070] The advantage of this method is that taking the time series characteristics as input data into the fault prediction model can improve the accuracy of fault prediction. At the same time, it improves the generalization ability of the equipment life prediction model and can adapt to the fault prediction of different types of thermal control equipment.

[0071] In this embodiment, the first equipment life prediction model and the second equipment life prediction model can be set separately, and the corresponding equipment life prediction method can be selected according to specific application scenarios and requirements. Exemplarily, if the operation data contains obvious time series characteristics, the first equipment life prediction model is used for equipment life prediction. If the time series characteristics in the equipment operation data are not obvious, the second equipment life prediction model is used for equipment life prediction.

[0072] In this embodiment, real-time life trend prediction of thermal control equipment based on long short-term memory network can early warn of potential faults, quickly identify anomalies in thermal control equipment, reasonably arrange maintenance tasks, optimize the allocation of operation and maintenance resources, thereby reducing equipment downtime and maintenance costs.

[0073] Furthermore, the data analysis module further includes a fault repair plan determination unit;

[0074] The fault repair plan determination unit is used to perform state simulation of the thermal control equipment through digital twin technology based on the current operation data, current structure data, and historical data of the thermal control equipment, so as to obtain the simulated operation data, simulated structure data, and simulated fault data of the thermal control equipment;

[0075] Based on the simulated fault data, determine the fault repair plan.

[0076] Digital twin technology is a technology that uses digital means to accurately model and real-time map physical entities, and completes the mapping of physical entities in the virtual space, thereby reflecting the whole life cycle process of physical entities.

[0077] The current operation data of the thermal control equipment may include temperature, pressure, flow rate, vibration, current, and voltage, etc. The current structure data may include the size, material, shape, and structure of the thermal control equipment, etc. The historical data may include the historical operation data, maintenance records, fault records, etc. of the thermal control equipment within a preset time period.

[0078] The simulated operation data may include the change trend of the operation data of the thermal control equipment under different working conditions, such as the change trend of temperature, pressure, flow rate, etc. The simulated structure data may refer to the simulated structure change of the thermal control equipment, such as the wear and deformation of the thermal control equipment.

[0079] The simulated fault data may include abnormal operation data and / or abnormal structure data. By analyzing the simulated fault data, it is possible to determine the possible fault types, fault locations, and fault degrees of the simulated thermal control equipment, etc.

[0080] Determining the fault repair plan based on the simulated fault data can be achieved by combining an expert knowledge base and historical fault repair records, etc.

[0081] In this embodiment, based on the digital twin technology, on the one hand, when a thermal control device fails, it can simulate the failure phenomenon. Through the simulated operation data, simulated structure data, and simulated failure data of the thermal control device obtained by simulation, the failure type can be analyzed and determined, and then the failure repair plan can be further determined. On the other hand, based on the real-time operation data and real-time structure data of the thermal control device, it can judge the change trend of the simulated operation data and simulated structure data of the thermal control device, so as to conduct failure early warning, realize the pre-maintenance of the thermal control device, and improve the operation and maintenance efficiency.

[0082] In a specific example, taking the thermal control device as a boiler, through the digital twin technology, the operation states of the boiler under different working conditions are simulated, including the change trends of operation data such as temperature, pressure, and flow rate. On the one hand, when the boiler fails, the digital twin model can simulate the failure phenomenon and obtain simulated failure data, such as abnormal furnace temperature, abnormal flue gas flow rate, etc. By analyzing the simulated failure data, it can be determined that the failure type is furnace coking, and then the failure repair plan is determined to be cleaning the furnace, adjusting combustion parameters, etc.

[0083] In this embodiment, based on the digital twin technology, it effectively simulates the operation state of the thermal control device, conducts failure diagnosis and maintenance guidance, can quickly identify equipment abnormalities, take failure repair measures in time, extend the service life of the thermal control device, and ensure the safe and stable operation of the thermal power plant. It improves the operation and maintenance efficiency of the thermal control device and reduces the operation and maintenance cost.

[0084] Furthermore, the device control module includes a failure repair control unit;

[0085] The failure repair control unit is used to send the failure repair plan to the thermal control device, or control the failure repair object to adjust the operation parameters according to the failure repair plan, where the failure repair object can include the thermal control device, components, etc.

[0086] In this embodiment, if the failure repair plan is, for example, cleaning the furnace, the failure repair plan can be directly sent to the thermal control device to guide the repair at the failure site of the thermal control device. It can be in the form of video, voice, text instructions, etc., and this embodiment does not limit this. If the failure repair plan is the adjustment of operation parameters, it can be directly realized automatically by the failure repair control unit, improving the failure repair efficiency.

[0087] Furthermore, the failure repair plan determination unit is also used to determine the failure repair progress based on the simulated operation data and simulated structure data of the thermal control device.

[0088] In this embodiment, after the fault repair control unit sends the fault repair plan to the thermal control device, or during the process of controlling the fault repair object to adjust the operating parameters, the fault repair plan determination unit can also monitor the status of the thermal control device in real time, and through digital twin technology, obtain the simulated operation data and simulated structure data in real time, and track the progress of the device fault repair according to the simulated operation data and simulated structure data until the simulated operation data and simulated structure data return to the normal state (the values of the simulated operation data and simulated structure data are within the preset value range).

[0089] Further, the device control module further includes a firmware update control unit;

[0090] The firmware update control unit is used to control the thermal control device to update the controller firmware.

[0091] Through the firmware update control unit, remote software upgrade is realized, and the automation and intelligence of thermal control device management are improved.

[0092] Further, the thermal control device control system may further include an operation and maintenance task determination module;

[0093] The operation and maintenance task determination module is used to determine the operation and maintenance entity matching the thermal control device according to the predicted life of the thermal control device determined by the first device life prediction unit or the second device life prediction unit, and / or the simulated fault data determined by the fault repair plan determination unit, and generate an operation and maintenance task list matching the thermal control device.

[0094] Among them, the operation and maintenance task list may include the operation and maintenance entity, the operating parameters that need to be adjusted and optimized and match the thermal control device, etc.

[0095] Through the operation and maintenance task determination module, the automatic and reasonable arrangement of operation and maintenance resources is realized, the operation and maintenance processes of the thermal control device are optimized, and the operation and maintenance efficiency of the thermal control device is improved.

[0096] Further, the thermal control device control system may further include a carbon emission monitoring module;

[0097] The carbon emission monitoring module is used to calculate the carbon emission according to the thermal control device operation data.

[0098] Through the carbon emission monitoring module, the carbon quota management of the thermal power plant is realized, the comprehensive energy efficiency is improved, and the carbon emission is reduced.

[0099] Embodiment 2

[0100] Figure 2The flowchart of a thermal control equipment control method provided in the second embodiment of the present invention. The embodiments of the present invention can be applied to the situation of optimizing and adjusting the operation parameters of thermal control equipment in thermal power plant management. This method can be implemented through a thermal control equipment control device, which can be set in the form of software / hardware and deployed in the thermal control equipment control system in the application layer of the thermal power plant management system.

[0101] As Figure 2 shown, the method includes:

[0102] S210. Determine the operation data of the thermal control equipment;

[0103] S220. Based on the operation data of the thermal control equipment, determine the operation parameters of the thermal control equipment when the reward function is maximized through a reinforcement learning model;

[0104] Wherein, the reinforcement learning environment of the reinforcement learning model is the operation environment of the thermal control equipment, the state space is the operation data of the thermal control equipment, and the action space is the operation parameters of the thermal control equipment;

[0105] S230. Control the thermal control equipment to adjust the operation parameters based on the operation parameters of the thermal control equipment when the reward function is maximized.

[0106] The process of determining the optimal operation parameters of the thermal control equipment based on the reinforcement learning model and performing automatic operation parameter adjustment has been described in the above embodiments, and will not be repeated here.

[0107] In this embodiment, through the operation parameter adjustment mechanism based on reinforcement learning, the adaptive adjustment of the operation parameters of the thermal control equipment is realized, the operation of the thermal control equipment is optimized, and the operation efficiency of the thermal power plant is improved.

[0108] Embodiment Three

[0109] Figure 3 The flowchart of another thermal control equipment control method provided in the third embodiment of the present invention. The embodiments of the present invention can be applied to the situation of predicting the service life and fault warning of thermal control equipment in thermal power plant management. This method can be implemented through a thermal control equipment control device, which can be set in the form of software / hardware and deployed in the thermal control equipment control system in the application layer of the thermal power plant management system.

[0110] As Figure 3 shown, the method includes:

[0111] S310. Determine the operation data of the thermal control equipment.

[0112] S320. Judge whether the operation data includes time series characteristics. If so, execute S330; otherwise, execute S340.

[0113] S330. Input the operation data into the first equipment life prediction model to obtain the predicted life of the thermal control equipment output by the first equipment life prediction model.

[0114] Among them, the first equipment life prediction model includes a long short-term memory network module.

[0115] S340. Determine the time series characteristics of the operation data of the thermal control equipment through the long short-term memory network algorithm.

[0116] S350. Input the time series characteristics of the operation data into the second equipment life prediction model to obtain the predicted life of the thermal control equipment output by the second equipment life prediction model.

[0117] The specific process of selecting different life prediction methods according to whether the operation data includes time series characteristics has been described in the above embodiments, and will not be repeated here in this embodiment.

[0118] S360. Perform a fault warning on the thermal control equipment according to the predicted life of the thermal control equipment.

[0119] In this embodiment, a fault prediction is performed according to the decay trend of the predicted life of the thermal control equipment over time. Exemplarily, a decay trend curve of the predicted life over time can be determined. If it is determined that the current curvature of the decay trend curve is greater than or equal to a preset curvature threshold, a fault warning is performed. Or, if it is determined that the predicted life is less than or equal to a preset life threshold, a fault warning is performed.

[0120] The technical solution of this embodiment is based on the long short-term memory network algorithm to predict the life of the thermal control equipment, and performs a fault warning according to the predicted life, which can improve the accuracy of the thermal control equipment fault prediction, quickly identify potential faults, realize preventive maintenance of the thermal control equipment, reduce the time for repairing equipment shutdown faults, and thus improve the operation and maintenance efficiency of the thermal power plant.

[0121] Embodiment 4

[0122] Figure 4 The flowchart of another thermal control equipment control method provided by the fourth embodiment of the present invention. The fourth embodiment of the present invention can be applied to the situation of repairing thermal control equipment faults in thermal power plant management. This method can be implemented through a thermal control equipment control device, which can be set in the form of software / hardware and deployed in the thermal control equipment control system in the application layer of the thermal power plant management system.

[0123] As Figure 4 shown, this method includes:

[0124] S410. Determine the current operating data, current structural data, and historical data of the thermal control device.

[0125] S420. Through digital twin technology, based on the current operating data, current structural data, and historical data of the thermal control device, conduct a simulation of the thermal control device state to obtain the simulated fault data of the thermal control device.

[0126] S430. Based on the simulated fault data, determine a fault repair plan, and control the thermal control device to perform fault repair based on the fault repair plan.

[0127] The specific process of simulating the thermal control device state based on digital twin technology, determining a fault repair plan, and performing thermal control device fault repair has been described in the above embodiments, and will not be elaborated here in this embodiment.

[0128] The technical solution of this embodiment can simulate the state of the thermal control device in real time based on digital twin technology. According to the simulated operating state of the thermal control device, it can predict in advance the possible faults of the thermal control device, shortening the operation and maintenance response time; at the same time, when the thermal control device fails, it can simulate the fault state of the thermal control device, automatically determine the fault repair plan, generate an operation and maintenance task order, realize remote fault troubleshooting of the thermal control device, reduce manual intervention, and improve operation and maintenance efficiency.

[0129] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0130] The above specific implementation manners do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A thermal control equipment control system, characterized in that: It includes data acquisition module, data analysis module and equipment control module; The data acquisition module is used to collect the operating data of the thermal control equipment; The data analysis module is used to perform data analysis based on the operating data of the thermal control device to obtain the operating parameters, predicted life and fault repair plan of the thermal control device; The equipment control module is used to adjust operating parameters and repair faults of the thermal control equipment.

2. The method according to claim 1, characterized in that: The data analysis module includes an equipment operation parameter determination unit; The device operating parameter determination unit is used to determine the operating parameters of the thermal control device when the reward function is maximized based on the operating data of the thermal control device through a reinforcement learning model; Among them, the reinforcement learning environment of the reinforcement learning model is the operating environment of the thermal control device, the state space is the operating data of the thermal control device, and the action space is the operating parameters of the thermal control device.

3. The method according to claim 1, characterized in that The data analysis module also includes a first equipment life prediction unit; The first equipment life prediction unit is used to determine the predicted life of the thermal control device based on the operation data of the thermal control device through the first equipment life prediction model; Among them, the first equipment life prediction model includes a long short-term memory network module.

4. The method according to claim 1, characterized in that The data analysis module also includes a second equipment life prediction unit; The second equipment life prediction unit is used to determine the time series characteristics of the operation data of the thermal control equipment through a long short-term memory network algorithm; The predicted life of the thermal control device is determined by the second device life prediction model based on the time series characteristics of the operating data of the thermal control device.

5. The method according to claim 1, characterized in that: The data analysis module also includes a fault repair solution determination unit; The fault repair solution determination unit is used to simulate the state of the thermal control device based on the current operation data, current structure data and historical data of the thermal control device through the digital twin technology to obtain the simulated operation data, simulated structure data and simulated fault data of the thermal control device; Determine the fault repair plan based on the simulated fault data.

6. The method according to claim 5, characterized in that The fault repair scheme determination unit is further used to determine the fault repair progress based on the simulated operation data and simulated structure data of the thermal control device.

7. The method according to claim 2, characterized in that: The device control module includes an operating parameter adjustment unit; The operating parameter adjustment unit is used to adjust the operating parameters of the thermal control device based on the operating parameters of the thermal control device determined by the device operating parameter determination unit; Alternatively, in response to a thermal control device operating parameter adjustment instruction sent by a user interaction interface, the operating parameters of the thermal control device are adjusted.

8. A method for controlling a thermal control device, characterized in that: The method comprises: Determine the operating data of thermal control equipment; Through the reinforcement learning model, based on the operating data of the thermal control equipment, the operating parameters of the thermal control equipment when the reward function is maximized are determined; The reinforcement learning environment of the reinforcement learning model is the operating environment of the thermal control device, the state space is the operating data of the thermal control device, and the action space is the operating parameters of the thermal control device; Based on the operating parameters of the thermal control device when the reward function is maximized, the thermal control device is controlled to adjust the operating parameters.

9. A method for controlling a thermal control device, characterized in that: The method comprises: Determine the operating data of thermal control equipment; If it is determined that the operating data includes a time series feature, the operating data is input into a first equipment life prediction model to obtain a predicted life of the thermal control device output by the first equipment life prediction model; Wherein, the first equipment life prediction model includes a long short-term memory network module; Otherwise, the time series characteristics of the operation data of the thermal control equipment are determined through the long short-term memory network algorithm; Inputting the time series characteristics of the operation data into the second equipment life prediction model to obtain the predicted life of the thermal control equipment output by the second equipment life prediction model; Provide fault warning for thermal control equipment based on its predicted lifespan.

10. A method for controlling a thermal control device, characterized in that: The method comprises: Determine the current operating data, current structural data and historical data of the thermal control equipment; Through digital twin technology, the state of thermal control equipment is simulated based on the current operation data, current structure data and historical data of the thermal control equipment to obtain the simulated fault data of the thermal control equipment; Based on the simulated fault data, a fault repair plan is determined, and the thermal control equipment is controlled to perform fault repair based on the fault repair plan.

Images