Combustion control method of garbage incinerator, garbage incineration system and related equipment

Abstract

The embodiment of the invention provides a combustion control method of a garbage incinerator, a garbage incineration system and related equipment. The industrial brain open platform periodically obtains real-time operation data collected in real time in the combustion process of the garbage incinerator; inputting the real-time operation data into an operation parameter prediction model to predict predicted values of key operation parameters of the garbage incinerator in a future time period; inputting the real-time operation data and the predicted value of the key operation parameter into a reinforcement learning model to decide a target set value of the key operation parameter of the garbage incinerator in a future time period; the target set value of the key operation parameter is sent to a combustion control system; and the combustion control system carries out combustion control on the garbage incinerator in the future time period according to the target set values of the key operation parameters. Therefore, the industrial brain open platform can realize more flexible and effective combustion control by using the operation parameter prediction model and the reinforcement learning model, and the resource utilization rate, the environmental protection performance and the economic benefit of the garbage incinerator are improved.

Description

Technical Field

[0001] The present application relates to the technical field of waste incineration, and particularly to a combustion control method for a waste incinerator, a waste incineration system and related equipment. Background Art

[0002] A waste incinerator is a facility specifically designed to treat solid waste (usually municipal domestic waste) through high-temperature combustion. Its main function is to convert waste into ash and gas through the combustion process, thereby significantly reducing the volume of waste. And in many cases, it can recover the heat energy generated during the combustion process to generate electricity or heat, achieving the reuse of resources.

[0003] In practical applications, the combustion process of a waste incinerator is complex and affected by various factors, such as but not limited to: waste calorific value, pollutant emission indicators, furnace temperature of the waste incinerator, oxygen content or negative pressure in the flue gas, etc. These factors act together to determine the resource utilization rate, environmental friendliness and economic benefits of the incineration process. Especially during the waste incineration process, key operating parameters such as furnace temperature, oxygen content in the flue gas and negative pressure have a direct impact on the resource utilization rate, environmental protection performance and economic benefits of the waste incinerator. For example, an appropriate furnace temperature helps to improve the combustion efficiency and reduce the generation of harmful substances; a suitable oxygen content in the flue gas is the basis for ensuring complete combustion, which can reduce the emissions of unburned substances and carbon monoxide; and maintaining an appropriate negative pressure can prevent flue gas leakage, protecting the environment and the safety of operators.

[0004] However, in practical applications, the set values of these key operating parameters usually rely on manual adjustment by operators based on personal experience. This method is difficult to ensure that the waste incinerator is always in a better operating state, because manual adjustment may not be able to accurately respond to the changes in various complex working conditions, reducing the resource utilization rate, environmental protection performance and economic benefits of the waste incinerator. Summary of the Invention

[0005] Embodiments of the present application provide a combustion control method for a waste incinerator, a waste incineration system and related equipment, so as to improve the resource utilization rate, environmental protection performance and economic benefits of the waste incinerator.

[0006] An embodiment of this application provides a combustion control method for a waste incinerator, which is applied to an industrial brain open platform. The method includes: periodically obtaining real-time operation data collected in real time during the combustion process of the waste incinerator; inputting the real-time operation data into an operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in a future time period; inputting the real-time operation data and the predicted values of the key operation parameters into a reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in a future time period; and sending the target setting values of the key operation parameters to the combustion control system, so that the combustion control system performs combustion control on the waste incinerator in a future time period according to the target setting values of the key operation parameters.

[0007] An embodiment of this application also provides a waste incineration system, including: an industrial brain open platform, a combustion control system, and a waste incinerator; the industrial brain open platform is configured to periodically obtain the real-time operation data of the waste incinerator collected in real time during the combustion process of the waste incinerator; input the real-time operation data into an operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in a future time period; input the real-time operation data and the predicted values of the key operation parameters into a reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in a future time period; and send the target setting values of the key operation parameters to the combustion control system; the combustion control system is configured to perform combustion control on the waste incinerator in a future time period according to the target setting values of the key operation parameters.

[0008] An embodiment of this application also provides an electronic device, including: a memory and a processor; the memory is configured to store a computer program; the processor is coupled to the memory and is configured to execute the computer program to perform the steps in the combustion control method for the waste incinerator.

[0009] An embodiment of this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to be able to implement the steps in the combustion control method for the waste incinerator.

[0010] An embodiment of this application also provides a computer program product, including computer program / instructions, which, when executed by a processor, causes the processor to be able to implement the steps in the combustion control method for the waste incinerator.

[0011] The technical solution provided by the embodiment of the present application is that the Industrial Brain Open Platform periodically obtains the real-time operation data collected in real time during the combustion process of the waste incinerator; inputs the real-time operation data into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the future time period; inputs the real-time operation data and the predicted values of the key operation parameters into the reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in the future time period; sends the target setting values of the key operation parameters to the combustion control system; and the combustion control system performs combustion control on the waste incinerator in the future time period according to the target setting values of the key operation parameters. Thus, the Industrial Brain Open Platform can accurately and efficiently determine the target setting values of the key operation parameters of the waste incinerator in the future time period by using the operation parameter prediction model and the reinforcement learning model, can flexibly adapt to different working conditions, realize more flexible and effective combustion control, and improve the resource utilization rate, environmental protection performance and economic benefits of the waste incinerator. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings: Figure 1 is a schematic structural diagram of an exemplary waste incineration system provided by the embodiment of the present application; Figure 2 is a signaling interaction diagram of a combustion control method for a waste incinerator provided by the embodiment of the present application; Figure 3 is an exemplary application scenario diagram; Figure 4 is a schematic structural diagram of a combustion control device for a waste incinerator provided by the embodiment of the present application; Figure 5 is a schematic structural diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a 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 of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0014] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the access relationship between associated objects and represents three possible relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In the written description of the present application, the character " / " generally indicates an "or" relationship between the associated objects before and after. In addition, in the embodiments of the present application, "first", "second", "third", etc. are only used to distinguish the content of different objects and have no other special meaning.

[0015] It should be noted that in the case where the embodiments of the present application involve user information, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present application are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse. Additionally, various models (including but not limited to language models or large models) involved in the present application comply with relevant laws and standards.

[0016] The technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0017] Figure 1 It is a schematic structural diagram of an exemplary waste incineration system provided by an embodiment of the present application. Refer to Figure 1 This waste incineration system may include: an industrial brain open platform 10, a combustion control system 20, and a waste incinerator 30.

[0018] The industrial brain open platform is an intelligent system integrating multiple technologies such as big data processing, cloud computing, Internet of Things (IoT), and artificial intelligence (AI). Its purpose is to integrate and analyze data from various sources such as enterprise systems, factory equipment, sensor data, and personnel management data, and utilize advanced technologies such as voice interaction, image / video recognition, machine learning, and artificial intelligence algorithms to mine the value of the data. By activating the value of massive data, the industrial brain open platform provides enterprises with powerful data analysis capabilities and intelligent decision-making support, thereby accelerating the digital transformation and intelligent upgrading of the industrial field.

[0019] The combustion control system 20 is a control system that ensures the efficient, safe and environmentally friendly operation of the waste incinerator. It optimizes the combustion efficiency and reduces harmful emissions by precisely controlling various parameters during the incineration process, such as temperature, oxygen content, combustion rate, etc.

[0020] The waste incinerator 30 is a facility for treating solid waste, which converts waste into ash, waste gas and heat energy through high-temperature combustion. This treatment method can not only reduce the volume of waste, but also utilize the heat energy generated during the incineration process for power generation or heating, thus achieving the purpose of resource recovery and utilization.

[0021] In this embodiment, historical operation data collected during the combustion process of the waste incinerator 30 is used to train the operation parameter prediction model and the reinforcement learning model. In this way, the industrial brain open platform 10 can accurately determine the target setting values of the key operation parameters of the waste incinerator in the future time period by using the operation parameter prediction model and the reinforcement learning model.

[0022] To better understand the technical solution provided by the embodiments of the present application, the following is introduced in conjunction with Figure 2 the signaling interaction diagram shown. Figure 2 This is the signaling interaction diagram of a combustion control method for a waste incinerator provided by the embodiments of the present application. Refer to Figure 2 and the method may include the following steps: 201. The industrial brain open platform periodically obtains the real-time operation data collected in real time during the combustion process of the waste incinerator.

[0023] Specifically, as shown in ① of Figure 1 , the industrial brain open platform periodically obtains the real-time operation data collected in real time during the combustion process of the waste incinerator. In practical applications, the industrial brain open platform can periodically obtain the real-time operation data collected in real time during the combustion process of the waste incinerator at set time intervals (such as 1 minute, 5 minutes, one hour, etc.).

[0024] In this embodiment, the real-time operation data refers to the operation data collected in real time during the combustion process of the waste incinerator. The real-time operation data can be various operation data, and there is no limitation on this. Further, in order to accurately determine the target setting values of the key operation parameters of the waste incinerator in the future time period, the real-time operation data includes at least one of the following: the number of pusher operations of the pusher in the recent time period, the grate action cycle, the number of grate actions, the working frequency of the primary air blower, the working frequency of the secondary air blower, the working frequency of the induced draft fan, the primary air volume, the secondary air volume, the flue gas flow rate, the flue gas temperature, the desuperheating water flow rate, the air chamber wind pressure, the steam flow rate, the steam temperature, the furnace temperature, the furnace negative pressure, the oxygen content in the flue gas, the environmental protection index data, and the key operation data of the waste storage system; the key operation data of the waste storage system includes: the coordinate position, weight, and waste fermentation time of the waste crane.

[0025] In this embodiment, the recent time period can be the time period closest to the current time. For example, the past minute, the past hour, etc., can be flexibly set as needed. The real-time performance of the real-time operation data in the recent time period is better and can reflect the current working condition of the waste incinerator.

[0026] Among them, the number of pusher operations of the pusher: refers to the number of actions of the pusher pushing the waste from the feed inlet into the waste incinerator for combustion during the waste incineration process. This parameter is an important indicator for measuring the rate of waste entering the incinerator and is very crucial for controlling the stability and efficiency of the incineration process.

[0027] The grate action cycle: refers to the time required for a complete process of the mechanical movement of the grate. This cycle can include multiple stages such as feeding, drying, combustion, burnout, and ash discharge.

[0028] The number of grate actions: refers to the number of operations of the grate within a specific time period. This parameter is very important for controlling the combustion process because it directly affects the fuel supply rate, combustion efficiency, and ash removal efficiency, etc.

[0029] The main function of the primary air blower is to provide the necessary oxygen for the combustion process to ensure that the fuel can burn fully. Usually, the working frequency of the primary air blower may vary within a relatively large range, such as from 30 Hz to 50 Hz or a wider range.

[0030] The main function of the secondary air blower is to provide excess air in the waste incinerator to ensure that there is sufficient oxygen in the combustion zone to completely burn the combustible gas and achieve a more thorough combustion process. This helps to improve the combustion efficiency and reduce the emission of harmful substances, such as carbon monoxide and unburned hydrocarbons. Usually, the working frequency range of the secondary air blower can be set within a relatively large interval, such as from 30 Hz to 50 Hz or higher.

[0031] The main function of the induced draft fan is to maintain an appropriate negative pressure in the waste incinerator, prevent flue gas leakage, and ensure the gas flow in the combustion chamber. Under normal circumstances, the operating frequency of the induced draft fan can vary within a relatively wide range, for example, from 20 Hz to 50 Hz or higher.

[0032] The primary air volume refers to the amount of air supplied by the primary air fan to the combustion chamber of the waste incinerator, which is mainly used to support the initial combustion process of the waste and ensure that the fuel (i.e., the waste) can burn fully. The supply of primary air is crucial for maintaining a stable combustion temperature, improving combustion efficiency, and reducing harmful emissions.

[0033] The secondary air volume refers to the amount of air additionally supplied to the combustion chamber during the waste incineration process to promote complete combustion. Different from the primary air, which is mainly used to support the initial combustion of the waste, the main function of the secondary air is to provide sufficient oxygen to ensure that combustible gases and fine particulate matter can burn fully in the high-temperature zone, thereby improving combustion efficiency and reducing harmful emissions such as carbon monoxide (CO), unburned hydrocarbons (HC), and fine particulate matter.

[0034] The flue gas flow rate refers to the flow velocity and total amount of the flue gas generated by combustion passing through equipment such as the incinerator, waste heat boiler, and flue gas purification system during the waste incineration process. Monitoring and controlling the flue gas flow rate is crucial for ensuring the stable operation of the incineration system, improving combustion efficiency, and meeting environmental protection emission standards.

[0035] The flue gas temperature refers to the temperature of the exhaust gas (i.e., the flue gas) generated after the combustion of fuels such as waste, coal, and natural gas during the combustion process. The flue gas temperature is a key operating parameter, which reflects the efficiency and state of the combustion process and has an important impact on subsequent heat energy recovery and pollutant control.

[0036] The desuperheating water flow rate refers to the amount of water sprayed in to regulate and control the temperature of the flue gas or steam, with the aim of reducing the temperature of the medium (such as superheated steam or high-temperature flue gas) directly or indirectly to protect downstream equipment from excessive temperature and optimize the overall efficiency of the system.

[0037] The air chamber air pressure refers to the pressure inside the air chamber (i.e., the cavity used to distribute the primary air or secondary air) in the waste incinerator. This pressure is crucial for ensuring that the air can be evenly and effectively distributed to the combustion area, and it directly affects the combustion efficiency, the degree of complete combustion of the fuel, and the amount of pollutants generated.

[0038] The steam flow rate refers to the amount of steam generated by the waste incinerator, and the steam flow rate is usually expressed in terms of mass flow rate (such as kilograms per hour or tons per hour) or volume flow rate (such as cubic meters per hour).

[0039] The steam temperature refers to the temperature of the steam generated by the waste incinerator. A higher steam temperature usually means a higher heat energy content, which can improve the power generation efficiency.

[0040] The furnace temperature refers to the temperature inside the combustion chamber (i.e., the furnace) in the waste incinerator. It is the temperature reached by the air and combustion products (flue gas) in the furnace due to the heat released during the fuel combustion process. The furnace temperature is one of the important parameters for measuring the efficiency and safety of the combustion process.

[0041] The furnace negative pressure refers to a slightly negative pressure state inside the furnace of the waste incinerator relative to the external atmospheric pressure. The main purpose is to ensure that the flue gas generated during the combustion process can flow along the predetermined path and prevent the flue gas from leaking into the surrounding environment, causing pollution and safety hazards.

[0042] The oxygen content in the flue gas refers to the oxygen content in the flue gas during the combustion process. It is one of the key factors indicating whether the fuel is fully burned.

[0043] The environmental protection index data refers to the specific values obtained by monitoring various pollutants emitted into the atmosphere during the process of waste incineration, such as, for example, but not limited to, the emission concentrations of pollutants such as particulate matter, sulfur dioxide, nitrogen oxides, and dioxins.

[0044] The coordinate position of the waste crane can refer to representing the spatial position of the waste crane, usually recorded in the form of three-dimensional coordinates (X, Y, Z); the weight of the waste crane can reflect the actual weight of the waste grabbed by the waste crane each time; the fermentation time can reflect the time from when the waste enters the waste storage to when it is put into the incinerator, usually measured in hours or days.

[0045] 202. The industrial brain open platform inputs the real-time operation data into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the future time period.

[0046] Specifically, after the industrial brain open platform obtains the real-time operation data, it inputs the real-time operation data into the operation parameter prediction model. As shown in ② of Figure 1 , the operation parameter prediction model predicts the predicted values of the key operation parameters of the waste incinerator in the future time period according to the real-time operation data. The duration of the future time period is not limited, such as the next 5 minutes, the next 10 minutes, the next 30 minutes, and so on.

[0047] In this embodiment, the key operation parameters refer to the important indicators that have a direct impact on the combustion efficiency, resource utilization rate, environmental protection emissions, and economic benefits of the waste incinerator. Preferably, the key operation parameters include, for example, but not limited to: furnace temperature, furnace negative pressure, oxygen content in the flue gas, steam flow rate, or steam temperature.

[0048] For example, assume that the current time is 10:34 on April 18, 2025, and the key operating parameters for the next 10 minutes (from 10:34 to 10:44) need to be predicted. First, collect relevant real-time operating data. Second, perform data preprocessing on the real-time operating data, such as including but not limited to steps like outlier removal, missing value filling, data cleaning, etc., to ensure data quality. Third, input the real-time operating data after data preprocessing into the operating parameter prediction model for prediction processing to obtain the predicted values of the key operating parameters in the next 10 minutes. For example, the current furnace temperature is 975°C, and the operating parameter prediction model predicts that the furnace temperature will fluctuate between 970°C and 980°C in the next 10 minutes. The current oxygen content in the flue gas is 6%, and the operating parameter prediction model predicts that the oxygen content in the flue gas will remain between 5.8% and 6.2% in the next 5 minutes to adapt to the change in combustion load. The current steam flow rate is 20 tons per hour, and the operating parameter prediction model predicts that the steam flow rate will slightly increase to about 20.5 tons per hour in the next 10 minutes, which may be due to the improvement of combustion efficiency.

[0049] 203. The industrial brain open platform inputs the real-time operating data and the predicted values of the key operating parameters into the reinforcement learning model to determine the target setting values of the key operating parameters of the waste incinerator in the future time period.

[0050] Reinforcement Learning (RL) is a learning method based on the "trial and error" mechanism, which learns better strategies by interacting with the environment. By outputting the target setting values of the key operating parameters of the waste incinerator through the reinforcement learning model, the intelligent level and operating efficiency of the waste combustion system can be significantly improved, providing technical support for the green and low-carbon development in the field of waste incineration. The reinforcement learning model can dynamically adjust strategies according to environmental changes, adapt to different working conditions, and achieve more flexible and effective combustion control. The reinforcement learning model determines the optimal action to be taken based on the current state (i.e.,), and the current state is also the real-time operating data and the predicted values of the key operating parameters, and the optimal action taken is also to determine the target setting values of the key operating parameters of the waste incinerator in the future time period.

[0051] In this embodiment, the industrial brain open platform inputs the real-time operating data and the predicted values of the key operating parameters of the waste incinerator in the future time period predicted by the operating parameter prediction model into the reinforcement learning model. See Figure 1As shown in ③ in [reference], the reinforcement learning model outputs the target setting values of the key operating parameters of the waste incinerator in the future time period. The target setting value can be understood as the ideal value that the key operating parameters of the waste incinerator need to reach within a certain future time period. For example, the target setting value of the furnace temperature is 970 °C; the target setting value of the flue gas oxygen content: 6%; the target setting value of the steam flow rate: 21 tons per hour. The target setting value of the furnace negative pressure: -30 Pa.

[0052] 204. The industrial brain open platform sends the target setting values of the key operating parameters to the combustion control system.

[0053] 205. The combustion control system conducts combustion control on the waste incinerator according to the target setting values of the key operating parameters in the future time period.

[0054] See Figure 1 As shown in ③ and ④ in [reference], the industrial brain open platform sends the target setting values of the key operating parameters to the combustion control system, and the combustion control system conducts combustion control on the waste incinerator according to the target setting values of the key operating parameters in the future time period to optimize the combustion process, improve the combustion efficiency, increase the resource utilization rate, and reduce pollution emissions. For example, in order to reach a furnace temperature of 970 °C, the combustion control system may need to increase the fuel supply rate. This can be achieved by adjusting the speed of the feeder to ensure that more fuel enters the furnace to provide the required heat. Another example, in order to maintain a flue gas oxygen content of 6%, the combustion control system needs to finely adjust the primary air fan and the secondary air fan to control the ratio and flow rate of the primary air and the secondary air. Another example, in order to achieve a steam flow rate of 21 tons per hour, the combustion control system adjusts the boiler water level and the water supply volume to ensure that enough water is converted into steam. Adjust the combustion intensity according to the actual demand, thereby affecting the steam output. Another example, in order to maintain an ideal furnace negative pressure of -30 Pa, the combustion control system needs to adjust the frequency of the induced draft fan. If the monitored actual negative pressure is higher than -30 Pa, then reduce the operating frequency of the induced draft fan; otherwise, increase the operating frequency.

[0055] In practical applications, the combustion control system continuously monitors the real values of the key operating parameters, compares them with the target setting values, and conducts real-time optimization of the waste incinerator system according to the comparison results to ensure that the waste incinerator system always operates in a better state.

[0056] In the technical solution provided by the embodiments of the present application, the Industrial Brain Open Platform periodically obtains the real-time operation data collected in real time during the combustion process of the waste incinerator; inputs the real-time operation data into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the future time period; inputs the real-time operation data and the predicted values of the key operation parameters into the reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in the future time period; sends the target setting values of the key operation parameters to the combustion control system; and the combustion control system performs combustion control on the waste incinerator in the future time period according to the target setting values of the key operation parameters. Thus, the Industrial Brain Open Platform can accurately and efficiently determine the target setting values of the key operation parameters of the waste incinerator in the future time period by using the operation parameter prediction model and the reinforcement learning model, can flexibly adapt to different working conditions, realize more flexible and effective combustion control, and improve the resource utilization rate, environmental protection performance and economic benefits of the waste incinerator.

[0057] In practical applications, there is no limitation on the model structure of the operation parameter prediction model. The model structure of the operation parameter prediction model includes, for example, but is not limited to: ARIMA (AutoRegressive Integrated Moving Average), SARIMA (Seasonal AutoRegressive Integrated Moving Average), LSTM (Long Short-Term Memory), etc.

[0058] In practical applications, there is no limitation on the training method of the operation parameter prediction model, for example, including but not limited to: supervised learning, unsupervised learning, and semi-supervised learning, etc.

[0059] Furthermore, in order to improve the prediction accuracy of the operation parameter prediction model, the training method of the operation parameter prediction model includes: obtaining the historical operation data of multiple different first time periods collected during the combustion process of the waste incinerator; constructing a first training data set and a first test data set according to the historical operation data of multiple different first time periods; aiming at predicting the predicted values of the key operation parameters of the waste incinerator in the second time period, using the first training data set to perform model training to obtain an initial operation parameter prediction model, where the second time period is later than the first time period; and using the first test data set to perform parameter adjustment processing on the operation parameter prediction model to obtain the operation parameter prediction model.

[0060] Specifically, the first time period is a past time period, and the second time period is later than the first time period. Relatively speaking, the second time period is the future time period corresponding to the first time period. The historical operation data can be understood as the operation data collected during the combustion process of the waste incinerator in the past time period. In the training dataset preparation stage, historical operation data of multiple different first time periods can be selected to cover different operating conditions, thereby enhancing the generalization ability of the model. Data preprocessing can also be performed on the collected historical operation data, such as removing outliers, filling in missing values, standardizing or normalizing, etc., to improve the data quality.

[0061] In this embodiment, the collected historical operation data is divided into a training dataset and a test dataset. For ease of understanding and distinction, the training dataset for training the operation parameter prediction model is hereinafter referred to as the first training dataset, and the test dataset for testing the operation parameter prediction model is hereinafter referred to as the first test dataset. In practical applications, there are no restrictions on the method of dividing the training dataset and the test dataset. In practical applications, it can be divided according to a division ratio. For example, 70%-80% of the historical operation data is used for training, and 20%-30% of the historical operation data is used for testing. Or, it can be divided in chronological order. The operation data of the waste incinerator is usually time series data and has time dependence (that is, the data at the current moment is related to the data at the previous moment). For example, the historical operation data is sorted by time. The historical operation data in the earlier time period is used as the first training dataset, and the historical operation data in the later time period is used as the first test dataset. For example, assuming there is data for the past year (from January 1, 2024 to December 31, 2024), the historical operation data for the first 9 months (from January 1, 2024 to September 30, 2024) can be used as the first training dataset, and the historical operation data for the last 3 months (from October 1, 2024 to December 31, 2024) can be used as the first test dataset.

[0062] In this embodiment, by combining the first training dataset and the first test dataset for model training, it can be ensured that the model can perform well on unseen data while avoiding the problems of overfitting or underfitting. First, use the first training dataset for model training to obtain an initial operating parameter prediction model; then, use the first test dataset to perform parameter adjustment on the operating parameter prediction model to obtain the final operating parameter prediction model. In practical applications, the first test dataset is mainly used to fine-tune the model parameters to make the operating parameter prediction model perform better on unseen data. For example, use the first test dataset to evaluate the model performance, such as calculating evaluation metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Coefficient of Determination (R²), etc. Fine-tune hyperparameters such as learning rate, batch size, number of layers, etc. according to the evaluation metrics to optimize the operating parameter prediction model.

[0063] In some alternative embodiments, the operating parameter prediction models for different operating modes can be trained. Different operating modes include: high-yield mode (maximizing steam volume), load-priority mode (prioritizing the control of steam stability), furnace temperature-priority mode (prioritizing the control of furnace temperature stability), environmental protection index control-priority mode, and some special system operation operations such as steam soot blowing, etc. Different operating modes will affect the change characteristics of the operating parameters. The main objective of the high-yield mode is to increase the steam production as much as possible. The main objective of the load-priority mode is to maintain the stability and reliability of the steam supply. The main objective of the furnace temperature-priority mode is to maintain the stability of the furnace temperature. The main objective of the environmental protection index control-priority mode is to further reduce pollutant emissions while meeting environmental regulations and standards, such as meeting more stringent internal control standards.

[0064] In practical applications, the first training dataset and the first test dataset associated with each operating mode index can be collected; use the first training dataset and the first test dataset associated with each operating mode for model training to obtain the operating parameter prediction models applicable to each operating mode; combine the operating parameter prediction models applicable to each operating mode to obtain the final operating parameter prediction model.

[0065] In some alternative embodiments, the implementation of inputting the real-time operation data into an operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in a future time period is as follows: input the real-time operation data into the operation parameter prediction model, so that the operation parameter prediction model predicts the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes; according to the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes, obtain the predicted values of the key operation parameters of the waste incinerator in the future time period.

[0066] In practical applications, the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes can be averaged or weighted and summed to obtain the predicted values of the key operation parameters of the waste incinerator in the future time period.

[0067] Furthermore, in order to accurately predict the predicted values of the key operation parameters, the implementation of obtaining the predicted values of the key operation parameters of the waste incinerator in the future time period according to the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes is as follows: perform weighted summation on the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes to obtain the intermediate predicted values of the key operation parameters of the waste incinerator in the future time period; with the goal of meeting the technological requirements of the combustion process, correct the intermediate predicted values of the key operation parameters of the waste incinerator in the future time period to obtain the predicted values of the key operation parameters of the waste incinerator in the future time period.

[0068] In practical applications, weighted calculation based on multiple objectives (multiple operation modes) is supported. Relevant personnel can set the weight information corresponding to each operation mode according to actual needs. By assigning weights to these different operation modes, the importance of each operation mode can be flexibly adjusted according to actual needs.

[0069] In practical applications, the technological requirements of the combustion process can restrict the numerical ranges of various operation parameters. For example, the temperature range of the furnace temperature; the pressure ranges corresponding to the air chamber air pressure, furnace negative pressure, etc.; the intervals corresponding to the emission values of various pollutants, etc. Correcting the prediction results with the goal of meeting the technological requirements of the combustion process can ensure the safe, environmentally friendly and efficient operation of the waste incineration process.

[0070] In this embodiment, the training method of the reinforcement learning model is not limited. For example, the reinforcement learning model is offline trained based on historical operation data. For another example, after offline training the reinforcement learning model based on historical operation data, the reinforcement learning model can also be updated in real time through an online learning method.

[0071] Further, to improve the model performance of the reinforcement learning model, the training method of the reinforcement learning model includes: obtaining historical operation data of multiple different third time periods collected during the combustion process of the waste incinerator; for any third time period, inputting the historical operation data of the third time period into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the fourth time period, where the fourth time period is later than the third time period; constructing a second training data set and a second test data set based on the historical operation data of multiple different third time periods and the predicted values of the key operation parameters in multiple fourth time periods; using the second training data set for model training with the goal of determining the target setting values of the key operation parameters of the waste incinerator in the fourth time period to obtain an initial reinforcement learning model; and performing parameter adjustment processing on the initial reinforcement learning model using the second test data set to obtain the reinforcement learning model.

[0072] Specifically, the third time period is a past time period, and the fourth time period is later than the third time period. Relatively speaking, the fourth time period is the future time period corresponding to the third time period. In the training data set preparation stage, historical operation data of multiple different third time periods can be selected to cover different operating conditions, thereby enhancing the generalization ability of the model. Data preprocessing can also be performed on the collected historical operation data, such as removing outliers, filling in missing values, standardizing or normalizing, etc., to improve the data quality. The collected historical operation data is divided into a training data set and a test data set. For the sake of easy understanding and distinction, the training data set for training the reinforcement learning model is referred to as the second training data set here, and the test data set for testing the reinforcement learning model is referred to as the second test data set.

[0073] In this embodiment, combining the second training data set and the second test data set for model training can ensure that the model performs well on unseen data and avoid problems of overfitting or underfitting. First, use the second training data set for model training to obtain an initial reinforcement learning model; perform parameter adjustment processing on the initial reinforcement learning model using the second test data set to obtain the reinforcement learning model. In practical applications, the second test data set is mainly used to fine-tune the model parameters to make the reinforcement learning model perform better on unseen data. For example, use the second test data set to evaluate the model performance, such as determining evaluation metrics such as the weighted reward function value over a period of time. The weighted reward function value is obtained by weighted summing the reward values of the reward function over a period of time; fine-tune hyperparameters such as the learning rate, batch size, and number of layers according to the evaluation metrics to optimize the reinforcement learning model.

[0074] Further, in order to improve the model performance of the reinforcement learning model and enable the reinforcement learning model to better dynamically optimize the key operating parameters of the waste incinerator. The second training dataset includes multiple current state data, and the current state data includes: historical operating data in the third time period and predicted values of the key operating parameters in the fourth time period; correspondingly, the implementation method of training the model using the second training dataset to obtain the initial reinforcement learning model is: input the current state data into the initial reinforcement learning model, and obtain the set value of the key operating parameters of the waste incinerator determined by the reinforcement learning model in the fourth time period; send the set value of the key operating parameters in the fourth time period to the combustion control system, so that the combustion control system performs combustion control on the waste incinerator according to the set value of the key operating parameters in the fourth time period; after performing combustion control based on the current state data, use the reward function to determine the reward value, and adjust the model parameters of the initial reinforcement learning model according to the reward value; repeat the above steps until the required initial reinforcement learning model is obtained.

[0075] In practical applications, a suitable reward function is designed to evaluate the effect of making action decisions based on the current state, encourage beneficial behaviors, and punish bad behaviors. Preferably, the reward function can be designed according to the following various factors: ① Improving combustion efficiency: increasing the reward value; ② Reducing pollutant emissions: increasing the reward value. ③ Exceeding safety limits (such as too high temperature or abnormal pressure): reducing the reward value; ③ Increasing the grid-connected power generation per ton of waste: increasing the reward value; ④ Reducing the grid-connected power generation per ton of waste: reducing the reward value; ⑤ Improving the index values of other key indicators: increasing the reward value; ⑥ Reducing the index values of other key indicators: reducing the reward value. Among them, the grid-connected power generation per ton of waste can be converted based on the steam volume used for power generation, the fan power, and the waste feeding volume. The grid-connected power generation per ton of waste can reflect the grid-connected power generation that can be generated by incinerating each ton of incoming waste. For example, A = B×C×D / 3600; E = A - F*T; N = E / M; where A represents the total power generation; B represents the steam volume; C represents the enthalpy difference; D represents the steam turbine efficiency; E represents the grid-connected power generation; F represents the fan power; T represents the operating time of the fan; N represents the grid-connected power generation per ton of waste; M represents the waste feeding volume. Of course, the determination method of the grid-connected power generation per ton of waste can be flexibly set as required. Other key indicators include, for example, but are not limited to: the steam volume generated per unit of waste (tons / ton) that measures the waste heat conversion efficiency; the fan power consumed per unit of waste (kW / ton) that reflects the energy consumption efficiency of air supply; the electrical energy output per unit of steam production (degrees / ton) that evaluates the power generation efficiency, etc.

[0076] In reinforcement learning, adjusting model parameters according to the reward value is a core step in model training and optimization. This process updates the model's policy or value function, enabling the model to gradually learn to take optimal actions in different states, thereby maximizing the long-term cumulative reward. In practical applications, appropriate optimization algorithms (such as gradient descent, policy gradient, etc.) can be used to adjust the model parameters based on the reward value.

[0077] By adjusting the model parameters of the reinforcement learning model according to the reward value, the model can gradually learn to make better decisions in complex industrial environments. In the scenario of a waste incinerator, this adjustment process can help optimize the target setting values of key operating parameters, thereby achieving higher combustion efficiency, lower pollutant emissions, and better economic benefits.

[0078] It should be noted that in practical applications, the initial reinforcement learning model obtained by only using the second training dataset for model training can also be used as the final reinforcement learning model for predicting the target setting values of key operating parameters, and there is no restriction on this.

[0079] To better understand the technical solution of this application, the following will be introduced in combination with Figure 3 the application scenario diagram shown. Refer to Figure 3 , the entire combustion control process can include the following steps: S1. Perform data preprocessing on the collected industrial data. Industrial data refers to the historical data collected at the industrial site, and the historical data can include the historical operating data corresponding to the waste incinerator. Data preprocessing includes, for example, but is not limited to: removing outliers, filling in missing values, standardization or normalization processing, etc.

[0080] S2. Model training of the operating parameter prediction model. Use the historical operating data to construct a data-driven AI (Artificial Intelligence) model (i.e., the operating parameter prediction model).

[0081] S3. Model training of the reinforcement learning model. The reinforcement learning model can be offline trained using the historical operating data.

[0082] S4. Model release. After the model is released, the industrial brain open platform can use the model for inference.

[0083] S5. The Industrial Brain Open Platform performs online optimization. First, the Industrial Brain Open Platform conducts online prediction of operating parameters. That is, the Industrial Brain Open Platform inputs real-time operating data into the operating parameter prediction model to predict the predicted values of the key operating parameters of the waste incinerator in the future time period. Then, the Industrial Brain Open Platform inputs the real-time operating data and the predicted values of the key operating parameters into the reinforcement learning model to determine the target setting values of the key operating parameters of the waste incinerator in the future time period. Finally, the Industrial Brain Open Platform sends the target setting values of the key operating parameters to the combustion control system. In this way, the combustion control system conducts combustion control on the waste incinerator according to the target setting values of the key operating parameters in the future time period.

[0084] Due to the complex physical and chemical processes, external disturbances, and the interaction between system internal variables in the waste incineration process, it is difficult for traditional mechanism model-based methods to achieve efficient real-time optimization. The technical solution provided in the embodiments of this application combines an operating parameter prediction model and a reinforcement learning model to achieve real-time intelligent decision-making of key operating parameters during the operation of the waste incinerator based on real-time operating data, effectively reducing the labor intensity of operators, realizing personnel streamlining, being able to more flexibly adapt to different operating conditions, improving the overall operating efficiency, increasing the power generation per ton of waste, and the overall economic benefits.

[0085] Figure 4 It is a structural schematic diagram of a combustion control device for a waste incinerator provided in the embodiments of this application. This device can be composed of hardware and / or software and is generally integrated in the Industrial Brain Open Platform. Refer to Figure 4 and this device may include: An acquisition module 41, configured to periodically acquire real-time operating data collected in real time during the combustion process of the waste incinerator; An operating parameter prediction module 42, configured to input the real-time operating data into the operating parameter prediction model to predict the predicted values of the key operating parameters of the waste incinerator in the future time period; A reinforcement learning module 43, configured to input the real-time operating data and the predicted values of the key operating parameters into the reinforcement learning model to determine the target setting values of the key operating parameters of the waste incinerator in the future time period; A sending module 44, configured to send the target setting values of the key operating parameters to the combustion control system, so that the combustion control system conducts combustion control on the waste incinerator according to the target setting values of the key operating parameters in the future time period.

[0086] Optionally, the real-time operation data includes at least one of the following: the number of material pushing operations of the pusher within a recent time period, the grate action cycle, the number of grate actions, the operating frequency of the primary air fan, the operating frequency of the secondary air fan, the operating frequency of the induced draft fan, the primary air volume, the secondary air volume, the flue gas flow rate, the flue gas temperature, the desuperheating water flow rate, the air chamber wind pressure, the steam flow rate, the steam temperature, the furnace temperature, the furnace negative pressure, the flue gas oxygen content, the environmental protection index data, and the key operation data of the waste storage system; the key operation data of the waste storage system includes: the coordinate position, weight, fermentation time, etc. of the waste crane.

[0087] Optionally, the key operation parameters include at least one of the following: furnace temperature, furnace negative pressure, flue gas oxygen content, steam flow rate, or steam temperature.

[0088] Optionally, the training method of the operation parameter prediction model includes: obtaining historical operation data of multiple different first time periods collected during the combustion process of the waste incinerator; constructing a first training data set and a first test data set based on the historical operation data of multiple different first time periods; aiming at predicting the predicted values of the key operation parameters of the waste incinerator in the second time period, using the first training data set for model training to obtain an initial operation parameter prediction model, where the second time period is later than the first time period; using the first test data set to perform parameter adjustment processing on the operation parameter prediction model to obtain the operation parameter prediction model.

[0089] Optionally, the training method of the reinforcement learning model includes: obtaining historical operation data of multiple different third time periods collected during the combustion process of the waste incinerator; for any one of the third time periods, inputting the historical operation data of the third time period into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the fourth time period, where the fourth time period is later than the third time period; constructing a second training data set and a second test data set based on the historical operation data of multiple different third time periods and the predicted values of the key operation parameters in multiple fourth time periods; aiming at determining the target set value of the key operation parameters of the waste incinerator in the fourth time period, using the second training data set for model training to obtain an initial reinforcement learning model; using the second test data set to perform parameter adjustment processing on the initial reinforcement learning model to obtain the reinforcement learning model.

[0090] Optionally, the second training dataset includes a plurality of current state data, and the current state data includes: historical operation data for a third time period and predicted values of key operation parameters for a fourth time period; correspondingly, using the second training dataset for model training to obtain an initial reinforcement learning model, including: inputting the current state data into the initial reinforcement learning model to obtain a set value of the key operation parameters of the waste incinerator decided by the reinforcement learning model for the fourth time period; sending the set value of the key operation parameters for the fourth time period to the combustion control system so that the combustion control system controls the combustion of the waste incinerator according to the set value of the key operation parameters for the fourth time period; after the combustion control is performed based on the current state data, determining a reward value using a reward function, and adjusting the model parameters of the initial reinforcement learning model according to the reward value; repeating the above steps until an initial reinforcement learning model that meets the requirements is obtained.

[0091] Optionally, the relevant factors of the reward function include one or more of the following: combustion efficiency, pollutant emissions, safety limits, and electricity generated per ton of waste; wherein, the electricity generated per ton of waste is obtained by conversion based on the steam amount used for power generation, the fan power, and the waste feeding amount.

[0092] The detailed implementation manners and beneficial effects of each module in the device of this embodiment have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0093] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can also be executed by different devices as the execution subject.

[0094] The embodiment of the present application further provides a combustion control method for a waste incinerator, including: periodically acquiring real-time operation data collected in real time during the combustion process of the waste incinerator; inputting the real-time operation data into an operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator for a future time period; inputting the real-time operation data and the predicted values of the key operation parameters into a reinforcement learning model to determine the target set values of the key operation parameters of the waste incinerator for a future time period; performing combustion control on the waste incinerator according to the target set values of the key operation parameters for the future time period.

[0095] For the detailed implementation manners and beneficial effects of each step in the method of this embodiment, reference can be made to the foregoing embodiments, and will not be elaborated here.

[0096] There is no limitation on the execution subject of the combustion control method for the waste incinerator provided in the embodiment of the present application, for example, it is a combustion control system, an industrial brain open platform, or a waste incinerator system with data processing capabilities, etc.

[0097] In addition, in some of the processes described in the above embodiments and the accompanying drawings, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The operation numbers such as 201 and 202 are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0098] Figure 5 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 5 shown, the electronic device includes: a memory 51 and a processor 52; The memory 51 is used to store computer programs and can be configured to store various other data to support operations on a computing platform. Examples of these data include instructions for any application program or method for operating on a computing platform, data structures, contact data, phone book data, messages, pictures, videos, etc.

[0099] The processor 52 is coupled to the memory 51 and is used to execute the computer program in the memory 51 for: executing the steps in the combustion control method of the waste incinerator.

[0100] Optionally, as Figure 5 shown, the electronic device further includes: other components such as a communication component 53, a display 54, a power supply component 55, an audio component 56, etc. Figure 5 Only some components are schematically shown in, and it does not mean that the electronic device only includes Figure 5 the components shown. In addition, Figure 5 the components within the dashed box in are optional components, not mandatory components, and can be determined according to the product form of the electronic device. The electronic device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, or an IOT (Internet of Things) device, or can also be a server device such as a conventional server, a cloud server, or a server array. If the electronic device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, or a smart phone, it may include Figure 5 the components within the dashed box in; if the electronic device of this embodiment is implemented as a server device such as a conventional server, a cloud server, or a server array, it may not include Figure 5 the components within the dashed box in.

[0101] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0102] The above-mentioned communication component is configured to facilitate communication between the device where the communication component is located and other devices in a wired or wireless manner. The device where the communication component is located can access a wireless network based on a communication standard, such as a 2G (2 Generation), 3G (3 Generation), 4G (4 Generation) / LTE (long Term Evolution), 5G (5 Generation) mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel.

[0103] The above-mentioned display includes a screen, and the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions, but also detect the duration and pressure associated with the touch or swipe operation.

[0104] The above-mentioned power supply component provides power for various components of the device where the power supply component is located. The power supply component can include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.

[0105] The above audio component can be configured to output and / or input an audio signal. For example, the audio component includes a microphone (MIC). When the device where the audio component is located is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in a memory or transmitted via a communication component. In some embodiments, the audio component further includes a speaker for outputting an audio signal.

[0106] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor is caused to implement the steps in the above method embodiments. Among them, the computer-readable storage medium can be implemented by volatile or non-volatile or a combination thereof, and can be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium.

[0107] Correspondingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the processor is enabled to implement each step in the above method embodiments. It should be understood that each process or a combination of multiple processes in the above method flow can be implemented by the computer program or instructions. In addition, these computer programs or instructions can be applied to the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices, so that the processors of general-purpose computers, special-purpose computers, embedded processors or other programmable data processing devices can be used as devices to implement the corresponding functions in the above method embodiments.

[0108] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0109] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A combustion control method for a waste incinerator, characterized in that, Applied to the industrial brain open platform, the method includes: Periodically obtain the real-time operation data collected in real time during the combustion process of the waste incinerator; Input the real-time operation data into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the future time period; Input the real-time operation data and the predicted values of the key operation parameters into the reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in the future time period; Send the target setting values of the key operation parameters to the combustion control system, so that the combustion control system controls the combustion of the waste incinerator according to the target setting values of the key operation parameters in the future time period.

2. The method according to claim 1, wherein Inputting the real-time operation data into the operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in the future time period includes: Input the real-time operation data into the operation parameter prediction model, so that the operation parameter prediction model predicts the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes; according to the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes, obtain the predicted values of the key operation parameters of the waste incinerator in the future time period.

3. The method according to claim 2, wherein Obtaining the predicted values of the key operation parameters of the waste incinerator in the future time period according to the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes includes: Perform weighted summation on the initial predicted values of the key operation parameters of the waste incinerator in the future time period under different operation modes to obtain the intermediate predicted values of the key operation parameters of the waste incinerator in the future time period; Taking the process requirements of the combustion process as the goal, correct the intermediate predicted values of the key operation parameters of the waste incinerator in the future time period to obtain the predicted values of the key operation parameters of the waste incinerator in the future time period.

4. The method according to any one of claims 1 to 3, characterized in that, The real-time operation data includes at least one of the following: the number of pusher strokes of the pusher in the recent time period, the grate action cycle, the number of grate actions, the working frequency of the primary air fan, the working frequency of the secondary air fan, the working frequency of the induced draft fan, the primary air volume, the secondary air volume, the flue gas flow rate, the flue gas temperature, the desuperheating water flow rate, the air chamber wind pressure, the steam flow rate, the steam temperature, the furnace temperature, the furnace negative pressure, the flue gas oxygen content, the environmental protection index data, and the key operation data of the waste storage system; the key operation data of the waste storage system includes at least one of the following: the coordinate position, weight, and fermentation time of the waste crane. The key operation parameters include at least one of the following: furnace temperature, furnace negative pressure, flue gas oxygen content, steam flow rate, steam temperature.

5. The method according to any one of claims 1 to 3, characterized in that, The training method of the operation parameter prediction model includes: Obtain the historical operation data of multiple different first time periods collected during the combustion process of the waste incinerator; Construct a first training data set and a first test data set according to the historical operation data of multiple different first time periods; With the goal of predicting the predicted values of the key operating parameters of the waste incinerator in the second time period, the first training data set is used for model training to obtain an initial operating parameter prediction model, where the second time period is later than the first time period; The parameter adjustment process is performed on the operating parameter prediction model using the first test data set to obtain the operating parameter prediction model.

6. The method according to any one of claims 1 to 3, characterized in that, The training method of the reinforcement learning model includes: Obtain historical operating data of multiple different third time periods collected during the combustion process of the waste incinerator; For any third time period, input the historical operating data of the third time period into the operating parameter prediction model to predict the predicted values of the key operating parameters of the waste incinerator in the fourth time period, where the fourth time period is later than the third time period; Construct a second training data set and a second test data set based on the historical operating data of multiple different third time periods and the predicted values of the key operating parameters in multiple fourth time periods; With the goal of determining the target setting values of the key operating parameters of the waste incinerator in the fourth time period, the second training data set is used for model training to obtain an initial reinforcement learning model; The parameter adjustment process is performed on the initial reinforcement learning model using the second test data set to obtain the reinforcement learning model.

7. The method according to claim 6, characterized in that, The second training data set includes multiple current state data, and the current state data includes: the historical operating data of the third time period and the predicted values of the key operating parameters in the fourth time period; Accordingly, using the second training data set for model training to obtain an initial reinforcement learning model includes: Input the current state data into the initial reinforcement learning model to obtain the setting values of the key operating parameters of the waste incinerator decided by the reinforcement learning model in the fourth time period; Send the setting values of the key operating parameters in the fourth time period to the combustion control system so that the combustion control system performs combustion control on the waste incinerator in the fourth time period according to the setting values of the key operating parameters; After performing combustion control based on the current state data, use the reward function to determine the reward value, and adjust the model parameters of the initial reinforcement learning model according to the reward value; repeat the above steps until an initial reinforcement learning model that meets the requirements is obtained.

8. The method according to claim 7, characterized in that The relevant factors of the reward function include one or more of the following: combustion efficiency, pollutant emissions, safety limits, electricity generated per ton of waste; among them, the electricity generated per ton of waste is obtained by converting the steam amount for power generation, fan power, and waste feeding amount.

9. A waste incineration system, characterized in that, Include: Industrial Brain Open Platform, Combustion Control System, and Waste Incinerator; The Industrial Brain Open Platform is used to periodically obtain the real-time operating data of the waste incinerator collected in real time during the combustion process of the waste incinerator; Input the real-time operating data into the operating parameter prediction model to predict the predicted values of the key operating parameters of the waste incinerator in the future time period; Input the real-time operation data and the predicted values of the key operation parameters into a reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in a future time period; send the target setting values of the key operation parameters to a combustion control system; The combustion control system is configured to perform combustion control on the waste incinerator in the future time period according to the target setting values of the key operation parameters.

10. A combustion control method for a waste incinerator, characterized in that, Comprising: Periodically obtain the real-time operation data collected in real time during the combustion process of the waste incinerator; Input the real-time operation data into an operation parameter prediction model to predict the predicted values of the key operation parameters of the waste incinerator in a future time period; Input the real-time operation data and the predicted values of the key operation parameters into a reinforcement learning model to determine the target setting values of the key operation parameters of the waste incinerator in a future time period; Perform combustion control on the waste incinerator in the future time period according to the target setting values of the key operation parameters.

11. An electronic device, characterized in that, Comprising: A memory and a processor; The memory is configured to store a computer program; the processor is coupled to the memory and is configured to execute the computer program to perform the steps in the method according to any one of claims 1-8 or claim 10.

12. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it causes the processor to be able to implement the steps in the method according to any one of claims 1-8 or claim 10.

13. A computer program product, characterized in that, Comprising computer program / instructions, when the computer program / instructions are executed by the processor, it causes the processor to be able to implement the steps in the method according to any one of claims 1-8 or claim 10.

Images