Control method and system for combustion-supporting air of waste incinerator based on acc+ai

Abstract

The application discloses an ACC+AI-based control method and system for combustion-supporting air of a waste incinerator, the method comprising: obtaining an evaporation capacity expected value and incineration parameters of a waste incinerator to be predicted; inputting the evaporation capacity expected value and the incineration parameters into a pre-trained MPC prediction model to determine a primary air blower frequency of the waste incinerator to be predicted at a next time; wherein the MPC prediction model is obtained by pre-training sample evaporation capacity and sample incineration parameters of a sample waste incinerator; and based on the primary air blower frequency, the combustion-supporting air of the waste incinerator to be predicted at the next time is controlled. Thus, the MPC prediction model takes the evaporation capacity prediction value as a control state value, and then outputs the primary air blower frequency of a next time period based on the incineration parameters, and the primary air blower frequency of the next time period and the air volume of each air chamber under the regulation grate are used to control the incineration area, thereby solving the lag problem in the existing adjustment of the evaporation capacity of the boiler.

Description

Technical Field

[0001] This application relates to the field of combustion air control technology, and in particular to a control method and system for combustion air in a waste incinerator based on ACC+AI. Background Technology

[0002] Currently, due to the complex and variable characteristics of waste, waste incinerators exhibit nonlinear and time-varying properties during combustion, requiring frequent manual operation. This leads to unstable combustion control and large fluctuations in boiler load. Therefore, there is an urgent need to automate the combustion process in waste incinerators.

[0003] In existing technologies, the combustion process of waste incinerators is mainly automated by using an automatic combustion control system (ACC) with a PID controller to directly or indirectly adjust the combustion air. This involves comparing the measured value of the boiler evaporation with the target value to obtain the deviation, and then using the deviation to adjust the flow rate of the combustion air. By adjusting the flow rate of the combustion air, the boiler load can be stably controlled.

[0004] When the measured value of boiler evaporation deviates from the target value, the PID controller will adjust the output frequency of the combustion air to make the actual value of evaporation reach the target value. However, the adjustment process takes a certain amount of time, and the length of time is closely related to the calorific value of the fuel, which may lead to a lag in the adjustment of boiler evaporation. Summary of the Invention

[0005] In view of the shortcomings of the prior art, this application provides a control method and system for combustion air of waste incinerator based on ACC+AI, so as to solve the lag problem in adjusting boiler evaporation caused by the prior art.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] The first aspect of this application provides a method for controlling the combustion air of a waste incinerator based on ACC+AI, including:

[0008] Obtain the expected evaporation rate and incineration parameters of the waste incinerator to be predicted; wherein, the incineration parameters include at least the primary fan frequency at the current moment;

[0009] The expected evaporation rate and the incineration parameters are input into a pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator to be predicted at the next moment; wherein, the MPC prediction model is pre-trained using sample evaporation rates and sample incineration parameters of sample waste incinerators; the MPC prediction model is pre-constructed based on the MPC controller and sample incineration parameters of sample waste incinerators.

[0010] Based on the frequency of the primary fan, the combustion air of the waste incinerator to be predicted is controlled in the next moment.

[0011] Optionally, in the above-mentioned control method for combustion air of a waste incinerator based on ACC+AI, the step of inputting the expected evaporation rate and the incineration parameters into a pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator to be predicted at the next moment includes:

[0012] The expected evaporation rate and the incineration parameters are input into a pre-trained MPC prediction model. The MPC prediction model initializes a control sequence for the internal primary fan frequency based on the current primary fan frequency in the incineration parameters. The control sequence contains multiple time points.

[0013] Based on the expected evaporation rate, the primary fan frequency at the current moment in the incineration parameters, and the current evaporation rate, the MPC model predicts the primary fan frequency and evaporation rate at the current time point in the control quantity sequence, and determines the primary fan frequency and evaporation rate at the current time point as the current data to be predicted; wherein, the current time point refers to the first time point in the control quantity sequence.

[0014] The current data to be predicted is input into the MPC prediction model to predict the primary fan frequency and evaporation rate at the next time point.

[0015] The predicted primary fan frequency and evaporation at the next time point are determined as the current data to be predicted, and the process is returned to input the current data to be predicted into the MPC prediction model to predict the predicted primary fan frequency and evaporation at the next time point, until the predicted primary fan frequency and evaporation at all time points in the control quantity sequence are predicted.

[0016] Determine whether the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraints.

[0017] If the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraint conditions, then the primary fan frequency at the first time point in the control quantity sequence will be taken as the primary fan frequency of the waste incinerator to be predicted at the next time point.

[0018] Optionally, in the above-mentioned control method for combustion air in a waste incinerator based on ACC+AI, the training method for the MPC prediction model includes:

[0019] Obtain the sample evaporation rate and sample incineration parameters of the sample waste incinerator;

[0020] The sample evaporation rate and the sample incineration parameters are input into the MPC prediction model to obtain the sample evaporation prediction rate and sample primary fan frequency of the sample waste incinerator at the next time point.

[0021] Determine whether the predicted evaporation amount and the primary fan frequency of the sample both meet the actual requirements;

[0022] If the predicted evaporation amount and the primary fan frequency of the sample both meet the actual requirements, then the MPC prediction model is determined as the trained MPC prediction model.

[0023] If the predicted evaporation amount and the primary fan frequency of the sample do not meet the actual requirements, the weight parameters of the MPC prediction model are adjusted, and the process of inputting the sample evaporation amount and the sample incineration parameters into the MPC prediction model is returned to obtain the predicted evaporation amount and the primary fan frequency of the sample waste incinerator at the next time point.

[0024] Optionally, in the above-mentioned control method for combustion air in a waste incinerator based on ACC+AI, the step of determining whether the sample evaporation prediction and the sample primary air fan frequency both meet the actual requirements includes:

[0025] Determine whether the frequency of the primary fan in the sample meets the ACC control air volume, and whether the weight parameters of the MPC prediction model meet the preset requirements;

[0026] If the primary fan frequency of the sample meets the ACC control air volume and the weight parameters of the MPC prediction model meet the preset requirements, then it is determined that the evaporation prediction amount and the primary fan frequency of the sample both meet the actual requirements.

[0027] If the sample primary fan frequency does not meet the ACC control air volume, and the weight parameters of the MPC prediction model do not meet the preset requirements, then it is determined that the sample evaporation prediction and the sample primary fan frequency do not meet the actual requirements.

[0028] Optionally, in the above-mentioned control method for combustion air of a waste incinerator based on ACC+AI, the step of controlling the combustion air of the waste incinerator to be predicted in the next moment based on the primary fan frequency includes:

[0029] Obtain the parameters of each region in the waste incinerator to be predicted;

[0030] Based on the parameters of each region and the frequency of the primary fan, the primary air volume of the primary fan is allocated to each region;

[0031] Based on the primary air volume allocated to each of the regions, the combustion air in each region of the waste incinerator to be predicted is controlled in the next moment.

[0032] The second aspect of this application provides a control system for combustion air in a waste incinerator based on ACC+AI, including:

[0033] The parameter acquisition unit is used to acquire the expected value of the evaporation rate of the waste incinerator to be predicted and the incineration parameters; wherein, the incineration parameters include at least the primary fan frequency at the current moment;

[0034] The parameter input unit is used to input the expected evaporation rate and the incineration parameters into a pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator to be predicted at the next moment; wherein, the MPC prediction model is pre-trained using sample evaporation rates and sample incineration parameters of sample waste incinerators; the MPC prediction model is pre-constructed based on the MPC controller and sample incineration parameters of the sample waste incinerators;

[0035] The air volume control unit is used to control the combustion air of the waste incinerator to be predicted in the next moment based on the frequency of the primary fan.

[0036] Optionally, in the above-mentioned ACC+AI-based control system for combustion air in a waste incinerator, the parameter input unit includes:

[0037] The first input unit is used to input the expected evaporation value and the incineration parameters into a pre-trained MPC prediction model. The MPC prediction model initializes the control sequence of the internal primary fan frequency based on the primary fan frequency at the current moment in the incineration parameters. The control sequence includes multiple time points.

[0038] The first prediction unit is used to predict the predicted primary fan frequency and evaporation amount at the current time point in the control quantity sequence based on the expected evaporation amount, the primary fan frequency at the current time in the incineration parameters, and the current evaporation amount using the MPC model, and to determine the predicted primary fan frequency and evaporation amount at the current time point as the current data to be predicted; wherein, the current time point refers to the first time point in the control quantity sequence.

[0039] The second prediction unit is used to input the current data to be predicted into the MPC prediction model to predict the primary fan frequency and evaporation rate at the next time point.

[0040] The first execution unit is used to determine the predicted primary fan frequency and evaporation amount at the next time point as the current data to be predicted, and return to execute to input the current data to be predicted into the MPC prediction model to predict the predicted primary fan frequency and evaporation amount at the next time point, until the predicted primary fan frequency and evaporation amount at all time points in the control quantity sequence are predicted.

[0041] The condition judgment unit is used to determine whether the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraint conditions.

[0042] As a unit, if the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraint conditions, then the primary fan frequency at the first time point in the control quantity sequence is taken as the primary fan frequency of the waste incinerator to be predicted at the next time point.

[0043] Optionally, the above-mentioned ACC+AI-based control system for combustion air in a waste incinerator also includes:

[0044] The first acquisition unit is used to acquire the sample evaporation rate and sample incineration parameters of the sample waste incinerator;

[0045] The second input unit is used to input the sample evaporation amount and the sample incineration parameters into the MPC prediction model to obtain the sample evaporation prediction amount and sample primary fan frequency of the sample waste incinerator at the next time point.

[0046] The judgment unit is required to determine whether the predicted evaporation amount of the sample and the primary fan frequency of the sample both meet the actual requirements.

[0047] The first determining unit is used to determine the MPC prediction model as the trained MPC prediction model if the predicted evaporation amount of the sample and the primary fan frequency of the sample both meet the actual requirements.

[0048] The second determining unit is used to adjust the weight parameters of the MPC prediction model if the sample evaporation prediction amount and the sample primary fan frequency do not meet the actual requirements, and return to the step of inputting the sample evaporation amount and the sample incineration parameters into the MPC prediction model to obtain the sample evaporation prediction amount and sample primary fan frequency of the sample waste incinerator at the next time point.

[0049] Optionally, in the above-mentioned ACC+AI-based control system for combustion air in a waste incinerator, the requirement judgment unit includes:

[0050] The judgment unit is used to determine whether the frequency of the primary fan of the sample meets the ACC control air volume and whether the weight parameters of the MPC prediction model meet the preset requirements.

[0051] The third determining unit is used to determine that if the sample primary fan frequency meets the ACC control air volume and the weight parameters of the MPC prediction model meet the preset requirements, then the sample evaporation prediction amount and the sample primary fan frequency both meet the actual requirements.

[0052] The fourth determining unit is used to determine that if the sample primary fan frequency does not meet the ACC control air volume and the weight parameters of the MPC prediction model do not meet the preset requirements, then the sample evaporation prediction amount and the sample primary fan frequency do not meet the actual requirements.

[0053] Optionally, in the above-mentioned ACC+AI-based control system for combustion air in a waste incinerator, the air volume control unit includes:

[0054] The second acquisition unit is used to acquire parameters for each region in the waste incinerator to be predicted.

[0055] The distribution unit is used to distribute the primary air volume of the primary fan to each of the regions according to the parameters of each region and the frequency of the primary fan;

[0056] A control unit is configured to control the combustion air in each zone of the waste incinerator to be predicted at the next moment, based on the primary air volume allocated to each zone.

[0057] This application provides a control method for combustion air in a waste incinerator based on ACC+AI. The method obtains the expected evaporation rate and combustion parameters of the waste incinerator to be predicted. The combustion parameters include at least the primary fan frequency at the current moment. The expected evaporation rate and combustion parameters are then input into a pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator at the next moment. The MPC prediction model is pre-trained using sample evaporation rates and combustion parameters from sample waste incinerators. The model is also pre-constructed based on an MPC controller and the sample combustion parameters from the sample waste incinerators. Finally, the combustion air in the waste incinerator is controlled based on the primary fan frequency at the next moment. Thus, the predicted evaporation rate is used as the control state variable by the MPC prediction model, and the primary fan frequency for the next time period is output based on the combustion parameters. The primary fan frequency for the next time period and the air volume in each air chamber under the grate are then adjusted to control the combustion zone, thereby solving the lag problem in existing methods for regulating boiler evaporation rates. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0059] Figure 1 A flowchart illustrating a method for controlling combustion air in a waste incinerator based on ACC+AI, provided in an embodiment of this application;

[0060] Figure 2 A flowchart illustrating the method for determining the frequency of a primary fan provided in an embodiment of this application;

[0061] Figure 3 A schematic diagram illustrating the principle of an MPC prediction model provided in an embodiment of this application;

[0062] Figure 4 A flowchart illustrating a training method for an MPC prediction model provided in an embodiment of this application;

[0063] Figure 5 A flowchart illustrating a determination method for an MPC prediction model provided in an embodiment of this application;

[0064] Figure 6 A schematic flowchart illustrating a method for controlling combustion air according to an embodiment of this application;

[0065] Figure 7A schematic diagram of the control principle structure for primary fan air volume distribution provided in an embodiment of this application;

[0066] Figure 8 This is a schematic diagram of the structure of a control system for combustion air in a waste incinerator based on ACC+AI, provided as another embodiment of this application. Detailed Implementation

[0067] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0068] In this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0069] This application provides a method for controlling the combustion air in a waste incinerator based on ACC+AI, such as... Figure 1 As shown, the specific steps include:

[0070] S101. Obtain the expected value of evaporation rate and incineration parameters of the waste incinerator to be predicted.

[0071] The incineration parameters may include the frequency of the primary fan at the current moment.

[0072] It should be noted that the predicted evaporation rate of the waste incinerator refers to the set evaporation rate that the incinerator is expected to achieve in the next moment. This allows the MPC prediction model to adjust the primary fan frequency based on the predicted evaporation rate, thereby stabilizing the evaporation rate of the waste incinerator at the predicted moment. This predicted evaporation rate is pre-set manually based on factors such as the composition of the waste in the incinerator and the incinerator's design operating conditions.

[0073] The incineration parameters of the waste incinerator to be predicted can include 143 parameters related to the waste incinerator, such as incinerator outlet temperature, air pressure, boiler drum pressure, etc., so that the MPC prediction model can know the combustion efficiency and basic conditions of the waste incinerator to be predicted based on the incineration parameters, thus enabling accurate prediction.

[0074] S102. Input the expected evaporation rate and incineration parameters into the pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator to be predicted at the next moment.

[0075] The MPC prediction model is pre-trained using sample evaporation and incineration parameters from sample waste incinerators, and is pre-constructed based on the MPC controller and sample incineration parameters from sample waste incinerators.

[0076] It should be emphasized that, in the embodiments of this application, the MPC prediction model combines the control principle of the incinerator's ACC (Automatic Combustion Control) system with the MPC (Model Predictive Control) control principle, i.e., the model predictive control method, to achieve the function of continuous predictive control. It continuously predicts the frequency of the primary fan of the waste incinerator at the next moment, solves the problem of lag in adjusting the evaporation rate, and can also reduce the fluctuations that may be caused by the control, thereby stabilizing the evaporation rate around the expected value.

[0077] Optionally, in another embodiment of this application, one specific implementation of step S102 is as follows: Figure 2 As shown, it includes the following steps:

[0078] S201. Input the expected evaporation rate and incineration parameters into the pre-trained MPC prediction model. Based on the current primary fan frequency in the incineration parameters, initialize the control sequence of the internal primary fan frequency through the MPC prediction model.

[0079] The control quantity sequence contains multiple time points.

[0080] It is important to emphasize that, considering that the MPC prediction model needs to predict the primary fan frequency at the next moment, it is necessary to consider the changes in evaporation and primary fan frequency at all time points in the next moment. Therefore, it is necessary to first initialize all time points Xc(1~k) in the control quantity sequence of the internal primary fan frequency based on the primary fan frequency at the current moment in the incineration parameters.

[0081] S202. Based on the expected evaporation rate, the primary fan frequency at the current moment in the incineration parameters, and the current evaporation rate, the MPC model is used to predict the primary fan frequency and evaporation rate at the current time point in the control quantity sequence, and the primary fan frequency and evaporation rate at the current time point are determined as the current data to be predicted.

[0082] Here, the current time point refers to the first time point in the control quantity sequence.

[0083] It should be noted that in order to consider the changes in evaporation and primary fan frequency at all time points in the next moment, the MPC model first needs to adjust and obtain the evaporation prediction Xc1 at the first time point in the control quantity sequence based on the expected evaporation value, the primary fan frequency at the current moment in the incineration parameters, and the current evaporation. Then, the MPC model will predict a corresponding primary fan frequency based on the evaporation prediction Xc1 and output the evaporation prediction Xc1 and the corresponding primary fan frequency.

[0084] S203. Input the current data to be predicted into the MPC prediction model to predict the primary fan frequency and evaporation rate at the next time point.

[0085] Understandably, the predicted evaporation amount Xc1 at the first time point and the corresponding primary fan frequency are used as inputs to the MPC prediction model at the next time point, and then the predicted evaporation amount Xc2 at the second time point and the corresponding primary fan frequency are predicted.

[0086] S204. The predicted primary fan frequency and evaporation rate at the next time point are determined as the current data to be predicted.

[0087] It is understandable that the embodiments of this application require continuously using the output of the MPC prediction model as the input of the next MPC prediction model until the predicted evaporation amount Xck at the Kth time point and the corresponding primary fan frequency are predicted. Only then can the changes in evaporation amount and primary fan frequency at all time points in the next time period be considered to achieve the function of continuous predictive control and reduce the overshoot and lag caused by the time-varying conditions of traditional PID control. Therefore, it is necessary to determine the primary fan frequency and evaporation prediction amount at the next time point as the current data to be predicted, and return to step S203 until the primary fan frequency and evaporation prediction amount Xck at all time points in the control quantity sequence are predicted.

[0088] S205. Determine whether the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraints.

[0089] It should be noted that the MPC prediction model predicts the primary fan frequency and evaporation forecast Xc(1~k) for the next K time points. However, considering that the predicted control sequence may not be optimal, in order to determine whether the primary fan frequency and evaporation forecast for all time points in the predicted control sequence are optimal, the hysteresis range is used as a preset constraint in the embodiment of this application. That is, it is determined whether the primary fan frequency and evaporation forecast for all time points in the control sequence meet the preset constraint, that is, whether the primary fan frequency and evaporation forecast for all time points in the control sequence are within the hysteresis range. If the primary fan frequency and evaporation forecast for all time points in the control sequence meet the preset constraint, it means that the primary fan frequency and evaporation forecast for all time points in the control sequence are within the hysteresis range, so step S206 is executed.

[0090] Optionally, if the predicted primary fan frequency and evaporation rate at all time points in the control sequence do not meet the preset constraints, it indicates that the predicted primary fan frequency and evaporation rate at all time points in the control sequence are not within the hysteresis range. Therefore, it is necessary to re-initialize the control sequence based on the last predicted primary fan frequency and use the MPC prediction model to re-predict the predicted primary fan frequency and evaporation rate Xc(1~k) for the next K time points in the control sequence until the control sequence meets the preset constraints.

[0091] It should also be noted that Xc(1~k) is the value in the vertical time dimension, and each calculation will update a new round of Xc(1~k).

[0092] S206. The primary fan frequency at the first time point in the control sequence is taken as the primary fan frequency of the waste incinerator to be predicted at the next time point.

[0093] It is understandable that when the primary fan frequency and evaporation prediction at all time points in the control sequence meet the preset constraints, the primary fan frequency at the first time point in the control sequence will be output as the primary fan frequency of the waste incinerator to be predicted at the next moment. Since the optimal control sequence Xc(1~k) is the output of the next K time points, the output needs to be based on the first time point in the future, so as to achieve the optimal evaporation rate stabilizing at the expected evaporation rate.

[0094] It should be noted that steps S201 to S206 can be found in [reference needed]. Figure 3 The diagram shown illustrates the principle of the MPC prediction model.

[0095] Optionally, embodiments of this application provide a training method for an MPC prediction model, such as... Figure 4 As shown, it includes the following steps:

[0096] S401. Obtain the sample evaporation rate and sample incineration parameters of the sample waste incinerator.

[0097] Specifically, the sample incineration parameters were pre-analyzed using 196 variables from the sample waste incinerator. The analysis revealed that 143 data points were correlated with the evaporation control target. Therefore, the sample incineration parameters refer to the 143 data points that are correlated with the evaporation control target.

[0098] S402. Input the sample evaporation and sample incineration parameters into the MPC prediction model to obtain the sample evaporation prediction and sample primary fan frequency of the sample waste incinerator at the next time point.

[0099] Specifically, an MPC prediction model is constructed based on the MPC controller and the sample incineration parameters of the sample waste incinerator. Furthermore, the MPC prediction model is trained using the coupling of the ACC and AI models based on the sample evaporation and sample incineration parameters to obtain the sample evaporation prediction amount and sample primary fan frequency of the sample waste incinerator at the next time point.

[0100] S403. Determine whether the predicted evaporation amount and the primary fan frequency of the sample both meet the actual requirements.

[0101] It should be noted that, in order to determine whether the MPC prediction model has been successfully trained, the prediction results of the MPC prediction model are judged, specifically whether the predicted evaporation amount and the primary fan frequency of the sample both meet the actual requirements. If both the predicted evaporation amount and the primary fan frequency of the sample meet the actual requirements, it indicates that the MPC prediction model has been successfully trained, and therefore step S404 is executed. If neither the predicted evaporation amount nor the primary fan frequency of the sample meets the actual requirements, it indicates that the MPC prediction model has failed to train, and therefore step S405 is executed.

[0102] Optionally, in another embodiment of this application, one specific implementation of step S403 is as follows: Figure 5 As shown, it includes the following steps:

[0103] S501. Determine whether the frequency of the primary fan in the sample meets the ACC control air volume and whether the weight parameters of the MPC prediction model meet the preset requirements.

[0104] It should be noted that, in order to determine whether the trained MPC prediction model can be put into practical use, it is necessary to judge whether the primary air fan frequency of the sample meets the ACC control air volume (for example, if the evaporation rate of a waste incineration boiler decreases at this time, the corresponding operation of the ACC control system is to increase the air volume), and whether the weight parameters of the MPC prediction model meet the preset requirements (for example, whether the furnace temperature threshold of the MPC prediction model meets the preset threshold). Therefore, if the primary air fan frequency of the sample meets the ACC control air volume and the weight parameters of the MPC prediction model meet the preset requirements, it means that the MPC prediction model can be put into practical use, and step S502 is executed. If the primary air fan frequency of the sample does not meet the ACC control air volume and the weight parameters of the MPC prediction model do not meet the preset requirements, it means that the MPC prediction model cannot be put into practical use, and step S503 is executed.

[0105] S502. The predicted evaporation rate and the primary fan frequency of the sample both meet the actual requirements.

[0106] S503. The predicted evaporation amount and the primary fan frequency of the sample do not meet the actual requirements.

[0107] S404. Determine the MPC prediction model as the trained MPC prediction model.

[0108] Specifically, when both the sample evaporation prediction and the sample primary air fan frequency meet the actual requirements, it indicates that the MPC prediction model has been successfully trained. Therefore, the MPC prediction model can be put into practical application to predict the total primary air volume of the waste incinerator in advance, so as to adjust the evaporation of the waste incinerator at the next moment in advance, so as to stabilize the evaporation at the predicted amount and solve the problem of lag in adjusting the evaporation.

[0109] S405. Adjust the weight parameters of the MPC prediction model.

[0110] Understandably, when the sample evaporation prediction and the sample primary fan frequency do not meet the actual requirements, it is necessary to readjust the weight parameters of the MPC prediction model and return to step S402 to iteratively train the MPC prediction model until the sample evaporation prediction and the sample primary fan frequency both meet the actual requirements.

[0111] S103. Based on the frequency of the primary fan, control the combustion air of the waste incinerator to be predicted in the next moment.

[0112] Understandably, the predicted primary fan frequency is used to control the total primary combustion air supplied to the waste incinerator for the next moment, thereby affecting the stability of the boiler's evaporation rate at the expected value.

[0113] Optionally, in another embodiment of this application, one specific implementation of step S103 is as follows: Figure 6 As shown, it includes the following steps:

[0114] S601. Obtain the parameters of each region in the waste incinerator to be predicted.

[0115] It should be noted that, since the required combustion air ratio varies in each zone of the waste incinerator to be predicted, in order to improve energy utilization efficiency and ensure that the evaporation rate in each zone remains stable within the expected value, thus avoiding lag issues, it is necessary to obtain parameters for each zone of the waste incinerator to be predicted. Optionally, these parameters can be collected using sensors and monitoring equipment.

[0116] S602. Based on the parameters of each area and the frequency of the primary fan, distribute the primary air volume of the primary fan to each area.

[0117] Specifically, the combustion zone typically requires a higher air supply, and therefore may require a higher primary air volume.

[0118] Dry areas typically require relatively high fan airflow to ensure that the fuel is sufficiently dried and to provide fuel with a relatively stable calorific value for combustion, thus facilitating the maintenance of stable evaporation.

[0119] The combustion zone typically requires a lower primary air volume, therefore the primary air volume allocated to the combustion zone is also lower. Since the fan frequency is used to control the primary air volume, in this embodiment, it is necessary to consider the parameters of these zones, the primary fan frequency, and the overall balance of the combustion process to achieve a reasonable allocation of the primary fan air volume.

[0120] S603. Based on the primary air volume allocated to each area, control the combustion air of each area in the waste incinerator to be predicted in the next moment.

[0121] Specifically, when the calorific value in the incinerator to be predicted is low, the MPC controller will control the primary air fan to appropriately increase the excess air (controlling the primary air fan), and combine this with the ACC control concept (controlling the damper) to increase the air volume in the drying zone to enhance the drying effect and promote combustion.

[0122] When high temperatures occur in the combustion zone, the combustion air is directed towards the combustion zone (achieved by controlling the damper). This serves two purposes: firstly, to prevent excessive fluctuations in the total combustion air volume, stabilizing the evaporation rate within the expected value, and secondly, to ensure complete fuel combustion. For details, please refer to [link to relevant documentation]. Figure 7 The diagram shows the control principle structure of the primary fan air volume distribution.

[0123] It is understandable that when the frequency of the primary air fan in the incinerator to be predicted increases or the damper in the combustion zone increases, the combustion air will increase and the evaporation will increase accordingly; conversely, the evaporation will decrease.

[0124] This application provides a control method for combustion air in a waste incinerator based on ACC+AI. The method obtains the expected evaporation rate and combustion parameters of the waste incinerator to be predicted. The combustion parameters include at least the primary fan frequency at the current moment. The expected evaporation rate and combustion parameters are then input into a pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator at the next moment. The MPC prediction model is pre-trained using sample evaporation rates and combustion parameters from sample waste incinerators. The model is also pre-constructed based on an MPC controller and the sample combustion parameters from the sample waste incinerators. Finally, the combustion air in the waste incinerator is controlled based on the primary fan frequency at the next moment. Thus, the predicted evaporation rate is used as the control state variable by the MPC prediction model, and the primary fan frequency for the next time period is output based on the combustion parameters. The primary fan frequency for the next time period and the air volume in each air chamber under the grate are then adjusted to control the combustion zone, thereby solving the lag problem in existing methods for regulating boiler evaporation rates.

[0125] Another embodiment of this application provides a control system for combustion air in a waste incinerator based on ACC+AI, such as... Figure 8 As shown, it includes the following units:

[0126] The parameter acquisition unit 801 is used to acquire the expected value of the evaporation rate of the waste incinerator to be predicted and the incineration parameters. Among them, the incineration parameters include at least the current primary fan frequency.

[0127] The parameter input unit 802 is used to input the expected evaporation rate and incineration parameters into the pre-trained MPC prediction model to determine the primary fan frequency of the waste incinerator to be predicted at the next time step. The MPC prediction model is pre-trained using sample evaporation rates and sample incineration parameters from a sample waste incinerator. The MPC prediction model is pre-constructed based on the MPC controller and the sample incineration parameters from the sample waste incinerator.

[0128] The air volume control unit 803 is used to control the combustion air of the waste incinerator to be predicted in the next moment based on the primary fan frequency.

[0129] It should be noted that the specific working process of the above-mentioned units in the embodiments of this application can be referred to steps S101 to S103 in the above method embodiments, and will not be repeated here.

[0130] Optionally, in another embodiment of this application, a control system for combustion air in a waste incinerator based on ACC+AI is provided, wherein the parameter input unit 802 includes:

[0131] The first input unit is used to input the expected evaporation rate and incineration parameters into the pre-trained MPC prediction model. The MPC prediction model initializes the control sequence of the internal primary fan frequency based on the current primary fan frequency in the incineration parameters. The control sequence contains multiple time points.

[0132] The first prediction unit is used to predict the primary fan frequency and evaporation forecast for the current time point in the control sequence using the MPC model based on the expected evaporation rate, the primary fan frequency at the current moment in the incineration parameters, and the current evaporation rate. The predicted primary fan frequency and evaporation forecast for the current time point are then determined as the data to be predicted. Here, the current time point refers to the first time point in the control sequence.

[0133] The second prediction unit is used to input the current data to be predicted into the MPC prediction model to predict the primary fan frequency and evaporation rate at the next time point.

[0134] The first execution unit is used to determine the primary fan frequency and evaporation prediction for the next time point as the current data to be predicted, and return to execute to input the current data to be predicted into the MPC prediction model to predict the primary fan frequency and evaporation prediction for the next time point, until the primary fan frequency and evaporation prediction for all time points in the control quantity sequence are predicted.

[0135] The condition judgment unit is used to determine whether the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraints.

[0136] As a unit, if the primary fan frequency and evaporation prediction at all time points in the control quantity sequence meet the preset constraints, then the primary fan frequency at the first time point in the control quantity sequence is taken as the primary fan frequency of the waste incinerator to be predicted at the next moment.

[0137] Optionally, another embodiment of this application provides a control system for combustion air in a waste incinerator based on ACC+AI, which further includes:

[0138] The first acquisition unit is used to acquire the sample evaporation rate and sample incineration parameters of the sample waste incinerator.

[0139] The second input unit is used to input the sample evaporation and sample incineration parameters into the MPC prediction model to obtain the sample evaporation prediction and sample primary fan frequency of the sample waste incinerator at the next time point.

[0140] The system requires a judgment unit to determine whether the predicted evaporation amount and the primary fan frequency of the sample both meet the actual requirements.

[0141] The first determining unit is used to determine the MPC prediction model as the trained MPC prediction model if both the sample evaporation prediction amount and the sample primary fan frequency meet the actual requirements.

[0142] The second determining unit is used to adjust the weight parameters of the MPC prediction model if the sample evaporation prediction amount and the sample primary fan frequency do not meet the actual requirements, and then return to the execution to input the sample evaporation amount and sample incineration parameters into the MPC prediction model to obtain the sample evaporation prediction amount and sample primary fan frequency of the sample waste incinerator at the next time point.

[0143] Optionally, another embodiment of this application provides a control system for combustion air in a waste incinerator based on ACC+AI, requiring a judgment unit including:

[0144] The judgment unit is used to determine whether the frequency of the primary fan in the sample meets the ACC control air volume and whether the weight parameters of the MPC prediction model meet the preset requirements.

[0145] The third determining unit is used to determine that if the sample primary fan frequency meets the ACC control air volume and the weight parameters of the MPC prediction model meet the preset requirements, then the sample evaporation prediction quantity and the sample primary fan frequency both meet the actual requirements.

[0146] The fourth determination unit is used to determine that if the sample primary fan frequency does not meet the ACC control air volume and the weight parameters of the MPC prediction model do not meet the preset requirements, then the sample evaporation prediction amount and the sample primary fan frequency do not meet the actual requirements.

[0147] Optionally, in another embodiment of this application, a control system for combustion air in a waste incinerator based on ACC+AI is provided, wherein the air volume control unit 803 includes:

[0148] The second acquisition unit is used to acquire parameters for each region in the waste incinerator to be predicted.

[0149] The distribution unit is used to distribute the primary air volume of the primary fan to each area according to the parameters of each area and the frequency of the primary fan.

[0150] The control unit is used to control the combustion air in each zone of the waste incinerator to be predicted at the next moment, based on the primary air volume allocated to each zone.

[0151] It should be noted that the specific working process of each unit provided in the above embodiments of this application can be referred to the corresponding steps in the above method embodiments, and will not be repeated here.

[0152] In summary, another embodiment of this application provides a control system for combustion air of a waste incinerator based on ACC+AI, which predicts the total primary air volume at the next moment through the MPC prediction model, thereby reducing the overshoot and lag caused by the time-varying operating conditions of traditional PID control.

[0153] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0154] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An ACC+AI-based control method for combustion-supporting air of a waste incinerator, characterized by, The method comprises the steps of: obtaining an evaporation capacity expected value of a to-be-predicted waste incinerator and incineration parameters; wherein the incineration parameters at least include a primary air fan frequency at a current time; inputting the evaporation capacity expected value and the incineration parameters into a pre-trained MPC prediction model to determine a primary air fan frequency of the to-be-predicted waste incinerator at a next time; wherein the MPC prediction model is pre-trained by sample evaporation capacity and sample incineration parameters of a sample waste incinerator; and the MPC prediction model is pre-constructed based on an MPC controller and sample incineration parameters of the sample waste incinerator; based on the primary air fan frequency, controlling combustion-supporting air of the to-be-predicted waste incinerator at the next time; wherein the step of inputting the evaporation capacity expected value and the incineration parameters into the pre-trained MPC prediction model to determine the primary air fan frequency of the to-be-predicted waste incinerator at the next time comprises: inputting the evaporation capacity expected value and the incineration parameters into the pre-trained MPC prediction model to initialize an internal primary air fan frequency control quantity sequence based on the primary air fan frequency at the current time in the incineration parameters by the MPC prediction model; wherein the control quantity sequence contains multiple time points; predicting the primary air fan frequency at the current time point and the evaporation capacity prediction in the control quantity sequence based on the evaporation capacity expected value, the primary air fan frequency at the current time in the incineration parameters, and the current evaporation capacity by the MPC model, and determining the primary air fan frequency at the current time point and the evaporation capacity prediction as current to-be-predicted data; wherein the current time point refers to the first time point in the control quantity sequence; inputting the current to-be-predicted data into the MPC prediction model to predict the primary air fan frequency at the next time point and the evaporation capacity prediction; determining the primary air fan frequency at the next time point and the evaporation capacity prediction as the current to-be-predicted data, and returning to the step of inputting the current to-be-predicted data into the MPC prediction model to predict the primary air fan frequency at the next time point and the evaporation capacity prediction, until the primary air fan frequencies at all time points and the evaporation capacity predictions in the control quantity sequence are predicted; judging whether the primary air fan frequencies at all time points and the evaporation capacity predictions in the control quantity sequence meet preset constraint conditions; if the primary air fan frequencies at all time points and the evaporation capacity predictions in the control quantity sequence meet the preset constraint conditions, taking the primary air fan frequency at the first time point in the control quantity sequence as the primary air fan frequency of the to-be-predicted waste incinerator at the next time.

2. The method of claim 1, wherein, The training method of the MPC prediction model comprises the steps of: obtaining sample evaporation capacity and sample incineration parameters of a sample waste incinerator; inputting the sample evaporation capacity and the sample incineration parameters into an MPC prediction model to obtain sample evaporation prediction and sample primary air fan frequency of the sample waste incinerator at a next time; judging whether the sample evaporation prediction and the sample primary air fan frequency meet actual requirements; If the sample evaporation prediction and the sample primary air fan frequency both meet the actual requirements, the MPC prediction model is determined as a trained MPC prediction model; If the sample evaporation prediction and the sample primary air fan frequency both do not meet the actual requirements, the weight parameters of the MPC prediction model are adjusted, and the sample evaporation and the sample incineration parameters are input into the MPC prediction model to obtain the sample garbage incinerator at a next time point.

3. The method of claim 2, wherein, The judgment whether the sample evaporation prediction and the sample primary air fan frequency both meet the actual requirements comprises: judging whether the sample primary air fan frequency conforms to the ACC control air volume and whether the weight parameters of the MPC prediction model conform to the preset requirements; If the sample primary air fan frequency conforms to the ACC control air volume and the weight parameters of the MPC prediction model conform to the preset requirements, it is determined that the sample evaporation prediction and the sample primary air fan frequency both meet the actual requirements; If the sample primary air fan frequency does not conform to the ACC control air volume and the weight parameters of the MPC prediction model do not conform to the preset requirements, it is determined that the sample evaporation prediction and the sample primary air fan frequency both do not meet the actual requirements.

4. The method of claim 1, wherein, The control of the combustion-supporting air of the garbage incinerator to be predicted at a next time point based on the primary air fan frequency comprises: obtaining parameters of each region in the garbage incinerator to be predicted; allocating a primary air volume of a primary air fan to each region according to the parameters of each region and the primary air fan frequency; controlling the combustion-supporting air of each region in the garbage incinerator to be predicted at a next time point based on the primary air volume allocated to each region.

5. An ACC+AI-based control system for combustion-supporting air of a waste incinerator, characterized by, It comprises: a parameter obtaining unit configured to obtain an evaporation expectation value and an incineration parameter of a garbage incinerator to be predicted, wherein the incineration parameter at least comprises a primary air fan frequency at a current time point; a parameter input unit configured to input the evaporation expectation value and the incineration parameter into a pre-trained MPC prediction model to determine a primary air fan frequency of the garbage incinerator to be predicted at a next time point, wherein the MPC prediction model is obtained by pre-training a sample evaporation and a sample incineration parameter of a sample garbage incinerator; and the MPC prediction model is obtained by pre-construction based on an MPC controller and the sample incineration parameter of the sample garbage incinerator; an air volume control unit configured to control combustion-supporting air of the garbage incinerator to be predicted at a next time point based on the primary air fan frequency; The parameter input unit comprises: a first input unit configured to input the evaporation expectation value and the incineration parameter into the pre-trained MPC prediction model to initialize a control amount sequence of an internal primary air fan frequency based on the primary air fan frequency at the current time point in the incineration parameter by the MPC prediction model, wherein the control amount sequence comprises a plurality of time points. The first prediction unit is configured to predict, based on the evaporation amount expected value, a primary air fan frequency at a current time point and a current evaporation amount, the primary air fan frequency at the current time point and the evaporation amount prediction value at the current time point in the control quantity sequence by using the MPC model, and determine the primary air fan frequency at the current time point and the evaporation amount prediction value at the current time point as current to-be-predicted data; wherein the current time point refers to a first time point in the control quantity sequence; The second prediction unit is configured to input the current to-be-predicted data into the MPC prediction model to predict a primary air fan frequency at a next time point and an evaporation amount prediction value at the next time point; The first execution unit is configured to determine the primary air fan frequency at the next time point and the evaporation amount prediction value at the next time point as current to-be-predicted data, and return to execute inputting the current to-be-predicted data into the MPC prediction model to predict the primary air fan frequency at the next time point and the evaporation amount prediction value at the next time point, until the primary air fan frequencies at all time points and the evaporation amount prediction values at all time points in the control quantity sequence are predicted; The condition judgment unit is configured to judge whether the primary air fan frequencies at all time points and the evaporation amount prediction values at all time points in the control quantity sequence satisfy preset constraint conditions; The as unit is configured to, if the primary air fan frequencies at all time points and the evaporation amount prediction values at all time points in the control quantity sequence satisfy the preset constraint conditions, take the primary air fan frequency at the first time point in the control quantity sequence as the primary air fan frequency of the to-be-predicted waste incinerator at a next time point.

6. The system of claim 5, wherein, Further comprising: The first acquisition unit is configured to acquire a sample evaporation amount and a sample incineration parameter of a sample waste incinerator; The second input unit is configured to input the sample evaporation amount and the sample incineration parameter into an MPC prediction model to obtain a sample evaporation prediction value at a next time point and a sample primary air fan frequency of the sample waste incinerator at the next time point; The requirement judgment unit is configured to judge whether the sample evaporation prediction value and the sample primary air fan frequency satisfy actual requirements; The first determination unit is configured to, if the sample evaporation prediction value and the sample primary air fan frequency satisfy the actual requirements, determine the MPC prediction model as a trained MPC prediction model; The second determination unit is configured to, if the sample evaporation prediction value and the sample primary air fan frequency do not satisfy the actual requirements, adjust a weight parameter of the MPC prediction model, and return to execute inputting the sample evaporation amount and the sample incineration parameter into the MPC prediction model to obtain the sample evaporation prediction value at the next time point and the sample primary air fan frequency of the sample waste incinerator at the next time point.

7. The system of claim 6, wherein, The requirement judgment unit comprises: The judgment unit is configured to judge whether the sample primary air fan frequency conforms to ACC control air volume, and whether a weight parameter of the MPC prediction model conforms to preset requirements; The third determination unit is configured to, if the sample primary air fan frequency conforms to the ACC control air volume, and the weight parameter of the MPC prediction model conforms to the preset requirements, determine that the sample evaporation prediction value and the sample primary air fan frequency satisfy the actual requirements; The fourth determining unit is configured to determine that the sample evaporation prediction and the sample primary air fan frequency both do not meet actual requirements if the sample primary air fan frequency does not meet the ACC control air volume and the weight parameter of the MPC prediction model does not meet preset requirements.

8. The system of claim 5, wherein, The air volume control unit comprises: The second obtaining unit is configured to obtain parameters of each region in the garbage incinerator to be predicted. The distribution unit is configured to distribute primary air volume of the primary air fan to each region according to the parameters of each region and the primary air fan frequency. The control unit is configured to control combustion-supporting air of each region in the garbage incinerator to be predicted in the next moment respectively based on the primary air volume distributed to each region.

Images