Intelligent control method and equipment for urban solid waste incineration process, medium and product

Abstract

The invention discloses an intelligent control method and device for the urban solid waste incineration process, a medium and a product, and relates to the technical field of urban solid waste incineration. The method comprises the steps that the pusher speed, the fire grate speed, the primary air flow, the secondary air flow, the combustion time, the main steam flow and the furnace oxygen amount of the urban solid waste incineration process at the current moment are obtained; according to the pusher speed, the fire grate speed, the combustion time and the main steam flow at the current moment, the main steam flow at the next moment is determined through a main steam flow prediction model; according to the primary air flow, the secondary air flow and the furnace oxygen amount at the current moment, the furnace oxygen amount at the next moment is determined through a furnace oxygen amount prediction model; and in combination with a switching rule based on expert knowledge, a main steam flow controller and a furnace oxygen amount controller are solved by utilizing a gradient descent algorithm, and the optimal control rate is determined so as to control the urban solid waste incineration process. The solid waste treatment efficiency is improved, and rapid and stable control over the main steam flow and the furnace oxygen amount is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of municipal solid waste incineration, and in particular to an intelligent control method, equipment, medium and product for a municipal solid waste incineration process. Background Art

[0002] With China's rapid economic development and accelerating urbanization, the production of municipal solid waste has increased dramatically, and its treatment has become a focal point for environmental protection. Municipal solid waste incineration technology, with its significant volume and weight reduction, resource reuse, and comprehensive harmless treatment, has become the primary method for treating municipal solid waste in China. However, as waste sorting in China is still in its infancy, the calorific value of solid waste fluctuates significantly, leading to issues such as an unstable incineration process, low waste heat utilization efficiency, and high pollutant emission concentrations. Therefore, achieving process control over municipal solid waste incineration and improving both treatment efficiency and incineration stability are of great theoretical and practical significance. Summary of the Invention

[0003] The purpose of this application is to provide an intelligent control method, equipment, medium and product for the municipal solid waste incineration process to improve the solid waste treatment efficiency and the stability of the incineration process.

[0004] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides an intelligent control method for a municipal solid waste incineration process, comprising: Obtain the current pusher speed, current grate speed, current primary air flow, current secondary air flow, current combustion time, current main steam flow, and current furnace oxygen content of the municipal solid waste incineration process; Determine the main steam flow rate at the next moment using a main steam flow rate prediction model based on the current pusher speed, the current grate speed, the current combustion time, and the current main steam flow rate; wherein the main steam flow rate prediction model is obtained by training a fuzzy neural network using the first training data set; Determining the furnace oxygen level at the next moment using a furnace oxygen level prediction model based on the current primary air flow rate, the current secondary air flow rate, and the current furnace oxygen level; wherein the furnace oxygen level prediction model is obtained by training a fuzzy neural network using the second training data set; Based on the main steam flow rate at the next moment and the furnace oxygen volume at the next moment, combined with the switching rules based on expert knowledge, the gradient descent algorithm is used to solve the main steam flow controller and the furnace oxygen volume controller to determine the optimal control rate to control the municipal solid waste incineration process; the switching rules based on expert knowledge include the first rule, the second rule and the third rule; the first rule is that when the pressure after the primary air-air preheater at the current moment is greater than the first set pressure and less than the second set pressure, the learning rate of the main steam flow controller increases the set value, and the combustion time at the current moment decreases the set combustion time; the second rule is that when the change rate of the pressure after the primary air-air preheater at the current moment is greater than the third set pressure When the pressure is constant, it is determined that screening is currently in progress, and the solutions of the main steam flow controller and the furnace oxygen controller are executed, and the first rule is not executed. When the rate of change of the pressure after the primary air preheater at the current moment is less than the third set pressure, it is determined that incineration is currently in progress, and the solutions of the main steam flow controller and the furnace oxygen controller and the first rule are executed; the third rule is that when the difference between the main steam flow set value at the next moment and the main steam flow at the next moment is greater than the set difference, the pushing is delayed, and the combustion time at the current moment is increased by the set combustion time; the optimal control rate includes the pusher speed increment, the grate speed increment, the combustion time increment, the primary air flow increment and the secondary air flow increment.

[0005] Optionally, training the fuzzy neural network using the first training data set specifically includes: Obtain a first training data set; the first training data set includes a pusher speed at a historical moment, a grate speed at a historical moment, a combustion time at a historical moment, a main steam flow at a historical moment, and an actual value of the main steam flow at a corresponding moment during a training municipal solid waste incineration process; The historical pusher speed, grate speed, combustion time and main steam flow of the municipal solid waste incineration process are used as input, and the actual value of the main steam flow at the corresponding time is used as output. The fuzzy neural network is trained and the LM algorithm is used to update the model parameters of the fuzzy neural network to obtain the main steam flow prediction model.

[0006] Optionally, the pusher speed, grate speed, combustion time and main steam flow rate of the training municipal solid waste incineration process at historical moments are used as inputs, and the actual value of the main steam flow rate at the corresponding moment is used as output to train the fuzzy neural network, and the LM algorithm is used to update the model parameters of the fuzzy neural network to obtain a main steam flow prediction model, specifically including: Input the pusher speed, grate speed, combustion time and main steam flow at the historical moment into the current fuzzy neural network to obtain the main steam flow prediction value at the corresponding moment; Determine a loss function value according to a predicted value of the main steam flow at a corresponding moment and an actual value of the main steam flow at a corresponding moment; Determine whether the loss function value is less than the set threshold; If so, the current fuzzy neural network is used as the main steam flow prediction model; If not, the LM algorithm is used to update the model parameters of the current fuzzy neural network, and the result is "the pusher speed at the historical moment, the grate speed at the historical moment, the combustion time at the historical moment and the main steam flow at the historical moment are input into the current fuzzy neural network to obtain the predicted value of the main steam flow at the corresponding moment".

[0007] Optionally, the main steam flow controller is: ; in, is the main steam flow control rate increment at time t+1; , is the pusher speed increment at time t+1; is the grate speed increment at time t+1; is the combustion time increment at time t+1; T is the transpose; is the learning rate of the main steam flow controller at time t; is the objective function of the main steam flow controller; is the pusher speed at time t; is the grate speed at time t; is the burning time at time t.

[0008] Optionally, the objective function of the main steam flow controller is: ; in, for Main steam flow set value at the moment; for Main steam flow at the moment; is the main steam flow control rate at time t, .

[0009] Optionally, the furnace oxygen controller is: ; in, is the increment of furnace oxygen control rate at time t+1; , is the primary wind flow increment at time t+1; is the secondary air flow increment at time t+1; T is the transposition; is the learning rate of the furnace oxygen controller at time t; is the objective function of the furnace oxygen controller; is the primary wind flow at time t; is the secondary air flow at time t.

[0010] Optionally, the objective function of the furnace oxygen controller is: ; in, for The furnace oxygen setting value at the moment; for The oxygen content of the furnace at the moment; is the furnace oxygen control rate at time t, .

[0011] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-described intelligent control methods for the urban solid waste incineration process.

[0012] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned intelligent control methods for the urban solid waste incineration process.

[0013] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned intelligent control methods for the urban solid waste incineration process.

[0014] According to the specific embodiments provided in this application, this application has the following technical effects: The present application provides an intelligent control method, equipment, medium and product for a municipal solid waste incineration process, which obtains the pusher speed, grate speed, primary air flow, secondary air flow, combustion time, main steam flow and furnace oxygen content at the current moment of the municipal solid waste incineration process; determines the main steam flow at the next moment according to the pusher speed, grate speed, combustion time and main steam flow at the current moment; the main steam flow prediction model is obtained by training a fuzzy neural network using a first training data set; determines the furnace oxygen content at the next moment according to the primary air flow, secondary air flow and furnace oxygen content at the current moment using a furnace oxygen prediction model; the furnace oxygen prediction model is obtained by training a fuzzy neural network using a second training data set; based on the main steam flow and furnace oxygen content at the next moment, combined with a switching rule based on expert knowledge, the main steam flow controller and the furnace oxygen controller are solved using a gradient descent algorithm to determine the optimal control rate to control the municipal solid waste incineration process. Based on fuzzy neural networks, this application establishes accurate and effective main steam flow prediction models and furnace oxygen content prediction models. Combined with switching rules based on expert knowledge, the gradient descent algorithm is used to solve the optimal control rate of operating quantities such as pusher speed, grate speed, combustion time, primary air flow, and secondary air flow in real time, thereby improving the solid waste treatment efficiency and achieving rapid and stable control of the main steam flow and furnace oxygen content. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] Figure 1 A flow chart of an intelligent control method for a municipal solid waste incineration process provided in one embodiment of the present application; Figure 2 This is a flow chart of the practical application of the intelligent control method for the municipal solid waste incineration process of this application; Figure 3 This is a curve chart showing the prediction results of the main steam flow rate in the municipal solid waste incineration process; Figure 4 This is a curve chart showing the prediction results of the oxygen content in the furnace during the municipal solid waste incineration process; Figure 5 This is the main steam flow control effect diagram of the municipal solid waste incineration process; Figure 6 This is the effect diagram of the oxygen content control in the furnace of the municipal solid waste incineration process; Figure 7 This is a curve chart showing the control results of pusher speed, grate speed and combustion time in the municipal solid waste incineration process; Figure 8 This is a curve diagram of the primary air flow and secondary air flow control results in the municipal solid waste incineration process; Figure 9 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0018] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0019] This application relates to a data- and knowledge-driven intelligent autonomous control method for the municipal solid waste incineration process (i.e., an intelligent control method for the municipal solid waste incineration process). This method establishes a prediction model for the main steam flow rate and the furnace oxygen content in the municipal solid waste incineration process, and designs a model predictive control strategy that automatically adjusts the primary air flow, secondary air flow, pusher speed, grate speed, and combustion time. It also incorporates multiple switching rules based on expert knowledge to improve the controller's control performance during unstable conditions and achieve tracking control of the furnace oxygen content and main steam flow rate. This application pertains to both the field of municipal solid waste management and the field of intelligent control.

[0020] In an exemplary embodiment, Figure 1 As shown, a method for intelligent control of a municipal solid waste incineration process is provided, comprising the following steps: S1: Obtain the current pusher speed, current grate speed, current primary air flow, current secondary air flow, current combustion time, current main steam flow and current furnace oxygen content of the municipal solid waste incineration process.

[0021] S2: Determine the main steam flow at the next moment using a main steam flow prediction model based on the current pusher speed, the current grate speed, the current combustion time, and the current main steam flow; wherein the main steam flow prediction model is obtained by training the fuzzy neural network using the first training data set.

[0022] As an optional implementation, training the fuzzy neural network using the first training data set specifically includes: S21: Obtain a first training data set; the first training data set includes the pusher speed, grate speed, combustion time, main steam flow rate and actual value of the main steam flow rate at the corresponding time during the training of the municipal solid waste incineration process at the historical moment.

[0023] S22: Taking the historical pusher speed, grate speed, combustion time and main steam flow of the municipal solid waste incineration process as input, and the actual value of the main steam flow at the corresponding time as output, the fuzzy neural network is trained, and the LM algorithm is used to update the model parameters of the fuzzy neural network to obtain the main steam flow prediction model.

[0024] As an optional implementation, S22 specifically includes: S221: Input the pusher speed, grate speed, combustion time and main steam flow at the historical moment into the current fuzzy neural network to obtain the main steam flow prediction value at the corresponding moment.

[0025] S222: Determine a loss function value according to the main steam flow rate prediction value at the corresponding moment and the main steam flow rate actual value at the corresponding moment.

[0026] S223: Determine whether the loss function value is less than a set threshold.

[0027] S224: If yes, the current fuzzy neural network is used as the main steam flow prediction model.

[0028] S225: If not, the LM algorithm is used to update the model parameters of the current fuzzy neural network, and the result is "the pusher speed at the historical moment, the grate speed at the historical moment, the combustion time at the historical moment and the main steam flow at the historical moment are input into the current fuzzy neural network to obtain the predicted value of the main steam flow at the corresponding moment".

[0029] S3: Determine the furnace oxygen content at the next moment based on the current primary air flow, the current secondary air flow, and the current furnace oxygen content using a furnace oxygen content prediction model; wherein the furnace oxygen content prediction model is obtained by training a fuzzy neural network using the second training data set.

[0030] In practical applications, the construction process of the main steam flow prediction model and the furnace oxygen quantity prediction model is as follows: 1. Data collection. Collect historical data on the pusher speed, grate speed, combustion time, main steam flow rate, actual main steam flow rate at the corresponding time, primary air flow rate, secondary air flow rate, and actual furnace oxygen content at the corresponding time for the historical municipal solid waste incineration process (for training).

[0031] 2. Determine the input and output variables of the operation index model (main steam flow prediction model and furnace oxygen quantity prediction model) and establish the corresponding prediction model: Determine the input variables and corresponding output variables of the main steam flow prediction model and the furnace oxygen quantity prediction model, and use fuzzy neural network (FNN) to establish the operation index model respectively.

[0032] (1) Determine the input variables of each operating indicator model: Since the main steam flow prediction model and furnace oxygen quantity prediction model for the municipal solid waste incineration process established include the main operating variables, the main operating variables of the municipal solid waste incineration plant using a reverse grate furnace are the pusher speed, grate speed, primary air flow, secondary air flow, and combustion time. Among them, the pusher speed and grate speed mainly affect the feeding speed, the combustion time mainly affects the feeding frequency, and the primary air flow and secondary air flow mainly affect the oxygen supply during the combustion process. Based on the above rules, the input and output variables of the main steam flow prediction model and the furnace oxygen quantity prediction model are: The input variables of the main steam flow prediction model are , input dimension ,in, is the pusher speed, is the grate speed, For burning time, Main steam flow rate. Output variable is the predicted main steam flow at the next moment.

[0033] The input variables of the furnace oxygen content prediction model are , input dimension ,in, For the primary air flow, is the secondary air flow, is the amount of oxygen in the furnace. Output variable It is the predicted furnace oxygen content at the next moment.

[0034] (2) Fuzzy neural network FNN is used to establish the main steam flow prediction model and furnace oxygen quantity prediction model. The method is as follows: The FNN-based model can be expressed as: (1) in, is the number of prediction models, is the first The prediction output of the prediction model, for Moment The input of the prediction model, for Moment The prediction model input, For the The number of input variables of a prediction model, is the number of fuzzy rules of FNN, for Moment Prediction model input and The center of the membership function; for Moment Prediction model input and The width of the membership function. is the sampling time of the municipal solid waste incineration process.

[0035] For the A first-order Takagi-Sugeno-Kang (TSK) fuzzy rule, defined as: (2) in, and for Moment The prediction model The 0th coefficient and the coefficients.

[0036] For the The center of the prediction model ,width and fuzzy rule coefficients , whose value is yet to be determined and is solved by the online learning algorithm given by formula (4)-formula (7).

[0037] Regular evaluation is used to test the accuracy of the model. The Mean Absolute Percentage Error (MAPE) can accurately measure the accuracy of the model. Moment prediction models for: (3) in, for Moment The prediction output of the prediction model, for Moment The expected output of a prediction model, The amount of data used to train the model.

[0038] Setting model accuracy thresholds ,like , then the model accuracy is higher, keep the model unchanged, if , the model accuracy is low and online learning is needed to update the model.

[0039] The loss function of the model online learning can be defined as: (4) in, for Moment The loss function of the prediction model is for Moment The prediction output error of a prediction model.

[0040] An adaptive Levenberg-Marquardt (LM) algorithm is proposed to update model parameters. The parameter update method is: (5) in, is the number of iterations of the adaptive LM algorithm, is the maximum number of iterations of the adaptive LM algorithm, is the identity matrix, The adaptive LM algorithm The first iteration The parameter matrix of the prediction model; for Moment The first iteration prediction model inputs and the center of the membership function; for Moment The first iteration The width of the prediction model input and membership function; for Moment The first iteration The fuzzy rule coefficients of the prediction model. For the The adaptive learning rate of the k-th prediction model at the iteration; and They are Moment The first iteration The Hessian matrix and gradient vector of the prediction model are defined as: (6) in, for Moment The first iteration The loss function of the prediction model is for Moment The first iteration The prediction output error of the prediction model. T is the transpose; for Moment The first iteration The Jacobian matrix of the prediction model is defined as: (7) in, for Moment The first iteration Prediction model input and The center of the membership function; for Moment The first iteration Prediction model input and The width of the membership function; for Moment The first iteration The prediction model The first order TSK fuzzy rule coefficients; for Moment The first iteration The center of the n-th input and r-th membership function of the prediction model; for Moment The first iteration The width of the n-th input and r-th membership function of the prediction model; for Moment The first iteration The nth coefficient of the rth first-order TSK fuzzy rule of the prediction model.

[0041] (8) in, is the first The first iteration The prediction output of a prediction model; for Moment Prediction model input, for Moment Prediction model input and The center of the membership function; for Moment Prediction model input and The width of the membership function.

[0042] (9) (10) Adaptive LM algorithm The adaptive learning rate of the k-th prediction model at the iteration for: (11) in, is the two-norm, is a constant, .

[0043] S4: Based on the main steam flow rate at the next moment and the furnace oxygen volume at the next moment, combined with the switching rules based on expert knowledge, the gradient descent algorithm is used to solve the main steam flow controller and the furnace oxygen volume controller to determine the optimal control rate to control the municipal solid waste incineration process; the switching rules based on expert knowledge include the first rule, the second rule and the third rule; the first rule is that when the pressure after the primary air-air preheater at the current moment is greater than the first set pressure and less than the second set pressure, the learning rate of the main steam flow controller increases by the set value, and the combustion time at the current moment decreases by the set combustion time; the second rule is that when the change rate of the pressure after the primary air-air preheater at the current moment is greater than the third ... When the pressure is set, it is determined that screening is currently in progress, the main steam flow controller and the furnace oxygen controller are solved, and the first rule is not executed. When the rate of change of the pressure after the primary air preheater at the current moment is less than the third set pressure, it is determined that incineration is currently in progress, and the main steam flow controller and the furnace oxygen controller are solved as well as the first rule. The third rule is that when the difference between the main steam flow set value at the next moment and the main steam flow at the next moment is greater than the set difference, the pushing of the material is delayed, and the combustion time at the current moment is increased by the set combustion time. The optimal control rate includes the pusher speed increment, the grate speed increment, the combustion time increment, the primary air flow increment and the secondary air flow increment.

[0044] like Figure 2As shown in the figure, in actual application, DCS (Distributed Control System) data is first collected and stored. The DCS data is then determined to determine whether the main steam flow prediction model and the furnace oxygen quantity prediction model are compatible. If so, the main steam flow prediction model is used to predict the main steam flow and the deviation between the main steam flow and the setpoint is calculated. The control ratios for the pusher speed, grate speed, and combustion time are then calculated. Based on the current control ratios, given the pusher speed, grate speed, and combustion time, the on-site operation results are output. While predicting the main steam flow, the furnace oxygen quantity is also predicted using the furnace oxygen quantity prediction model and the deviation between the furnace oxygen quantity and the setpoint is calculated. The control ratios for the primary and secondary air flow rates are then calculated. Based on the current control ratios, given the primary and secondary air valve openings, the on-site operation results are output. If not, the parameters of the main steam flow prediction model and the roadmap prediction model are updated before the main steam flow and furnace oxygen quantity predictions and subsequent steps are performed.

[0045] In practical applications, a main steam flow controller and a furnace oxygen controller are established, and switching rules are established based on expert knowledge (i.e., switching rules based on expert knowledge) to solve the optimal control rate and achieve stable and rapid tracking control of the main steam flow and furnace oxygen.

[0046] (1) The objective function of the tracking control of the main steam flow controller is: (12) in, is the objective function of the main steam flow controller; for Main steam flow set value at the moment; for Main steam flow at the moment; is the main steam flow control rate at time t, ; is the pusher speed at time t; is the grate speed at time t; is the burning time at time t.

[0047] The control rate is updated as: (13) in, is the main steam flow control rate increment at time t+1; , is the pusher speed increment at time t+1; is the grate speed increment at time t+1; is the combustion time increment at time t+1. The main steam flow control rate increment is solved as: (14) in, is the learning rate of the main steam flow controller at time t. , the main steam flow control rate increment is specifically: (15) (16) (17) in, It is the prediction output of the main steam flow prediction model at time t+1.

[0048] Through the above continuous iterations, main steam flow tracking control is achieved.

[0049] (2) The objective function of the furnace oxygen controller for tracking control is: (18) in, is the objective function of the furnace oxygen controller; for The furnace oxygen setting value at the moment; for The oxygen content of the furnace at the moment; is the furnace oxygen control rate at time t, ; is the primary wind flow at time t; is the secondary air flow at time t.

[0050] The control rate is updated as: (19) in, is the increment of furnace oxygen control rate at time t+1; , is the primary wind flow increment at time t+1; is the secondary air flow increment at time t+1. The furnace oxygen control rate increment is solved as: (20) in, is the learning rate of the furnace oxygen controller at time t, , the specific increment of furnace oxygen control rate is: (twenty one) (twenty two) in, It is the predicted output of the furnace oxygen content prediction model at time t+1.

[0051] Through the above continuous iterations, the furnace oxygen content tracking control is achieved.

[0052] (3) Switching rules based on expert knowledge.

[0053] Due to the large fluctuations in the municipal solid waste incineration process, the controller may not respond in a timely manner. In order to further improve the response speed and stability of the controller, based on the experience of on-site operators, a switching rule based on expert knowledge is formulated and combined with a model predictive control method to improve the control effect.

[0054] 1) Pressure after primary air preheater It is an important reference to show the amount of solid waste pushed in each time and the amount reduced with incineration. After each push, Raise and push material once The temperature will rise by about 70Pa to 120Pa. As the burning progresses, It gradually decreases and eventually returns to its initial state. Based on the above expert experience, the first rule is established: when the current pressure after the primary air preheater is greater than the first set pressure and less than the second set pressure, the learning rate of the main steam flow controller increases by the set value, and the current combustion time decreases by the set combustion time.

[0055] In this embodiment, the first rule is as follows: like , then increase the learning rate of the main steam flow controller And reduce burning time .

[0056] 2) During the on-site operation, there is a screening process. Every half an hour, the ash accumulated in the air chamber is blown out of the air chamber horizontally for about 30 seconds. There will be violent fluctuations, when screening begins, Rapidly reduce about 300Pa to 400Pa, and when the screening is finished, Quickly return to the state before screening. The judgment of changes causes interference and may lead to the misjudgment that the solid waste entering the furnace has been completely incinerated. Based on the above expert knowledge, the second rule is established. When the rate of change of the pressure after the primary air-air preheater at the current moment is greater than the third set pressure, it is determined that screening is currently in progress, and the main steam flow controller and the furnace oxygen controller are solved, and the first rule is not executed. When the rate of change of the pressure after the primary air-air preheater at the current moment is less than the third set pressure, it is determined that incineration is currently in progress, and the main steam flow controller and the furnace oxygen controller are solved as well as the first rule.

[0057] In this embodiment, the second rule is as follows: like , then the material is currently being screened, and only the controller operation is executed at this time, and the first rule is not executed. , it is a normal combustion situation, executing the controller operation and the first rule.

[0058] 3) There is a long lag between solid waste incineration and main steam flow, and the controller has a certain lag in tracking the main steam flow. When solid waste is incinerated, the main steam flow increases with a lag, and the incineration time will be delayed if the controller is relied upon alone. Given a low value, the controller responds slowly when the main steam flow increases, resulting in premature material pushing. Based on the above expert knowledge, a third rule is established. When the difference between the main steam flow set value at the next moment and the main steam flow at the next moment is greater than the set difference, the material pushing is delayed, and the combustion time at the current moment is increased by the set combustion time.

[0059] In this embodiment, the third rule is as follows: like At this time, the main steam flow is at a high state, so the material pushing should be delayed. .

[0060] The above expert rules ensure the control response speed in boundary conditions, avoiding the situation where the material layer continues to thicken or thin. In non-boundary conditions, the model predictive control method is used to achieve stable tracking control.

[0061] This application uses the collected historical data to establish a main steam flow prediction model and a furnace oxygen content prediction model for the municipal solid waste incineration process. As an embodiment, actual data from a municipal solid waste incineration plant in Beijing are used to verify the effectiveness of the method proposed in this application. The original data sampling interval is 30 seconds, and a total of 1500 groups of experimental data are collected. The variables required to establish the main steam flow prediction model and the furnace oxygen content prediction model are extracted. The 1500 groups of data are used for pre-training of the prediction model, and the main steam flow and furnace oxygen content control effects of the municipal solid waste incineration process are tested under any initial values.

[0062] (1) Establish a main steam flow prediction model and a furnace oxygen quantity prediction model based on fuzzy neural network. Based on 1000 sets of historical data, the adaptive LM algorithm is used to train the main steam flow prediction model and the furnace oxygen quantity prediction model. The prediction results of the main steam flow are as follows: Figure 3 As shown, X-axis: time, unit is 30 seconds, Y-axis: main steam flow, unit is t / h. The prediction results of furnace oxygen content are as follows Figure 4 As shown, X-axis: time, unit is 30 seconds, Y-axis: furnace oxygen content, unit is %.

[0063] (2) Based on the obtained main steam flow prediction model and furnace oxygen content prediction model for the municipal solid waste incineration process, the optimal control rate is solved by using the switching rule based on expert knowledge. The setting value of the main steam flow is given in the order of 75t / h, 78t / h, 76t / h, 74t / h, and 72t / h every 5 hours. The setting value of the furnace oxygen content is given in the order of 5.5%, 7%, 5%, 6%, and 4.5% every 5 hours. The main steam flow control effect of the municipal solid waste incineration process is shown in Figure 2. Figure 5 As shown, the X axis is time, the unit is 30 seconds, the Y axis is the main steam flow, the unit is t / h. Figure 6 As shown, X-axis: time, unit is 30 seconds, Y-axis: furnace oxygen content, unit is %. The control results of pusher speed, grate speed and combustion time in the process of municipal solid waste incineration are shown as follows: Figure 7 As shown, X-axis: time, unit is 30 seconds, Y-axis: pusher speed, unit is %, grate speed, unit is %, combustion time, unit is second. The control results of primary air flow and secondary air flow in the process of municipal solid waste incineration are shown in Figure 2. Figure 8 As shown, X axis: time, unit is 30 seconds, Y axis: primary air flow, unit is m 3 / h, secondary air flow rate, unit is m 3 / h.

[0064] (3) The MAPE was used to quantitatively evaluate the accuracy of the prediction model. The calculation results showed that the MAPE of the main steam flow prediction model was 1.45%, with a prediction accuracy of 98.55%. The MAPE of the furnace oxygen quantity prediction model was 4.09%, with a prediction accuracy of 95.91%. The control effect was quantitatively evaluated using the Integral Absolute Error (IAE). The calculation results showed that the IAE of the main steam flow control was 0.0328, with a control accuracy of 96.72%. The IAE of the furnace oxygen quantity control was 0.041, with a control accuracy of 95.9%.

[0065] This application establishes accurate and effective main steam flow prediction models and furnace oxygen content prediction models. By solving the optimal control rate of operating quantities such as pusher speed, grate speed, combustion time, primary air flow, and secondary air flow in real time, rapid and stable control of main steam flow and furnace oxygen content is achieved, which is of great significance to the stable operation and sustainable development of the urban solid waste incineration process.

[0066] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned intelligent control method for the municipal solid waste incineration process when executing the computer program.

[0067] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the above-mentioned intelligent control method for the municipal solid waste incineration process.

[0068] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned intelligent control method for the municipal solid waste incineration process when executed by a processor.

[0069] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an intelligent control method for a municipal solid waste incineration process is realized.

[0070] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0072] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0073] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0074] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0075] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. An intelligent control method for municipal solid waste incineration process, characterized in that: include: Obtain the current pusher speed, current grate speed, current primary air flow, current secondary air flow, current combustion time, current main steam flow, and current furnace oxygen content of the municipal solid waste incineration process; Determine the main steam flow rate at the next moment using a main steam flow rate prediction model based on the current pusher speed, the current grate speed, the current combustion time, and the current main steam flow rate; wherein the main steam flow rate prediction model is obtained by training a fuzzy neural network using the first training data set; Determining the furnace oxygen level at the next moment using a furnace oxygen level prediction model based on the current primary air flow rate, the current secondary air flow rate, and the current furnace oxygen level; wherein the furnace oxygen level prediction model is obtained by training a fuzzy neural network using the second training data set; Based on the main steam flow rate at the next moment and the furnace oxygen volume at the next moment, combined with the switching rules based on expert knowledge, the gradient descent algorithm is used to solve the main steam flow controller and the furnace oxygen volume controller to determine the optimal control rate to control the municipal solid waste incineration process; the switching rules based on expert knowledge include the first rule, the second rule and the third rule; the first rule is that when the pressure after the primary air-air preheater at the current moment is greater than the first set pressure and less than the second set pressure, the learning rate of the main steam flow controller increases the set value, and the combustion time at the current moment decreases the set combustion time; the second rule is that when the change rate of the pressure after the primary air-air preheater at the current moment is greater than the third set pressure When the pressure is constant, it is determined that screening is currently in progress, and the solutions of the main steam flow controller and the furnace oxygen controller are executed, and the first rule is not executed. When the rate of change of the pressure after the primary air preheater at the current moment is less than the third set pressure, it is determined that incineration is currently in progress, and the solutions of the main steam flow controller and the furnace oxygen controller and the first rule are executed; the third rule is that when the difference between the main steam flow set value at the next moment and the main steam flow at the next moment is greater than the set difference, the pushing is delayed, and the combustion time at the current moment is increased by the set combustion time; the optimal control rate includes the pusher speed increment, the grate speed increment, the combustion time increment, the primary air flow increment and the secondary air flow increment.

2. The intelligent control method for municipal solid waste incineration process according to claim 1 is characterized in that: The fuzzy neural network is trained using the first training data set, specifically including: Obtain a first training data set; the first training data set includes a pusher speed at a historical moment, a grate speed at a historical moment, a combustion time at a historical moment, a main steam flow at a historical moment, and an actual value of the main steam flow at a corresponding moment during a training municipal solid waste incineration process; The historical pusher speed, grate speed, combustion time and main steam flow of the municipal solid waste incineration process are used as input, and the actual value of the main steam flow at the corresponding time is used as output. The fuzzy neural network is trained and the LM algorithm is used to update the model parameters of the fuzzy neural network to obtain the main steam flow prediction model.

3. The intelligent control method for municipal solid waste incineration process according to claim 2 is characterized in that: The historical pusher speed, grate speed, combustion time and main steam flow rate of the municipal solid waste incineration process are used as inputs, and the actual value of the main steam flow rate at the corresponding time is used as output. The fuzzy neural network is trained and the LM algorithm is used to update the model parameters of the fuzzy neural network to obtain the main steam flow prediction model. Specifically, the following steps are involved: Input the pusher speed, grate speed, combustion time and main steam flow at the historical moment into the current fuzzy neural network to obtain the main steam flow prediction value at the corresponding moment; Determine a loss function value according to a predicted value of the main steam flow at a corresponding moment and an actual value of the main steam flow at a corresponding moment; Determine whether the loss function value is less than the set threshold; If so, the current fuzzy neural network is used as the main steam flow prediction model; If not, the LM algorithm is used to update the model parameters of the current fuzzy neural network, and the result is "input the pusher speed, grate speed, combustion time and main steam flow at the historical moment into the current fuzzy neural network to obtain the predicted value of the main steam flow at the corresponding moment".

4. The intelligent control method for municipal solid waste incineration process according to claim 1 is characterized in that: The main steam flow controller is: ； in, is the main steam flow control rate increment at time t+1; , is the pusher speed increment at time t+1; is the grate speed increment at time t+1; is the combustion time increment at time t+1; T is the transpose; is the learning rate of the main steam flow controller at time t; is the objective function of the main steam flow controller; is the pusher speed at time t; is the grate speed at time t; is the burning time at time t.

5. The intelligent control method for municipal solid waste incineration process according to claim 4 is characterized in that: The objective function of the main steam flow controller is: ； in, for Main steam flow set value at the moment; for Main steam flow at the moment; is the main steam flow control rate at time t, .

6. The intelligent control method for municipal solid waste incineration process according to claim 1, characterized in that: The furnace oxygen controller is: ； in, is the increment of furnace oxygen control rate at time t+1; , is the primary wind flow increment at time t+1; is the secondary air flow increment at time t+1; T is the transposition; is the learning rate of the furnace oxygen controller at time t; is the objective function of the furnace oxygen controller; is the primary wind flow at time t; is the secondary air flow at time t.

7. The intelligent control method for municipal solid waste incineration process according to claim 6, characterized in that: The objective function of the furnace oxygen controller is: ； in, for The furnace oxygen setting value at the moment; for The oxygen content of the furnace at the moment; is the furnace oxygen control rate at time t, .

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent control method for the urban solid waste incineration process according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the intelligent control method for the urban solid waste incineration process according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the intelligent control method for the urban solid waste incineration process according to any one of claims 1 to 7 is implemented.

Images