Incineration heat hierarchical utilization method based on energy quality matching

Abstract

The application belongs to the technical field of waste incineration, more particularly to an incineration heat graded utilization method based on energy quality matching. The application breaks through the limitation of fixed pressure grade, establishes accurate mapping of steam quality and energy utilization scene based on real-time thermodynamic calculation of real-time steam parameters and real-time dynamic grading decision. Secondly, a steam demand dynamic response model is constructed through an LSTM load prediction module to identify the supply-demand gap of steam of different qualities in advance and form a priority allocation matrix. Finally, a multi-level optimization system with the goal of maximizing economic benefits and minimizing heat loss is constructed by combining a fuzzy PID control engine and a three-level path switching mechanism, so as to realize optimal dynamic matching of steam parameters and energy utilization equipment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of waste incineration, more specifically, relates to an incineration heat hierarchical utilization method based on energy and quality matching. BACKGROUND

[0002] With the acceleration of urbanization, waste incineration for power generation has become a core means of municipal solid waste treatment and energy recovery; in the incineration process, waste heat is converted into steam through a waste heat boiler to drive a steam turbine unit for power generation, and part of the steam is extracted for plant heating or municipal heating, forming a typical energy cascade utilization system.

[0003] The traditional system generally adopts a fixed pressure distribution mode, divides the steam network into three fixed pressure levels (such as 5MPa, 2.5MPa, 0.8MPa) of high pressure, medium pressure and low pressure, and adjusts the steam parameters through mechanical pressure reducing valves. However, due to the large fluctuation of waste heat value (4,200-9,600kJ / kg), the steam production dynamically changes with the working condition, resulting in forced degradation of high-grade steam. SUMMARY

[0004] The application provides an incineration heat hierarchical utilization method based on energy and quality matching, which aims to solve the technical problem of forced degradation of high-grade steam caused by the traditional method.

[0005] The incineration heat hierarchical utilization method based on energy and quality matching comprises the following steps:

[0006] Data acquisition and preprocessing: collect the steam parameters of the incineration boiler and user demand data, and preprocess the collected data to obtain the preprocessed steam parameters of the incineration boiler and user demand data;

[0007] Enthalpy and entropy calculation and dynamic hierarchical decision: based on the preprocessed steam parameters of the incineration boiler, the enthalpy value of the steam is calculated according to the thermodynamic model, and then the entropy value of the steam is calculated according to the enthalpy value of the steam; the steam is divided into three levels through the enthalpy value and the entropy value, and the steam level is obtained, and the steam level is determined based on the calculated enthalpy value and the entropy value;

[0008] Load prediction and demand matching: based on the steam level, historical load data and external data, the future power generation demand and heat load demand are output by using the LSTM load prediction module; then, the supply-demand gap of each steam level is calculated according to the prediction result, the priority allocation suggestion is generated, and the future and heat demand prediction curve and the steam distribution priority matrix are obtained;

[0009] Multi-objective optimization and control instruction generation: based on the results of steam grade, load prediction and demand matching, and real-time equipment state, based on fuzzy PID control engine and three-level path intelligent switching mechanism, using dynamically adjusted three-dimensional fuzzy rule base to optimize PID parameters in real time, taking maximizing economic benefit and quality loss balance as objective function, realizing steam distribution through hierarchical control strategy.

[0010] The application breaks through the fixed pressure grade limit, establishes the accurate mapping of steam quality and energy use scene based on real-time thermodynamic calculation of steam parameters for real-time dynamic hierarchical decision-making; secondly, a steam demand dynamic response model is constructed through an LSTM load prediction module to identify the supply-demand gap of steam of different qualities in advance and form a priority allocation matrix; finally, a multi-level optimization system with the goal of maximizing economic benefit and minimizing quality loss is constructed by combining a fuzzy PID control engine and a three-level path switching mechanism, realizing optimal dynamic matching of steam parameters and energy-using equipment.

[0011] Preferably, before calculating the enthalpy value, moving average filtering is used to moving average filter the pressure and temperature in the steam parameters; whether it is in a transition state is identified based on the moving average filtered data; wherein in the process of transitioning from one grade to another, the stage in which the pressure and temperature are unstable, the determination of the transition state is based on a set threshold value, if it belongs to the transition state, it is marked as a transition state;

[0012] In the determination process of the steam grade, the transition state is introduced, and a fuzzy logic method is used to compensate the grade of the steam, in the case of transition state, if the deviation of pressure and temperature is less than the threshold value, the current grade is maintained; if the deviation is greater than the threshold value, the grade is allowed to switch.

[0013] Preferably, the steps of prediction by the LSTM load prediction module are as follows:

[0014] Before prediction, time series alignment and aggregation are performed on the data, all data are time series aligned, and sliding average method is used for aggregation for steam data, so that the time series of other data are aligned;

[0015] Feature construction is performed on the data based on time alignment and aggregation, including steam grade proportion, meteorological compensation factor and production plan weight, wherein the steam grade proportion is the proportion of steam of different grades in the total steam flow; the meteorological compensation factor is a compensation coefficient constructed according to the influence of outdoor temperature on steam demand; the production plan weight is the normalized garbage treatment amount, reflecting the influence of production intensity on steam generation;

[0016] A standardized feature matrix is constructed based on the time-aligned and aggregated data and the data constructed from the features, the standardized feature matrix is taken as the input of the LSTM load prediction module, prediction is performed based on the LSTM load prediction module, and future power generation demand and heat supply demand are obtained;

[0017] The LSTM load prediction module includes an LSTM layer, an Attention layer, and a fully connected layer; the Attention layer dynamically calculates the contribution weight of the time step in the sequence to the current prediction from the output of the LSTM layer, obtains a weighted time sequence, and then maps the output to the predicted value of the power generation and heat supply demand through the fully connected layer.

[0018] Preferably, the step of generating the priority allocation suggestion is as follows:

[0019] Demand-steam conversion: according to the turbine efficiency and the enthalpy value of high-pressure steam, the required high-pressure steam flow is calculated; according to the temperature difference of supply and return water and the specific heat capacity, the required medium-pressure steam flow is calculated;

[0020] Gap rate calculation: the difference between the power generation steam demand and the actual high-pressure steam flow is calculated to reflect the supply-demand gap of high-pressure steam; the difference between the heat supply steam demand and the actual medium-pressure steam flow is calculated to reflect the supply-demand gap of medium-pressure steam; the difference between the actual low-pressure steam flow and the leachate treatment demand is calculated to reflect the excess of low-pressure steam;

[0021] Priority dynamic weight allocation: the power generation weight is dynamically adjusted according to the grid frequency deviation; the heat supply weight is dynamically adjusted according to the device fouling condition; the leachate weight is dynamically adjusted according to the low-pressure steam flow;

[0022] The obtained weight and gap rate are combined to generate a weight coefficient, and then a steam allocation priority matrix is obtained, which includes the weight coefficients of power generation, heat supply, and leachate treatment.

[0023] Preferably, the fuzzy PID control engine includes the following processing steps:

[0024] Fuzzy rule matching: the input load deviation, deviation change rate, and device health index are fuzzified by a pre-set fuzzy rule library;

[0025] PID parameter adjustment: the PID parameters are adjusted according to the PID parameter adjustment amount output by the fuzzy rule, and preliminary PID parameters are obtained;

[0026] Objective function optimization: taking the maximization of the balance between comprehensive income and quality loss as the objective function, the preliminary PID parameters are used to find the optimal PID parameters that satisfy the objective function through gradient descent iteration.

[0027] Preferably, the three-level path intelligent switching mechanism comprises a high-pressure steam path, a medium-pressure steam path and a low-pressure steam path.

[0028] The high-pressure steam path stabilizes power grid fluctuations through linear adjustment of the steam intake of the back pressure unit by monitoring the frequency deviation of the power grid in real time; if the frequency deviation exceeds the threshold of ±0.2 Hz, the heat accumulator is immediately started to store heat.

[0029] The medium-pressure steam path adopts a feedforward-feedback composite control, wherein the feedforward control adjusts the heating valve opening degree in advance based on the predicted heating demand; the feedback control fine-tunes the heating valve opening degree with a period of ≤5 seconds based on the optimized PID parameters to eliminate real-time heating temperature / flow deviation.

[0030] The low-pressure steam path calculates the heat transfer coefficient of the evaporator in real time, automatically switches to the standby evaporation unit if the efficiency is lower than 85%, and increases the steam distribution amount to compensate for the efficiency loss; and dynamically intercepts low-pressure steam resources according to the priority matrix.

[0031] Preferably, it further comprises feedback correction, compares the instruction with the execution result, calculates the cumulative deviation, and if the cumulative deviation is less than or equal to the preset deviation threshold, triggers the PID parameter adjustment based on the gradient descent method.

[0032] If the cumulative deviation is greater than the preset deviation threshold, expert diagnosis is performed.

[0033] The beneficial effects of the present application include:

[0034] The present application breaks through the limitation of fixed pressure level by making real-time dynamic hierarchical decisions based on real-time thermodynamic calculation of steam parameters, and establishes a precise mapping of steam quality and energy use scenarios; secondly, a dynamic response model of steam demand is constructed through the LSTM load prediction module to identify the supply-demand gap of steam of different qualities in advance, and a priority allocation matrix is formed; finally, a multi-level optimization system with the goal of maximizing economic benefits and minimizing heat loss is constructed by combining the fuzzy PID control engine and the three-level path switching mechanism, so as to realize the optimal dynamic matching of steam parameters and energy-using equipment. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Figure 1 The overall step block diagram provided by the embodiments of the present application.

[0037] Figure 2The specific step block diagram of step S2 provided for the embodiment of the present application is shown in the following.

[0038] Figure 3 The specific step block diagram of step S3 provided for the embodiment of the present application is shown in the following.

[0039] Figure 4 The specific step block diagram of step S4 provided for the embodiment of the present application is shown in the following. DETAILED DESCRIPTION

[0040] In order to make the technical problems, technical solutions and beneficial effects of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0041] Referring to Figure 1 Based on the incineration heat hierarchical utilization method capable of matching energy quality, the method comprises the following steps:

[0042] S1. Data acquisition and preprocessing: collecting incineration boiler steam parameters and user demand data, and preprocessing the collected data to obtain preprocessed incineration boiler steam parameters and user demand data;

[0043] The incineration boiler steam parameters include the pressure, temperature and flow rate of the incineration boiler outlet steam parameters; the user side demand parameters include power grid dispatching instructions (frequency, power demand), heating pipe network pressure and leachate treatment capacity;

[0044] The preprocessing includes abnormal value detection, time synchronization and the like, so as to ensure the data quality. The preprocessing performed in order to ensure the data quality is a conventional technical means in the art, and thus will not be described in detail herein

[0045] S2. Enthalpy and entropy calculation and dynamic hierarchical decision: based on the preprocessed incineration boiler steam parameters, the enthalpy value of the steam is calculated according to a thermodynamic model, and then the entropy value of the steam is calculated according to the enthalpy value of the steam; the steam is divided into three levels through the enthalpy value and the entropy value to obtain the steam level, and the steam level is determined based on the calculated enthalpy value and the entropy value;

[0046] Referring to Figure 2 First, in order to eliminate sensor noise and smooth the data, a sliding window technique is used to smooth the real-time steam pressure and temperature, wherein the window length is 30 seconds and the period is 10 seconds, and the smoothed data is obtained based on the moving average filtering;

[0047] Based on the smoothed data, according to the changes of the pressure and the temperature, it is judged whether it is in a transition state, and the definition of the boundary zone is determined according to the threshold values of the pressure and the temperature:

[0048] High pressure / medium pressure boundary: ;

[0049] Medium pressure / low pressure boundary: ;

[0050] Temperature boundary: ;

[0051] Wherein the identification rules of transition state are as follows:

[0052] If or , it is marked as a transition state; wherein represents the steam pressure at time t; represents the steam temperature at time t;

[0053] The specific enthalpy and specific entropy of steam are calculated, and the energy quality of steam is quantified based on the specific enthalpy and specific entropy:

[0054] Wherein the specific enthalpy of steam is calculated according to the simplified model of IAPWS-IF97 standard, and the specific expression is as follows:

[0055] ;

[0056] In the formula: represents the specific heat capacity at constant pressure; represents the density of steam; represents the latent heat of phase change; represents the pressure correction factor, and e represents the base number of natural logarithm;

[0057] Steam specific entropy calculation:

[0058] ;

[0059] In the formula: represents the specific enthalpy under the reference environmental condition; represents the specific entropy under the reference environmental condition; h represents the calculated specific enthalpy value; represents the calculated specific entropy value; wherein the specific entropy of steam is calculated based on the following formula:

[0060] ;

[0061] In the formula: represents the specific entropy of steam; represents the reference environmental temperature; represents the filtered temperature; R represents the gas constant of water vapor; represents the filtered steam pressure; represents the reference environmental pressure;

[0062] Dynamic classification decision: According to the filtered pressure, temperature, specific enthalpy value and whether it is in the transition state, the steam grade is divided, as follows:

[0063] High pressure: , ;

[0064] Medium pressure: , ;

[0065] Low pressure: , ;

[0066] In the transition state, the deviation of pressure and temperature will affect the grade determination; therefore, fuzzy logic is used to adjust the classification to avoid frequent switching of the transition state, and the fuzzy logic rules are as follows:

[0067] If and , then ; (prefer to keep the original grade);

[0068] If or , then ; (allow grade switching);

[0069] Wherein and represent the pressure deviation and temperature deviation respectively, the pressure deviation is calculated based on the obtained real-time pressure and the corresponding demarcation value ; The temperature deviation is obtained based on the obtained real-time temperature and the corresponding decomposition value ;

[0070] Wherein the compensated specific enthalpy value: ; by adjusting the compensated specific enthalpy value: , avoid frequent grade switching.

[0071] In this embodiment, the transition state is defined by pressure and temperature threshold, the unstable area when grade switching is identified, and by introducing fuzzy logic compensation mechanism, when the deviation is small, the original grade is preferentially retained through the compensation factor, avoiding frequent grade switching caused by slight parameter fluctuation, significantly improving the system control stability, reducing unnecessary action of the actuator, prolonging the service life of the equipment; secondly, since the traditional steam classification only relies on static threshold, it is easy to be affected by working condition fluctuation, while in this embodiment, the transition state is dynamically identified and combined with fuzzy compensation, so that the classification decision has the ability of "inertia maintenance", keeping the current grade when the parameter fluctuates, and triggering only when it significantly deviates from the threshold, thereby avoiding control loop oscillation and improving the running stability of the incineration boiler steam system.

[0072] S3. Load forecasting and demand matching: Based on steam grade, historical load data and external data, the LSTM load forecasting module is used to output the future power generation demand and heat load demand; then the supply-demand gap of each steam grade is calculated according to the prediction results, the priority allocation suggestion is generated, and the future and heat demand prediction curve and the steam allocation priority matrix are obtained;

[0073] The steam grade is the real-time steam grade label (high pressure, medium pressure, low pressure), the value and the flow, and the sampling period is 10 seconds; the historical load data is the power generation and heat supply demand in the past 72 hours, the time granularity is 5 minutes, and the date type is included; the external data includes weather forecast and production plan, wherein the weather forecast is the temperature and wind speed in the next 24 hours, and the time granularity is 1 hour; the production plan is the garbage treatment amount in the next 24 hours, and the time granularity is 1 hour;

[0074] Referring to Figure 3 As shown in the figure, first, the input data is time series aligned and aggregated: the 10-second steam data is aggregated into 5-minute granularity by the sliding average algorithm (window width 30, overlap rate 50%);

[0075] Then, the time stamp of the external data is aligned, and the 1-hour granularity meteorological data is converted into 5-minute granularity by linear difference;

[0076] Feature construction: including steam grade proportion, meteorological compensation factor and production plan weight;

[0077] Among them, the steam grade proportion is the proportion of high pressure, medium pressure and low pressure steam in the total flow, for example, the calculation formula of high pressure steam proportion is as follows:

[0078] ;

[0079] In the formula: represents the proportion of high pressure steam in the total flow; represents the flow of high pressure steam; represents the flow of medium pressure steam; represents the flow of low pressure steam;

[0080] The steam grade proportion in this embodiment can reflect the current energy quality distribution and provide real-time energy quality state information for the prediction model, and compared with a single pressure / temperature parameter, it can more comprehensively represent the steam supply and demand relationship.

[0081] Among them, the meteorological compensation factor is designed according to the influence of outdoor temperature on steam demand, and the specific expression is as follows:

[0082] ;

[0083] In the formula: represents the outdoor temperature; Meteorological compensation factor;

[0084] In this embodiment, the impact of outdoor temperature on heat demand is quantified, enabling the model to adapt to climate change.

[0085] The production plan is heavily dependent on the normalized value of waste disposal, reflecting the impact of production planning on steam demand:

[0086] ;

[0087] wherein: represents the actual waste disposal amount; the maximum value is 30.

[0088] In this embodiment, the waste disposal amount is normalized, directly related to the amount of steam generated, enabling the model to capture production load changes in advance.

[0089] Based on the feature construction and the data after time alignment and aggregation, a standardized feature matrix is constructed, including 15-dimensional features (time, steam grade proportion, 㶲 value, meteorological factor, production weight, etc.), with a time granularity of 5 minutes, and the data is standardized by Z-score (mean value is 0, variance is 1);

[0090] Based on the constructed standardized feature matrix as the input of the LSTM load prediction model, the demand prediction for the next 4 hours is carried out;

[0091] The structure of the LSTM load prediction model is as follows:

[0092] LSTM layer: the first layer uses 128 neurons to extract time dependence, and the second layer uses 64 neurons to combine the Attention layer to enhance the weight of key time steps.

[0093] The Attention layer dynamically calculates the contribution weight of each time step in the historical sequence to the current prediction, and the specific expression is as follows:

[0094] ;

[0095] wherein: represents the output of the LSTM hidden layer; represents the output of the previous time step; and represent trainable weight parameters; represents a trainable weight vector;

[0096] The Attention layer weights the time series output by the second LSTM layer to obtain a weighted time series, and then a fully connected layer processes the weighted time series to map to a final load prediction value, wherein the fully connected layer uses 32 neurons; based on this, the power generation and heating demand in the next 4 hours is output, with a time granularity of 5 minutes.

[0097] Power generation steam demand: based on the turbine efficiency and the enthalpy value of high-pressure steam, the required high-pressure steam flow is calculated:

[0098] ;

[0099] In the formula: represents the turbine efficiency; represents the enthalpy value of high-pressure steam; represents the power generation demand; represents the required high-pressure steam flow;

[0100] Heating steam demand: based on the supply and return water temperature difference and the specific heat capacity, the required steam flow is calculated:

[0101] ;

[0102] In the formula: represents the supply water temperature; represents the return water temperature; represents the specific heat capacity; represents the heating demand; represents the required steam flow;

[0103] Based on the turbine efficiency and the high-pressure steam enthalpy value (energy quality), the required flow is calculated, rather than the traditional pressure-based grading distribution, so that the power generation system reduces flow consumption when the high-pressure steam enthalpy value is high (such as 300℃, 5MPa) (the higher the enthalpy value, the higher the energy utilization rate).

[0104] The high-pressure, medium-pressure, and low-pressure steam gap rates are calculated respectively:

[0105] ;

[0106] ;

[0107] ;

[0108] In the formula: represents the high-pressure steam flow; represents the high-pressure steam gap rate; represents the medium-pressure steam gap rate; represents the medium-pressure steam flow; represents the low-pressure steam gap rate; represents the filtrate treatment demand; represents the low-pressure steam flow rate;

[0109] wherein the calculated supply-demand gap rate 、 、 , a positive value represents a shortage, and a negative value represents a surplus;

[0110] The power generation weight is calculated according to the dynamic adjustment of the grid frequency deviation, and the greater the frequency deviation, the higher the priority of power generation:

[0111] ;

[0112] In the formula: represents the real-time frequency deviation of the grid; represents the power generation weight;

[0113] The heat supply weight is calculated as follows:

[0114] ;

[0115] In the formula: represents the fouling coefficient; represents the heat supply weight;

[0116] The filtrate weight is calculated as follows:

[0117] ;

[0118] In the formula: represents the low-pressure steam flow rate; represents the filtrate weight;

[0119] The Softmax function is used to combine the weight and the gap rate to generate a steam allocation priority matrix:

[0120] ;

[0121] wherein is the weight coefficient of high-pressure steam; is the weight coefficient of medium-pressure steam; is the weight coefficient of low-pressure steam;

[0122] The weight and the gap rate data are normalized based on the above Softmax function, and then the final steam allocation priority matrix is obtained.

[0123] S4. Multi-objective optimization and control instruction generation: based on the results obtained by steam grade, load forecasting and demand matching, and real-time device state, based on fuzzy PID control engine and three-level path intelligent switching mechanism, using dynamically adjusted three-dimensional fuzzy rule base to optimize PID parameters in real time, taking maximizing economic benefit and quality loss balance as objective function, realizing steam distribution through hierarchical control strategy;

[0124] Referring to Figure 4 As shown in the figure, the fuzzy PID control engine includes the following processing steps:

[0125] Fuzzy rule matching: through the preset fuzzy rule base, the input load deviation, deviation rate and device health index are fuzzified;

[0126] Among them, the load deviation is the output value of the current power / heat supply demand and the predicted value; the change rate of the load deviation is the trend of the load deviation over time; the device health index includes the real-time health score of key devices such as steam turbines and accumulators;

[0127] Among them, the fuzzification processing is matched through the fuzzy rule base, which is as follows:

[0128] According to the amplitude (such as "positive large" "negative small") and the rate of change (such as "rapid rise" "slow decline") of the load deviation, combined with the device health state (such as "good" "warning"), the matching control strategy is selected from the predefined fuzzy rule base;

[0129] For example: if the power demand deviation is "negative large" (serious shortage) and the device health state is "good", the steam turbine output is preferentially increased, and the weight of the heat distribution is reduced;

[0130] PID parameter adjustment: adjust the PID parameters according to the PID parameter adjustment amount output by the fuzzy rule to obtain the preliminary PID parameters;

[0131] The adjustment amount (such as "increase the proportional coefficient Kp") output by the fuzzy rule acts on the PID controller to optimize the control response speed and stability in real time. For example:

[0132] When the load deviation increases rapidly, increase the proportional coefficient (Kp) to speed up the response.

[0133] When the device health index is low, reduce the integral coefficient (Ki) to avoid device overload.

[0134] Based on this, the preliminary PID parameters are obtained, and multi-objective optimization calculation is performed to maximize the comprehensive benefit and quality loss balance as the objective function, using the preliminary PID parameters, through gradient descent method iteration, the optimal PID parameters that meet the objective function are found; The expression of the objective function is as follows:

[0135] ;

[0136] wherein: and represents a quality loss function; represents an actual steam pressure; represents an actual temperature; represents a reference pressure; represents a reference temperature;

[0137] In the embodiment, the equipment health index (such as the turbine bearing temperature, the regenerator leakage rate) is introduced as a fuzzy input, and when the health state is "warning", the integral coefficient Ki is automatically reduced (such as from 0.5 to 0.3), so as to avoid over-integral adjustment and cause equipment overload.

[0138] The three-level path intelligent switching mechanism includes a high-pressure steam path, a medium-pressure steam path, and a low-pressure steam path;

[0139] The high-pressure steam path adjusts the inlet flow of the back pressure unit linearly to suppress the grid fluctuation by monitoring the grid frequency deviation in real time; wherein the linear adjustment expression of the inlet flow of the back pressure unit is as follows:

[0140] ;

[0141] wherein: represents a frequency adjustment coefficient; represents a grid frequency deviation; represents the inlet flow of the back pressure unit; represents the designed inlet flow;

[0142] If the frequency deviation exceeds the threshold value of ±0.2 Hz, the regenerator is immediately started to store heat, wherein the heat storage amount of the regenerator is calculated based on the following formula:

[0143] ;

[0144] wherein: represents a regenerative efficiency; represents the heat storage amount of the regenerator; represents the capacity of the regenerator;

[0145] In the embodiment, the grid frequency deviation is monitored in real time, and the inlet flow of the back pressure unit is linearly adjusted to quickly suppress the fluctuation.

[0146] The medium-pressure steam path adopts a feedforward-feedback composite control, wherein the feedforward control adjusts the heating valve opening degree in advance based on the predicted heating demand;

[0147] ;

[0148] wherein: represents the opening degree of the heat supply valve; represents the basic opening degree; represents the heat supply adjustment coefficient; represents the predicted building heat load;

[0149] The feedback control is based on the optimized PID parameters to fine-tune the heat supply valve opening degree with a period of ≤5 seconds to eliminate the real-time heat supply temperature / flow deviation;

[0150] ;

[0151] wherein: represents the heat supply deviation; , , represents the proportional, integral, and differential parameters of the PID controller; represents the last heat supply valve opening degree; represents the integral term of the heat supply deviation; the rate of change of the heat supply deviation;

[0152] In the present embodiment, the feedback control combines the optimized PID parameters (5-second fine-tuning period) to eliminate the flow deviation in real time, so that the heat supply pipe network pressure fluctuation is ≤0.05 MPa.

[0153] Low-pressure steam path: continuously monitor the heat transfer coefficient of the evaporator, when the heat transfer coefficient is lower than 85%, it indicates that the evaporator is scaled, affecting the heat transfer efficiency, therefore triggering the switch to the standby evaporating unit to maintain the efficiency of steam generation; the following formula is used to calculate the evaporation capacity after switching:

[0154] ;

[0155] wherein: represents the scaling impact coefficient; represents the heat transfer coefficient; represents the current evaporation capacity of the evaporating unit after switching; represents the adjusted evaporation capacity of the evaporating unit after switching; wherein the scaling impact coefficient is calculated based on the current heat transfer efficiency and the reference heat transfer efficiency; that is, by subtracting the ratio of the current heat transfer efficiency and the reference heat transfer efficiency from 1;

[0156] When distributing steam, according to the priority of leachate treatment, the following formula is used for distribution:

[0157] ;

[0158] wherein: represents the priority weight of leachate treatment; represents the total distribution amount of low-pressure steam; represents the amount of steam for leachate treatment;

[0159] In this embodiment, the heat transfer coefficient is lower than 85%, the standby evaporation unit is automatically switched over, the switching time is less than or equal to 30 seconds, the steam production is prevented from being reduced due to fouling (for example, when the heat transfer efficiency is reduced by 20% due to fouling, the standby unit can compensate for 15% of the evaporation loss), the continuous operation of the leachate treatment is ensured (the traditional manual switching needs 2-3 hours, which easily leads to the interruption of sewage treatment), the priority weight ensures that the low-pressure steam is preferentially supplied to the leachate treatment (an industry demand), even if the total amount of low-pressure steam is insufficient, more than 70% of the treatment demand can still be ensured, and the risk of overflow of the landfill leachate is avoided.

[0160] S5. Feedback correction: compare the instruction with the execution result, calculate the cumulative deviation, if the cumulative deviation is less than or equal to the preset deviation threshold, trigger the PID parameter adjustment based on the gradient descent method;

[0161] If the cumulative deviation is greater than the preset deviation threshold, expert diagnosis is performed.

[0162] The present application dynamically classifies and decides in real time based on the thermodynamic calculation of real-time steam parameters, breaks through the limitation of fixed pressure level, establishes the accurate mapping of steam quality and energy use scene, then constructs the dynamic response model of steam demand through the LSTM load prediction module, identifies the supply-demand gap of steam of different qualities in advance, forms the priority allocation matrix, finally combines the fuzzy PID control engine and the three-level path switching mechanism, constructs the multi-level optimization system with the maximum economic benefit and the minimum heat loss as the target, realizes the optimal dynamic matching of steam parameters and energy-using equipment.

[0163] The above is only a preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for hierarchical utilization of incineration heat based on energy-quality matching, characterized in that: The following steps are involved: Data collection and preprocessing: Collect incineration boiler steam parameters and user demand data, preprocess the collected data to obtain preprocessed incineration boiler steam parameters and user demand data; Enthalpy and exergy calculation and dynamic classification decision-making: Based on the pre-treated incineration boiler steam parameters, the steam enthalpy value is calculated according to the thermodynamic model, and then the steam exergy value is calculated based on the steam enthalpy value. The steam is divided into three grades based on the enthalpy value and exergy value to obtain the steam grade, and the steam grade is determined based on the calculated enthalpy and exergy value. Load forecasting and demand matching: Based on steam levels, historical load data, and external data, including weather forecasts and production plans, the LSTM load forecasting module outputs future power generation and heat load demands. The forecast results are then used to calculate the supply and demand gap for each steam level, generate priority allocation recommendations, and obtain future and heat demand forecast curves and a steam allocation priority matrix. Multi-objective optimization and control command generation: Based on the steam level, load forecast and demand matching results, as well as real-time equipment status, a fuzzy PID control engine and a three-level path intelligent switching mechanism are used. A dynamically adjusted three-dimensional fuzzy rule library is used to optimize PID parameters in real time. The objective function is to maximize the balance between economic benefits and quality losses, and steam distribution is achieved through a hierarchical control strategy.

2. The method for graded utilization of incineration heat based on energy-quality matching according to claim 1 is characterized in that: Before calculating the enthalpy value, a moving average filter is used to perform moving average filtering on the pressure and temperature in the steam parameters; then, based on the data after the moving average filtering, whether it is in a transition state is identified; wherein the pressure and temperature are unstable during the process of the transition state value transitioning from one level to another, wherein the transition state is determined based on a set threshold, and if it is a transition state, it is marked as a transition state; In the process of determining the steam level, the transition state is introduced and the steam level is compensated using a fuzzy logic method. In the transition state, if the deviation of pressure and temperature is less than a threshold, the current level is maintained; if the deviation is greater than the threshold, the level is allowed to be switched.

3. The method for graded utilization of incineration heat based on energy-quality matching according to claim 1 is characterized in that: The steps for the LSTM load forecasting module to perform forecasting are as follows: Before prediction, the data is time-series aligned and aggregated. All data are time-series aligned. The steam data is aggregated using the sliding average method to align with the time series of other data. Feature construction is performed based on the time-aligned and aggregated data, including steam grade ratio, meteorological compensation factor, and production plan weight. The steam grade ratio is the proportion of steam of different grades in the total steam flow; the meteorological compensation factor is a compensation coefficient constructed based on the impact of outdoor temperature on steam demand; the production plan weight is the normalized waste treatment volume, reflecting the impact of production intensity on steam generation; A standardized feature matrix is ​​constructed based on the time-aligned and aggregated data and the data obtained by feature construction, the standardized feature matrix is ​​used as the input of the LSTM load forecasting module, and a prediction is performed based on the LSTM load forecasting module to obtain future power generation demand and heating demand; The LSTM load forecasting module includes an LSTM layer, an Attention layer, and a fully connected layer. The Attention layer dynamically calculates the contribution weight of the time step in the output sequence of the LSTM layer to the current prediction, obtaining a weighted time series. The output is then mapped to the predicted values ​​of power generation and heating demand through the fully connected layer.

4. The method for graded utilization of incineration heat based on energy-quality matching according to claim 1 is characterized in that: The steps for generating the priority allocation suggestion are as follows: Demand-steam conversion: Calculate the required high-pressure steam flow rate based on the turbine efficiency and the enthalpy of high-pressure steam; calculate the required medium-pressure steam flow rate based on the supply and return water temperature difference and specific heat capacity; Gap rate calculation: Calculate the difference between power generation steam demand and actual high-pressure steam flow to reflect the supply and demand gap of high-pressure steam; calculate the difference between heating steam demand and actual medium-pressure steam flow to reflect the supply and demand gap of medium-pressure steam; calculate the difference between actual low-pressure steam flow and leachate treatment demand to reflect the excess of low-pressure steam; Dynamic priority weight allocation: Dynamically adjust power generation weight according to grid frequency deviation; dynamically adjust heating weight according to equipment scaling; dynamically adjust leachate weight according to low-pressure steam flow; The obtained weights are combined with the gap ratio to generate weight coefficients, and then the steam allocation priority matrix is ​​obtained, which includes the weight coefficients of power generation, heat supply and leachate treatment.

5. The method for graded utilization of incineration heat based on energy-quality matching according to claim 1 is characterized in that: The fuzzy PID control engine includes the following processing steps: Fuzzy rule matching: Through the preset fuzzy rule library, the input load deviation, deviation change rate and equipment health index are fuzzified; PID parameter adjustment: adjust the PID parameters according to the PID parameter adjustment amount output by the fuzzy rule to obtain preliminary PID parameters; Objective function optimization: Taking the balance between maximizing comprehensive benefits and quality loss as the objective function, preliminary PID parameters are used and the gradient descent method is used to iterate to find the optimal PID parameters that meet the objective function.

6. The method for graded utilization of incineration heat based on energy-quality matching according to claim 5 is characterized in that: The three-level path intelligent switching mechanism includes a high-pressure steam path, a medium-pressure steam path, and a low-pressure steam path; The high-pressure steam path monitors the grid frequency deviation in real time and linearly adjusts the steam inlet of the back-pressure unit to smooth out grid fluctuations. If the frequency deviation exceeds the threshold of ±0.2Hz, the heat accumulator is immediately activated to store heat. Medium-pressure steam path: Feedforward-feedback composite control is adopted, in which feedforward control adjusts the heating valve opening in advance based on the predicted heating demand; Feedback control is based on optimized PID parameters, fine-tuning the heating valve opening in a cycle of ≤5 seconds to eliminate real-time heating temperature / flow deviation; Low-pressure steam path: Calculates the evaporator heat transfer coefficient in real time. If the efficiency is less than 85%, it automatically switches to a standby evaporation unit and increases the steam distribution volume to compensate for the efficiency loss. It also dynamically intercepts low-pressure steam resources based on a priority matrix.

7. The method for graded utilization of incineration heat based on energy-quality matching according to claim 1 is characterized in that: It also includes feedback correction, comparing instructions with execution results, calculating the cumulative deviation, and triggering PID parameter adjustment based on the gradient descent method if the cumulative deviation is less than or equal to the preset deviation threshold; If the accumulated deviation is greater than the preset deviation threshold, expert diagnosis is performed.

Images