Cooperative scheduling method of heat storage system based on dynamic prediction of steam production and consumption
By constructing a steam production consumption prediction model and coordinated scheduling of the heat storage system, dynamically adjusting the pressure of the steam pipeline network, the problems of pressure fluctuations and low energy utilization in the steam system are solved, and efficient coordination and safe and stable operation of the steam pipeline network are achieved.
Patent Information
- Application Number
- CN202510243159.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-03
- Publication Date
- 2025-07-08
AI Technical Summary
The existing steam system scheduling methods are difficult to respond quickly to sudden changes in steam demand, resulting in large fluctuations in the pressure of the steam pipeline network, low energy utilization rate, and safety hazards.
By constructing a steam production consumption prediction model, combining the coordinated scheduling of the heat storage system, using real-time data acquisition and time series analysis, dynamically predict the net steam increment and pipeline pressure, adjust the opening of the steam valves of the heat storage device, and achieve efficient coordination of the steam pipeline network.
It reduces pressure fluctuations in the steam pipeline network, improves the operating safety and stability of the system, optimizes the distribution and utilization of steam, and reduces resource waste.
Smart Images

Figure CN120278310A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of industrial energy management, and particularly to a collaborative scheduling method for a heat storage system based on dynamic prediction of steam production and consumption. Background Art
[0002] The steam system in a steel plant is an important link to ensure the stable operation of the production process. Steam not only provides heat energy support for each production process, but also is a key medium for energy recovery and conversion. At present, the operation of the steam system in a steel plant often faces problems such as large fluctuations in the pressure of the steam pipe network, low energy utilization rate, slow system response, etc., and the dynamic changes in steam production and consumption also pose higher requirements for the stable operation of the system.
[0003] Existing steam system scheduling methods rely on manual experience or simple rule control. These methods often seem powerless in the face of complex dynamic changes. On the one hand, manual scheduling is difficult to quickly respond to sudden changes in steam demand due to lagging decision-making and strong subjectivity, resulting in large fluctuations in the pressure of the pipe network and waste of resources caused by steam venting; on the other hand, simple rule control models lack in-depth analysis of dynamic characteristics and are difficult to adapt to complex working conditions in the modern steel production environment. This situation not only affects the operation efficiency of the system, but also may pose safety hazards to equipment due to fluctuations in the pressure of the pipe network.
[0004] Therefore, a collaborative scheduling method for a heat storage system based on dynamic prediction of steam production and consumption is needed. Summary of the Invention
[0005] In view of this, the present invention provides a collaborative scheduling method for a heat storage system based on dynamic prediction of steam production and consumption. With collaborative scheduling as the core, by integrating real-time data collection, time series analysis and dynamic prediction models, it realizes accurate prediction and optimal scheduling of steam production and consumption in the steam system of a steel plant; solves the problems that it is difficult for the existing technology to accurately predict steam production and consumption in the face of complex dynamic changes, and problems such as large fluctuations in the pressure of the steam pipe network.
[0006] For this purpose, the present invention provides the following technical solutions:
[0007] A collaborative scheduling method for a heat storage system based on dynamic prediction of steam production and consumption, comprising:
[0008] Construct a steam pipe network data set;
[0009] Using a steam production and consumption prediction model, obtain the net increase in steam in the steam pipe network within a future set time based on the steam pipe network data set;
[0010] Establish a correlation model between the net increase in steam and the pipe network pressure, and input the net increase in steam in the steam pipe network to obtain a predicted value of the pipe network pressure;
[0011] Taking the difference between the predicted value of the pipe network pressure and the actual value of the pipe network pressure as the steam pipe network pressure difference, and obtaining the regulating value of the accumulator according to the steam pipe network pressure difference;
[0012] Combining the regulating value of the accumulator and the adjustable steam volume range to determine the adjustment instruction;
[0013] Controlling the heat storage system based on the adjustment instruction.
[0014] Furthermore, the steam production and consumption prediction model includes:
[0015] For the process with regular fluctuations in steam production, constructing a time series prediction model based on a long short-term memory network;
[0016] For the process with irregular fluctuations in steam consumption, constructing a prediction model based on a stacked function model. Furthermore, the steam net increment and pipe network pressure correlation model includes:
[0017] V0 = πr 2 h
[0018]
[0019] P1 = p1 + p0
[0020] P2 = p2 + p0
[0021]
[0022] In the formula, V0 is the steam pipe network volume, ΔV is the pipe network net increment, p0 is the standard atmospheric pressure, p1 is the current pipe network gauge pressure, and p2 is the future set pipe network gauge pressure.
[0023] Furthermore, obtaining the regulating value of the accumulator according to the steam pipe network pressure difference:
[0024] V adjust = K·ΔP
[0025] Among them, V adjust is the regulating value of the accumulator, ΔP is the pressure difference, and K is the proportional regulation coefficient.
[0026] Furthermore, the adjustable steam volume range of the accumulator includes:
[0027] The steam inlet volume of the accumulator is greater than 0 and less than the available water storage volume of the accumulator;
[0028] The steam outlet volume of the accumulator is greater than 0 and less than the stored water volume of the accumulator;
[0029] The available water storage volume of the accumulator is the difference between the maximum water storage volume of the accumulator and the stored water volume of the accumulator.
[0030] Further, the adjustment instruction includes: a heat accumulator adjustment value, an adjustment direction, an adjustment time point, and a steam generator set adjustment value.
[0031] Further, the adjustment time point is the sum of the heat accumulator response time, the transmission delay time of the steam pipe network, and the current time.
[0032] Further, determine the opening degree of the heat accumulator valve according to the heat accumulator adjustment value:
[0033] L = K v ·V adjust
[0034] where K v is an adjustment coefficient.
[0035] Further, controlling the heat storage system based on the adjustment instruction includes:
[0036] When the heat accumulator adjustment value is within the adjustable steam volume range, control the heat accumulator valve according to the adjustment time point, the adjustment direction, and the heat accumulator valve opening degree;
[0037] When the heat accumulator adjustment value is not within the adjustable steam volume range, control the power generation power of the steam generator set according to the adjustment time point and the adjustment direction until the heat accumulator adjustment value returns to the adjustable steam volume range.
[0038] Further, the steam pipe network data set includes:
[0039] Real-time data of production plans, working condition signals, instantaneous steam production and consumption, and the water storage volume already stored in the heat accumulator for each process.
[0040] Advantages and positive effects of the present invention:
[0041] The present invention combines dynamic data in the factory and production plans to accurately predict the net steam increment in the steam pipe network and the pressure in the pipe network; and combines with the adjustable range of the heat accumulator to obtain the heat accumulator adjustment value, so as to reduce the pressure fluctuation of the pipe network, the waste of resources caused by steam discharge, and the potential safety hazards of equipment.
[0042] 1) By obtaining real-time data of production plans, working condition signals, and instantaneous steam production and consumption of each process in the steel plant, and using a prediction model based on time series, accurate prediction values of steam production and consumption of equipment in each process of the steel plant within a future set time are obtained.
[0043] 2) Based on the prediction results of steam production and consumption, determine the net steam increment of the steam pipe network and establish a correlation model between the net steam increment and the pipe network pressure to obtain accurate pressure prediction values.
[0044] 3) Determine the required regulating value of the heat accumulator based on the predicted pressure value and the adjustable range of the current heat accumulator, adjust the opening degrees of the regulating valves of the steam inlet and outlet valves of the heat accumulator in advance, and control the steam input and output of the heat accumulator; while achieving the stable pressure in the pipe network, meet the safety requirements of the heat accumulator at the same time.
[0045] The present invention optimizes the distribution and utilization of steam, ensures the balance between supply and demand of the steam pipe network, reduces pressure fluctuations, and thus improves the operation safety, stability and economy of the steam pipe network. Description of the Drawings
[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.
[0047] Figure 1 It is a flowchart of the collaborative scheduling method of the heat storage system based on the dynamic prediction of steam production and consumption in the embodiment of the present invention;
[0048] Figure 2 It is a logical framework diagram of the collaborative scheduling of the heat storage system based on the dynamic prediction of steam production and consumption in the embodiment of the present invention;
[0049] Figure 3 It is a comparison chart of the steam pipe network pressure before and after the collaborative scheduling of the heat storage system in the embodiment of the present invention. Detailed Embodiments
[0050] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0051] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0052] The present invention provides a coordinated scheduling method for a heat storage system based on dynamic prediction of steam production and consumption: through a steam production and consumption prediction model based on time series, determine the predicted values of steam production and consumption of each process equipment in the steel plant within a future set time, providing basic data support for the coordinated scheduling of the system; based on the prediction results of steam production and consumption, determine the net steam increment of the steam pipe network; establish a correlation model between the net steam increment and the pipe network pressure, and combine the adjustable range of the heat storage device and the predicted pressure value to determine the adjustment value of the heat storage device; by adjusting the opening degree of the regulating valves of the steam inlet and outlet valves of the heat storage device in advance, dynamically control the steam input and output volume of the heat storage device. Ensure the efficient coordination between the steam pipe network and the heat storage device, realize the coordinated scheduling of the heat storage system based on dynamic prediction of steam production and consumption, ensure the supply-demand balance of the steam pipe network, significantly reduce pressure fluctuations, and thus improve the operation safety, stability and economy of the steam pipe network.
[0053] Combined with Figure 1 As shown, the method steps of the present invention include:
[0054] S1: Classify each process, and obtain real-time data of the production plan, working condition signal, instantaneous steam production and consumption, and the water storage volume already stored in the heat storage device of each process;
[0055] S2: Use the production plan and working condition signal to determine the production start time and planned production volume; establish a steam production and consumption prediction model based on time series, and determine the predicted values of steam production and consumption of each process equipment in the steel plant within a future set time;
[0056] S3: Determine the net steam increment of the steam pipe network according to the predicted values of steam production and consumption; establish a correlation model between the net steam increment and the pipe network pressure, and obtain the predicted value of the pipe network pressure;
[0057] S4: Compare the predicted value of the pipe network pressure with the actual pressure value of the current system, calculate the pressure difference, and determine the required adjustment value of the heat storage device according to the pressure difference;
[0058] S5: Calculate the range of steam volume that can be adjusted by the heat accumulator based on the difference between the maximum water storage capacity of the heat accumulator and the water storage volume already in the heat accumulator.
[0059] S6: Determine the adjustment amount of the heat accumulator based on the adjustment demand of the heat accumulator and the range of adjustable steam volume; according to the adjustment amount of the heat accumulator, adjust in advance the opening degree of the regulating valves of the steam inlet and outlet valves of the heat accumulator to control the steam input and output volume of the heat accumulator.
[0060] The method of the present invention will be further described with the following embodiments:
[0061] In step S1 of this embodiment, each process includes: the process of the generating unit and the process of the using unit;
[0062] The process of the generating unit includes: steelmaking, rolling, CDQ (Coke Dry Quenching), activated coke;
[0063] The process of the using unit includes: sintering, pelletizing, coking, steelmaking, oxygen production, ironmaking, acid making, power generation;
[0064] The types of processes of the generating unit and the using unit include: processes with regular fluctuations in steam production and consumption and processes with irregular fluctuations in steam production and consumption;
[0065] Processes with regular fluctuations in steam production and consumption include: CDQ, steelmaking; Processes with irregular fluctuations in steam production and consumption include: sintering, pelletizing, coking, oxygen production, ironmaking, acid making, power generation, rolling, activated coke; The production plan is the production plan of the monthly steel output provided by the steel plant;
[0066] The working condition signals include: production start signal and production stop signal.
[0067] In step S2 of this embodiment, the future set time is set to t, and the future time value range is 10 ≤ t ≤ 240 min;
[0068] According to the real-time data of each process production plan, working condition signals, instantaneous steam production and consumption, and the water storage volume already in the heat accumulator obtained in S1, perform data preprocessing, including data cleaning, normalization processing, and time series alignment;
[0069] For processes with regular fluctuations in steam production, construct a time series prediction model based on a long short-term memory network, which includes an input layer, an LSTM (Long Short-Term Memory) layer, a fully connected layer, and an output layer;
[0070] For processes with irregular fluctuations in steam consumption, construct a prediction model based on a stacked function model, which includes an input layer, a multi-layer perceptron layer, and an output layer;
[0071] According to the production plan and working condition signals, determine the planned production volume and production start time for each process. Take the determined planned production volume and production start time as inputs and input them into the trained time series prediction model and stacked function model of the long short-term memory network for training. Preferably, the training model dataset includes data within the most recent 72 hours;
[0072] Use the trained LSTM model to predict the instantaneous steam generation volume of the process equipment with regular fluctuations belonging to the generating unit within the future set time, and the instantaneous steam consumption volume of the process equipment with regular fluctuations belonging to the using unit within the future set time;
[0073] Use the trained stacked function model to predict the instantaneous steam generation volume of the process equipment with irregular fluctuations belonging to the generating unit within the future set time, and the instantaneous steam consumption volume of the process equipment with irregular fluctuations belonging to the using unit within the future set time;
[0074] The steam production and consumption prediction model includes, but is not limited to, the LSTM model and the stacked function model. According to the feedback of the actual production data, adjust the structure and parameters of the model to ensure the adaptability and accuracy of the model.
[0075] Among them, the time series prediction model based on LSTM specifically includes: using a steam flowmeter to collect real-time data on the steam production and consumption of each process equipment, constructing a time series, production plan, and working condition signal input feature set based on the collected real-time data, and performing denoising, normalization, and outlier correction on the original data through data preprocessing methods such as forward filling to fill missing values and linear interpolation to replace outlier data. Take the processed sequence data as training data and input it into the LSTM network. Use the first eighty percent of the data as the training set, and the remaining twenty percent of the data as the validation set. Capture the change rules of the steam production and consumption of the process equipment with regular fluctuations through training the model, optimize the model parameters, improve the prediction accuracy, and obtain the time series prediction model based on LSTM.
[0076] A prediction model based on a stacked function model, specifically including: collecting real-time data of steam production and consumption of each process equipment using a steam flowmeter, constructing an input feature set of time series, production plan, and working condition signals based on the collected real-time data, and performing denoising, normalization, and outlier correction on the original data through data preprocessing methods such as forward filling to fill missing values and linear interpolation to replace outlier data. The processed sequence data is used as training data and input into the stacked function model. Eighty percent of the data is used as the training set, and the remaining twenty percent of the data is used as the validation set. The sub-models of each layer of the model are trained layer by layer. The output of each layer of the model is combined with the original input features and used as the input of the next layer of the model. The parameters of each layer of the model are optimized using the cross-validation method to improve the overall prediction accuracy, and a prediction model based on the stacked function model is obtained.
[0077] In step S3 of this embodiment, the steam net increment of the steam pipe network is determined according to the predicted value of steam production and consumption; an association model between the steam net increment and the pipe network pressure is established to obtain the predicted value of the pipe network pressure; the following steps are included:
[0078] 1) Determine the steam net increment of the steam pipe network: The net increment of the steam pipe network is obtained by subtracting the steam production of the using unit from the steam production of each process production unit.
[0079] 2) Establish an association model between the steam net increment and the pipe network pressure. The inputs of the association model include: steam net increment, pipe network volume, and the pipe network gauge pressure at time i. The output of the model is the pipe network gauge pressure at time i + t.
[0080] 3) Use the steam pipe network volume and combine the structural parameters of the actual steel plant's steam pipe network to obtain the predicted value of the pipe network pressure; the structural parameters of the actual steel plant's steam pipe network include: the diameter and length of the pipeline.
[0081] Among them, the association model between the steam net increment and the pipe network pressure specifically includes:
[0082] V0 = πr 2 h
[0083]
[0084] P1 = p1 + p0
[0085] P2 = p2 + p0
[0086]
[0087] In the formula, V0 is the steam pipe network volume, ΔV is the pipe network net increment, p0 is the standard atmospheric pressure, 101.325 kPa, p1 is the current pipe network gauge pressure, and p2 is the future set pipe network gauge pressure.
[0088] Output the predicted value of the pipe network pressure, i.e., the surface pressure p2 of the pipe network at time i + t, using the correlation model between the net steam increment and the pipe network pressure.
[0089] In this embodiment S4, determine the required regulating value V of the heat accumulator according to the pressure difference. adjust , including:
[0090] 1) Compare the predicted value of the steam pipe network pressure at time i + t predicted in S3 with the real-time steam pipe network pressure value measured by the pressure monitoring device at time i, and calculate the pressure difference between the predicted steam pipe network pressure value and the real-time steam pipe network pressure value.
[0091] 2) Determine the regulating value of the heat accumulator according to the pressure difference using the proportional regulation formula. The proportional regulation formula:
[0092] V adjust = K·ΔP
[0093] where V adjust is the required regulating value of the heat accumulator, K is the proportional regulation coefficient, ΔP is the pressure difference, and the value of the regulation coefficient is adjusted according to the dynamic response characteristics of the system. Preferably, the value range of the regulation coefficient is 0.1 ≤ K ≤ 1.0.
[0094] Specifically, the proportional regulation coefficient:
[0095]
[0096] where: Q rate is the maximum regulation rate of the heat accumulator, V0 is the volume of the steam pipe network, V is the available water storage capacity of the heat accumulator, and Q 流量 is the flow rate of the steam pipe network.
[0097] In this embodiment S5, calculating the adjustable steam volume range of the heat accumulator includes the following steps:
[0098] 1), Determine the maximum water storage capacity of the heat accumulator. In this embodiment, the maximum water storage capacity takes into account the physical capacity of the heat accumulator, safety limits, and the operating requirements of the system, and receive and determine the water storage volume of the heat accumulator that has been stored.
[0099] Among them, according to the safety limits of the heat accumulator and the operating requirements of the system, set a safety margin to correct the value range of its maximum water storage capacity to ensure that the system does not exceed the safety limits when operating at full load.
[0100] The water storage volume of the heat accumulator that has been stored is monitored in real time by a liquid level sensor installed inside the heat accumulator. The liquid level sensor will accurately measure the water level height and convert the measurement result into the water storage volume of the heat accumulator that has been stored. By monitoring the water storage volume of the heat accumulator that has been stored, the adjustment module can obtain the water storage state inside the heat accumulator in real time.
[0101] 2), V is the available water storage capacity of the heat accumulator: the maximum water storage capacity V max and the water storage volume V cur already stored in the heat accumulator;
[0102] 3), Based on the available water storage capacity V of the heat accumulator and the water storage volume V cur already stored in the heat accumulator, the adjustable steam volume range of the heat accumulator is the steam inlet volume [0, V] and the steam outlet volume [0, V cur .
[0103] In this embodiment S6, based on the adjustment requirements of the heat accumulator and the adjustable steam volume range, the adjustment amount of the heat accumulator is determined, and the opening degrees of the regulating valves of the steam inlet and outlet valves of the heat accumulator are adjusted in advance to control the steam input and output of the heat accumulator, including the following steps:
[0104] According to the heat accumulator adjustment value obtained in S4 and the adjustable steam volume range obtained in S5, determine the adjustment instruction; the adjustment instruction includes: adjustment direction (steam inlet or steam outlet), adjustment time point, regulating valve opening degree, and steam generator set adjustment value;
[0105] A) When the heat accumulator adjustment value is within the adjustable steam volume range:
[0106] The heat accumulator adjustment time point is the sum of the response time of the heat accumulator, the transmission delay time of the steam pipe network, and the current time;
[0107] According to the heat accumulator adjustment value of the heat accumulator, adjust the opening degrees of the regulating valves of the steam inlet and outlet valves of the heat accumulator:
[0108] The opening degree L in of the steam inlet valve and the opening degree L out of the steam outlet valve are determined by the adjustment formula:
[0109] L = K v ·V adjust
[0110] where K v is the adjustment coefficient, and the value of the adjustment coefficient is adjusted according to the dynamic response characteristics of the system; preferably, the value range of the adjustment coefficient is 0.001 ≤ K v ≤ 0.005;
[0111] Control the steam input and output volume of the heat accumulator according to the adjustment instruction.
[0112] B) When the heat accumulator adjustment value is not within the adjustable steam volume range, a further power generation scheduling method of the steam generator set is introduced in combination with the adjustment instruction:
[0113] b1) When the regulating direction of the heat accumulator in the adjustment instruction is steam output, and the regulating value of the heat accumulator is greater than the stored water volume of the heat accumulator, then adjust the power generation of the steam generator set until the regulating value of the heat accumulator is less than the stored water volume of the heat accumulator;
[0114] Specifically, when the regulating value of the heat accumulator is greater than the stored water volume of the heat accumulator and the stored water volume of the heat accumulator drops to 0, the system issues an alarm and stops the steam output operation, and at the same time reduces the power generation of the steam generator set;
[0115] Reduction value of power generation:
[0116] P 减小 = k p ·(V adjust - V cur )
[0117] Wherein, P 减小 is the power generation adjustment value, k p is the power generation efficiency of the steam generator set. The power generation efficiency ranges from 0.2 to 0.5 MW / m3 according to different generator set models;
[0118] Adjust the operating power of the generator set to reduce the operating power and thus reduce the power generation of the generator set and the steam consumption. When the regulating value of the heat accumulator is less than the stored water volume of the heat accumulator, stop adjusting the power generation of the steam generator set.
[0119] b2) When the regulating direction of the heat accumulator in the adjustment instruction is steam input, and the regulating value of the heat accumulator is greater than the available storage volume of the heat accumulator, then increase the power generation of the steam generator set until the regulating value of the heat accumulator is less than the available storage volume of the heat accumulator;
[0120] Specifically, when the heat accumulator reaches the maximum storage volume, the system issues an alarm and stops the steam input operation, and at the same time increases the power generation of the steam generator set;
[0121] Increase value of power generation:
[0122] P 增大 = k p ·(V adjust - V)
[0123] Wherein, P 增大 is the power generation adjustment value, k p is the power generation efficiency of the steam generator set. The power generation efficiency ranges from 0.2 to 0.5 MW / m3 according to different generator set models; Adjust the operating power of the generator set to increase the operating power and thus increase the power generation of the generator set and consume steam. When the regulating value of the heat accumulator is less than the available storage volume of the heat accumulator, stop adjusting the power generation of the steam generator set.
[0124] Combined with Figure 2The logic framework diagram of the collaborative scheduling of the heat storage system shown below further illustrates the method of the present invention with application examples:
[0125] In this application example, through the collaborative work of steam net increment calculation, pressure prediction model, heat accumulator regulation module and real-time feedback, the operation state of the steam pipe network is monitored and adjusted, and the dynamic regulation and optimization of the steam pipe network are carried out to achieve the stability and balance of the pipe network pressure.
[0126] First, through real-time data acquisition, the steam generation and consumption of each production link of the steam pipe network are obtained, and then the steam net increment at the current moment is calculated;
[0127] The steam net increment is input into the correlation model between the steam net increment and the pipe network pressure to obtain the predicted value of the pipe network pressure. The predicted value of the pipe network pressure is compared with the pressure value currently monitored in real time by the pipe network to obtain the pressure difference;
[0128] According to the pressure difference, the heat accumulator regulation module dynamically calculates the regulation amount of the heat accumulator;
[0129] The heat accumulator regulation module determines the range of the steam inlet amount and the steam outlet amount according to the water storage amount already stored in the heat accumulator and the steam amount interval that the heat accumulator can regulate, so as to dynamically adjust the opening degrees of the inlet and outlet valves of the heat accumulator and realize the balance regulation of the steam pipe network pressure.
[0130] The comparison of the steam pipe network pressure before and after the collaborative scheduling of the heat storage system in this application example is as Figure 3 shown. Through Figure 3 It can be seen that: through the collaborative scheduling of the heat storage system by the method of the present invention, the pressure fluctuation of the steam pipe network can be significantly improved: the black curve represents before scheduling, and the red curve represents after scheduling. At the beginning of steam production, due to the imbalance between steam supply and demand, the pipe network pressure rises rapidly. Through the collaborative scheduling of the heat storage system, the rising trend of the steam pressure is effectively controlled and the fluctuation amplitude is reduced. When the steam production reaches the peak, the pressure of the steam pipe network without scheduling increases significantly and large fluctuations occur, and the highest pressure is about 0.95 MPa. After collaborative scheduling, the pipe network pressure is effectively smoothed, and the highest pressure is maintained within about 0.75 MPa, and the system operates more stably. Therefore, through real-time monitoring of the steam net increment and the pipe network pressure, and dynamically adjusting the inlet and outlet steam amounts of the heat accumulator, the collaborative scheduling effectively alleviates the pressure fluctuation caused by the imbalance between steam supply and demand. When the steam production ends, the pressure of the pipe network without scheduling drops rapidly, while the pressure of the pipe network after collaborative scheduling gradually drops and is maintained within the safe operation range. By optimizing the operation mode of the heat accumulator, the pressure fluctuation of the pipe network is made gentle.
[0131] Through this application example, the effectiveness of the collaborative scheduling of the heat storage system is verified, and the dynamic balance management of the steam pipe network pressure is successfully realized, providing practical support for the optimization of the steam system in the steel plant.
[0132] The method of the present invention utilizes the steam net increment calculation and the pipe network pressure prediction model, combines the regulating strategy of the steam inlet and outlet valves of the heat accumulator, and forms a closed-loop control. The dispatching system calculates the relationship between the steam net increment and the pipe network pressure in real time, predicts the future pressure change trend, and dynamically adjusts the steam inlet and outlet volume of the heat accumulator according to the pressure difference to ensure that the pipe network pressure is always maintained within the set target range. This process not only improves the operation stability of the steam system but also enhances the energy utilization efficiency.
[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.
Claims
1. A coordinated scheduling method for a heat storage system based on dynamic prediction of steam production and consumption, characterized in that, Including: Construct a steam pipeline network dataset; Using the steam production and consumption prediction model, obtain the net steam increment of the steam pipeline network within a future set time based on the steam pipeline network dataset; Establish a correlation model between the net steam increment and the pipeline network pressure, input the net steam increment of the steam pipeline network, and obtain the predicted value of the pipeline network pressure; Take the difference between the predicted value of the pipeline network pressure and the actual pressure value of the pipeline network as the steam pipeline network pressure difference, and obtain the regulating value of the heat accumulator according to the steam pipeline network pressure difference; Combine the regulating value of the heat accumulator and the adjustable steam volume range to determine the adjustment instruction; Control the heat storage system based on the adjustment instruction.
2. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 1, wherein, The steam production and consumption prediction model includes: For the processes with regular fluctuations in steam production, construct a time series prediction model based on a long short-term memory network; For the processes with irregular fluctuations in steam consumption, construct a prediction model based on a stacked function model.
3. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 1, characterized in that, The correlation model between the net steam increment and the pipeline network pressure includes: V0 = πr 2 h P1 = p1 + p0 P2 = p2 + p0 In the formula, V0 is the volume of the steam pipeline network, ΔV is the net increment of the pipeline network, p0 is the standard atmospheric pressure, p1 is the gauge pressure of the pipeline network at the current moment, and p2 is the gauge pressure of the pipeline network at the future set moment.
4. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 1, wherein Obtaining the regulating value of the heat accumulator according to the steam pipeline network pressure difference: V adjust = K·ΔP Among them, V adjust is the regulating value of the heat accumulator, ΔP is the pressure difference, and K is the proportional regulation coefficient.
5. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 1, wherein, The adjustable steam volume range of the heat accumulator includes: The steam inlet volume of the heat accumulator is greater than 0 and less than the available water storage volume of the heat accumulator; The steam outlet volume of the heat accumulator is greater than 0 and less than the stored water volume of the heat accumulator; The available water storage volume of the heat accumulator is the difference between the maximum water storage volume of the heat accumulator and the stored water volume of the heat accumulator.
6. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 1, characterized in that, The adjustment instruction includes: the regulating value of the heat accumulator, the adjustment direction, the adjustment time point, and the regulating value of the steam generator set.
7. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 6, wherein The adjustment time point is the sum of the response time of the heat accumulator, the transmission delay time of the steam pipeline network, and the current moment.
8. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 6, wherein, Determine the valve opening of the heat accumulator according to the regulating value of the heat accumulator: L = K v ·V adjust Among them, K v is an adjustment coefficient.
9. The collaborative scheduling method of a heat storage system based on dynamic prediction of steam production and consumption according to claim 6, characterized in that, Controlling the heat storage system based on the adjustment instruction includes: When the regulating value of the heat accumulator is within the adjustable steam volume range, control the heat accumulator valve according to the adjustment time point, the adjustment direction, and the valve opening of the heat accumulator; When the regulating value of the heat accumulator is not within the adjustable steam volume range, control the power generation power of the steam generator set according to the adjustment time point and the adjustment direction until the regulating value of the heat accumulator returns to the adjustable steam volume range.
10. The collaborative scheduling method of the heat storage system based on the dynamic prediction of steam production and consumption according to claim 1, wherein The steam pipeline network dataset includes: Real-time data of the production plans, operating condition signals, instantaneous steam production and consumption, and stored water volume of the heat accumulator of each process.