Operation Optimization Method and System for the Load of a Secondary Reheat Unit Based on Big Data

Abstract

The present invention discloses an operation optimization method and system for the load of a secondary reheat unit based on big data, which relates to the technical field of operation optimization of thermal power generation equipment; obtaining the target power consumption collected in the target area in the current period, inputting the target power consumption into a short-term power consumption prediction model to obtain the predicted power consumption in the next period of the current period; determining a set of working schemes according to the predicted power consumption, and calculating the equipment cost score for any one of the working schemes in the set of working schemes; determining the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit works according to the working parameters; by obtaining the target power consumption and using the prediction model to plan power resources, the power consumption demand in the next period can be accurately predicted, and then multiple working schemes can be formulated and the equipment cost can be evaluated. Finally, the power generation scheme with the optimal cost-benefit is selected to ensure that while meeting the power consumption demand, the equipment wear is minimized, and the power generation efficiency and economy are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation optimization of thermal power generation equipment, and particularly relates to an operation optimization method and system for the load of a secondary reheat unit based on big data. Background Art

[0002] With the continuous adjustment of the global energy structure and the increasing environmental pressure, traditional coal-fired units are difficult to meet the environmental protection requirements of modern society. The secondary reheat unit significantly improves the thermal efficiency of the unit and effectively reduces pollutant emissions by dividing the heat of the fuel into two parts and recycling it on two different circuits. The above technology is a technological innovation for traditional coal-fired units. By adopting the secondary reheat technology, the unit can improve the overall efficiency under the same parameters and reduce the emissions of carbon dioxide, nitrogen oxides, etc.

[0003] Patent No.: CN114488798A discloses a performance monitoring and operation optimization method for a secondary reheat unit based on data reconciliation, studies the dominant factors and action mechanisms affecting the characteristics of the main components of the thermal system, obtains the component characteristic curves within the full operating conditions range, and establishes a high-precision mathematical model of the key components of the thermal system for the full operating conditions; uses the measurement redundancy information of the thermal parameters of the unit and adopts a data reconciliation algorithm to reduce the measurement uncertainty of the key data; provides accurate target values for the health status monitoring of components, and realizes various performance monitoring functions through the comparison of the monitored values and the target values; based on the high-precision mathematical model of the full operating conditions, obtains the system optimization model through overall integration, and obtains the optimization potential of the unit and parameter adjustment through scenario hypothesis calculation to realize the real-time operation optimization of the unit.

[0004] Although the above technology solves some problems, there are still some problems, such as: the determination of the working plan for the secondary reheat unit does not fully consider the equipment loss and the evaluation of future electricity consumption, resulting in abnormally high working costs and maintenance costs. Summary of the Invention

[0005] The object of the present invention is to solve the problem that the determination of the working plan for the secondary reheat unit does not fully consider the equipment loss and the evaluation of future electricity consumption, resulting in abnormally high working costs and maintenance costs, and proposes an operation optimization method and system for the load of a secondary reheat unit based on big data.

[0006] In the first aspect of the implementation of the present invention, an operation optimization method for the load of a secondary reheat unit based on big data is first proposed. The method includes:

[0007] Obtain the target electricity consumption collected in the target area in the current period, and input the target electricity consumption into the short-term electricity consumption prediction model to obtain the predicted electricity consumption in the next period of the current period;

[0008] Determine a set of working plans according to the predicted power consumption, and calculate the equipment cost score for any one set of working plans in the set of working plans;

[0009] Determine the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit operates according to the working parameters; the target equipment cost score is the equipment cost score with the serial number 1 in the set of working plans.

[0010] Optionally, before inputting the power consumption into the short-term power consumption prediction model to obtain the predicted power consumption for the next period, the method further includes:

[0011] Obtain the historical power consumption and historical meteorological data of the target area, align the historical power consumption and the historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set;

[0012] Input the feature data set into the NARX neural network model for training to obtain model parameters, and iteratively update the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term power consumption prediction model;

[0013] Obtain the predicted meteorological data for the next period of the target area in the current period, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption for the next period.

[0014] Optionally, calculating the equipment cost score for any one set of working plans in the set of working plans includes:

[0015] Determine the working parameters of the secondary reheat unit according to the working plan, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature;

[0016] Calculate the equipment cost score for each set of working plans in the set of working plans according to the simulation data, and arrange the equipment cost scores in ascending order to obtain an equipment cost score table;

[0017] Equipment cost score calculation formula:

[0018]

[0019] Where F is the equipment cost score, T1 is the steam temperature, T0 is the preset standard steam temperature, P1 is the steam pressure, P0 is the preset standard steam pressure, t1 is the preset time period, and ω is a constant proportionality coefficient and is not zero.

[0020] Optionally, after the secondary reheat unit operates according to the working parameters, it further includes:

[0021] Real-time monitor the secondary reheat unit to obtain operation data, and calculate a real-time feedback score based on the operation data;

[0022] Update the constant proportionality coefficient of the equipment cost score calculation formula according to the real-time feedback score.

[0023] Optionally, evaluating the real-time feedback score includes:

[0024] If the real-time feedback score is greater than the evaluation threshold, it is determined that the accuracy of the equipment cost score is missing, and the constant proportionality coefficient in the equipment cost score calculation formula is updated;

[0025] If the absolute temperature difference is greater than the temperature threshold range, then for the coefficient in the equipment cost score calculation formula Update the coefficient; the absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature;

[0026] If the absolute pressure difference is greater than the pressure threshold range, then update the ω coefficient in the equipment cost score calculation formula; the absolute pressure difference is calculated from the simulated steam pressure and the actual steam pressure.

[0027] In the second aspect of the implementation of the present invention, an operation optimization system for the load of a secondary reheat unit based on big data is proposed, including: a power consumption prediction module, a working plan determination module, and a working parameter operation module:

[0028] The power consumption prediction module is used to obtain the target power consumption collected in the target area in the current period, and input the target power consumption into the short-term power consumption prediction model to obtain the predicted power consumption in the next period;

[0029] The working plan determination module is used to determine a set of working plans according to the predicted power consumption, and calculate the equipment cost score for any one of the working plans in the set of working plans;

[0030] The working parameter operation module is used to determine the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit operates according to the working parameters; the target equipment cost score is the equipment cost score with the serial number one in the set of working plans.

[0031] Optionally, the power consumption prediction module includes: a training data acquisition module, a model update and iteration module, and a model prediction module:

[0032] The training data acquisition module is used to acquire the historical power consumption and historical meteorological data of the target area, align the historical power consumption and the historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set;

[0033] The model update and iteration module is used to input the feature data set into the NARX neural network model for training to obtain model parameters, and iteratively update the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term power consumption prediction model;

[0034] The model prediction module is used to acquire the predicted meteorological data for the next period of the target area in the current period, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption for the next period.

[0035] Optionally, the working scheme determination module includes: a data simulation module and an equipment cost calculation module:

[0036] The data simulation module is used to determine the working parameters of the secondary reheating unit according to the working scheme, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature;

[0037] The equipment cost calculation module is used to calculate the equipment cost score of each set of working schemes in the working scheme set according to the simulation data, and arrange the equipment cost scores in ascending order to obtain an equipment cost score table;

[0038] Equipment cost score calculation formula:

[0039]

[0040] where F is the equipment cost score, T1 is the steam temperature, T0 is the preset standard steam temperature, P1 is the steam pressure, P0 is the preset standard steam pressure, t1 is the preset time period, and ω is a constant proportionality coefficient, both of which are not zero.

[0041] Optionally, the system further includes: a feedback score calculation module and an evaluation and update coefficient module

[0042] The feedback score calculation module is used to monitor the operation data of the secondary reheating unit in real time, and calculate the real-time feedback score according to the operation data;

[0043] The evaluation and update coefficient module is used to update the constant proportionality coefficient of the equipment cost score calculation formula according to the real-time feedback score.

[0044] Optionally, the evaluation update coefficient module includes: a coefficient judgment module, a first execution update module, and a second execution update module:

[0045] The coefficient judgment module is configured to, if the real-time feedback score is greater than the evaluation threshold, determine that the accuracy of the equipment cost score is missing, and update the constant proportional coefficient in the equipment cost score calculation formula;

[0046] The first execution update module is configured to, if the absolute temperature difference is greater than the temperature threshold range, update the coefficient in the equipment cost score calculation formula; The absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature;

[0047] Advantages of the present invention:

[0048] The present invention provides an operation optimization method for the load of a secondary reheat unit based on big data. By obtaining the target power consumption collected in the target area in the current cycle, the target power consumption is input into the short-term power consumption prediction model to obtain the predicted power consumption for the next cycle of the current cycle; a set of working plans is determined according to the predicted power consumption, and the equipment cost score is calculated for any one of the working plans in the set of working plans; the working parameters of the secondary reheat unit are determined according to the target equipment cost score, so that the secondary reheat unit works according to the working parameters; by obtaining the target power consumption and using the prediction model to plan power resources, the power consumption demand for the next cycle can be accurately estimated, and then multiple working plans can be formulated and the equipment cost can be evaluated. Finally, the power generation plan with the best cost-benefit is selected to ensure that while meeting the power consumption demand, the equipment wear is minimized and the power generation efficiency and economy are improved. Description of the Drawings

[0049] The present invention will be further described below with reference to the accompanying drawings.

[0050] Figure 1 FIG. is a flowchart of an operation optimization method for the load of a secondary reheat unit based on big data provided by an embodiment of the present invention;

[0051] Figure 2 FIG. is a framework diagram of an operation optimization system for the load of a secondary reheat unit based on big data provided by an embodiment of the present invention. Detailed Embodiments

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying 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. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the descriptions such as "first" and "second" in the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the fact that those skilled in the art can implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0053] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0054] The embodiment of the present invention provides an operation optimization method for the load of a secondary reheat unit based on big data. Refer to Figure 1 , Figure 1 is a flowchart of the operation optimization method for the load of a secondary reheat unit based on big data provided by the embodiment of the present invention. The method includes the following steps:

[0055] S101, obtain the target power consumption collected in the target area in the current period, and input the target power consumption into the short-term power consumption prediction model to obtain the predicted power consumption in the next period of the current period;

[0056] S102, determine a set of working plans according to the predicted power consumption, and calculate the equipment cost score for any one set of working plans in the set of working plans;

[0057] S103, determine the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit works according to the working parameters;

[0058] The target equipment cost score is the equipment cost score with the serial number one in the set of working plans.

[0059] Based on the operation optimization method for the load of a secondary reheat unit based on big data provided by the embodiments of the present invention, by obtaining the target electricity consumption and using a prediction model to plan power resources, it can accurately estimate the electricity demand in the next cycle, and then formulate multiple working plans and evaluate the equipment costs. Finally, it selects the power generation plan with the optimal cost-benefit, ensuring that while meeting the electricity demand, the equipment wear is minimized, and the power generation efficiency and economy are improved.

[0060] In one implementation, the load is the electricity consumption, and the working parameter is the coal conveying amount per unit time; obtain the target electricity consumption collected in the target area in the current cycle, use the short-term electricity consumption prediction model to predict the electricity consumption in the next cycle, which can accurately plan power resources, and then determine multiple working plans according to the prediction results, and calculate the equipment cost scores of each plan, so as to select the plan with the optimal cost-benefit, that is, generate electricity with the least equipment wear while ensuring to meet the electricity consumption in the next cycle. The above steps not only improve the efficiency of power management but also guarantee the economic benefits.

[0061] In one implementation, after determining the working plan, finely adjust the working parameters of the secondary reheat unit according to the equipment cost score to ensure its operation in the optimal state. This step enhances the scientificity and accuracy of decision-making through accurate data analysis and model prediction, thereby improving the operation efficiency and reliability of the secondary reheat unit; the current cycle is a cycle of one week (seven days), and the next cycle is the next cycle based on the current cycle as the reference cycle.

[0062] In one implementation, the working plan is the coal feeding amount during the operation of the secondary reheat unit, that is, the coal conveying amount per unit time; the secondary reheat unit is responsible for power supply in the target area. When the electricity consumption is greater than the power generation, the secondary reheat unit needs to increase the power generation. Therefore, the coal conveying amount per unit time needs to be increased, and the increase in the coal conveying amount will cause abnormal wear of the equipment of the secondary reheat unit. For example: the expansion and contraction caused by abnormal equipment temperature, and the impact on the fan blades of the steam turbine due to the sharp increase in steam pressure and gas transmission volume in a short time.

[0063] In one embodiment, before step S101, it includes:

[0064] Obtain the historical electricity consumption and historical meteorological data of the target area, align the historical electricity consumption and historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set;

[0065] Input the feature data set into the NARX neural network model for training to obtain model parameters, and perform iterative updates on the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term electricity consumption prediction model;

[0066] Obtain the predicted meteorological data for the next cycle of the target area in the current cycle, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption for the next cycle.

[0067] In one implementation, the NARX neural network model has a powerful time series modeling ability. Using the NARX neural network model as the short-term power consumption prediction model can significantly improve the accuracy and reliability of short-term power consumption prediction. By using time series alignment and fuzzy clustering processing of historical power consumption and historical meteorological data, deeper feature information can be mined, the correlation between weather and power consumption can be enhanced, so that when the model faces the predicted meteorological data of a new cycle, it can more accurately predict the power consumption of the target area; after completing feature recognition and extraction of power consumption and meteorological data, the features are used as inputs to the model for training to obtain the short-term load prediction model.

[0068] In one implementation, by performing fuzzy clustering on historical power consumption, similar power consumption curves are divided into the same category. The power consumption curve is a curve with time as the abscissa and power consumption as the ordinate, which is used to reflect the change in power consumption in the time series. Mapping the meteorological data in the same time series can enhance the correlation between meteorological data and power consumption data; the advantage of fuzzy clustering is that it can handle the uncertainty in the data, making the classification results more flexible and accurate; perform the first feature extraction on the load curve to identify important feature points in the load curve, such as peaks and valleys, etc., providing a basis for subsequent feature recognition. On the basis of the first feature extraction, use the statistical frequency distribution method to further screen and optimize the features. By counting the occurrence frequencies of various load characteristics, the most representative features are selected as the overall feature markers to improve the accuracy and generalization ability of the subsequent prediction model.

[0069] In one embodiment, step S102 includes:

[0070] Determine the working parameters of the secondary reheat unit according to the working plan, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature;

[0071] Calculate the equipment cost score for each set of working plans in the working plan set according to the simulation data, and arrange the equipment cost scores in ascending order to obtain the equipment cost score table;

[0072] Equipment cost score calculation formula:

[0073]

[0074] Where F is the equipment cost score, T1 is the steam temperature, T0 is the preset standard steam temperature, P1 is the steam pressure, P0 is the preset standard steam pressure, and t1 is the preset time period. Both \( \alpha \) and \( \omega \) are constant proportionality coefficients and are not zero.

[0075] In one implementation, during the simulation of the power generation mode of a secondary reheat unit, by constructing an accurate mathematical model and inputting relevant parameters, the operating state of the unit under different working schemes is simulated, and the equipment cost score is calculated. Its operation process is efficient and accurate, and it can quickly generate an equipment cost score table arranged in ascending order of cost and assign serial numbers to the equipment cost score table, starting from the smallest and arranging them in sequence. For example, the smallest equipment cost score has a serial number of 1, and so on. This provides strong data support for optimizing the power generation mode; in the simulation of the steam system or the thermal system, the steam pressure is a key simulation parameter. By setting the initial conditions, boundary conditions of the system, and the physical properties of the steam, the change of the steam pressure can be simulated. For example, in the dynamic simulation analysis of a steam accumulator, the change of the steam pressure can be predicted through simulation. In the simulation models of some equipment, the equipment temperature sets the heat transfer processes such as heat conduction and heat convection of the equipment, as well as the initial temperature of the equipment, and the change of the equipment temperature can be simulated; the numerical values obtained from a single simulation (steam pressure and steam temperature) are more than one, so the difference in simulation numerical values can be reduced by taking the average value.

[0076] In one implementation, the coal conveying speed is determined according to the predicted power consumption, that is, while completing the power generation within the specified time, the minimum equipment loss should be ensured. Equipment loss is inevitable during the operation of a secondary reheat unit. Therefore, by reducing its wear, the service life of the equipment can be maximally extended, and the cost can be further reduced; the equipment cost scores are arranged in ascending order to obtain an equipment cost score table, that is, the equipment cost scores are arranged in ascending numerical order, and the smallest one is the working parameter that satisfies the minimum equipment loss.

[0077] In one embodiment, step S102 further includes:

[0078] Real-time monitor the secondary reheat unit to obtain operation data, and calculate the real-time feedback score according to the operation data;

[0079] Update the constant proportionality coefficients of the equipment cost score calculation formula according to the real-time feedback score.

[0080] In one implementation, the real-time feedback score calculation formula:

[0081]

[0082] where \( \alpha \), \( \beta \), and \( \gamma \) are all constant proportionality coefficients and are not zero, \( T_2 \) is the equipment temperature, \( T \) maxT1 is the highest temperature the equipment can withstand, T3 is the preset standard temperature of the equipment, t0 is the preset time period, t is the duration of noise occurrence within the t0 time period, N i Ni is the noise intensity of the i-th equipment, n is the total number of times equipment noise occurs, Z j Aj is the equipment amplitude of the j-th equipment, m is the total number of times equipment amplitude occurs, P3 is the preset standard steam pressure in the steam transmission pipeline, P2 is the steam pressure in the steam transmission pipeline, T3 is the preset standard temperature in the steam transmission pipeline, T2 is the steam temperature in the steam transmission pipeline, L0 is the preset steam flow rate in the steam transmission pipeline, L is the steam flow rate of the steam transmission pipeline.

[0083] In one implementation, after the secondary reheat unit operates according to the working parameters, real-time monitoring is carried out on the steam transmission pipeline and steam turbine in the secondary reheat unit, and the state of the equipment can be effectively obtained. Through the real-time feedback scoring calculation formula, the state of the equipment can be quantified, realizing precise monitoring and rapid response to the operation state of the unit; evaluating the real-time feedback score and updating the constant proportionality coefficient of the equipment cost scoring calculation formula can ensure more accurate equipment cost evaluation when determining tasks next time, so as to reduce the wear of the equipment.

[0084] In one implementation, the real-time feedback scoring calculation formula includes the monitoring of the equipment part and the monitoring of the steam transmission pipeline. From these two aspects, the effects brought about by operating according to the working parameters can be more accurately reflected. By comprehensively monitoring the vibration, noise, and temperature parameters of the equipment (steam turbine), as well as key indicators such as the steam pressure, steam temperature, and steam flow rate of the steam transmission pipeline, the operating state and performance of the equipment can be reflected in real time. Through the monitoring data, it not only helps to accurately evaluate the degree of equipment loss, but also can optimize the working parameters of the equipment and the equipment cost scoring calculation formula, improve the operating efficiency and stability, and at the same time reduce energy consumption and operating costs.

[0085] In one embodiment, the evaluation of the real-time feedback score includes:

[0086] If the real-time feedback score is greater than the evaluation threshold, it is determined that the accuracy of the equipment cost score is missing, and the constant proportionality coefficient in the equipment cost scoring calculation formula is updated;

[0087] If the absolute temperature difference is greater than the temperature threshold range, then for the coefficient in the equipment cost scoring calculation formula is updated; the absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature;

[0088] If the absolute pressure difference is greater than the pressure threshold range, then the ω coefficient in the equipment cost scoring calculation formula is updated; the absolute pressure difference is calculated from the simulated steam pressure and the actual steam pressure.

[0089] In one implementation, the coefficient in the device cost scoring calculation formula corresponds to the steam temperature, and the ω coefficient in the device cost scoring calculation formula corresponds to the steam pressure. When the real-time feedback score is greater than the evaluation threshold, it indicates that the evaluation of the device cost during actual operation is inaccurate at this time. According to the actual situation, the coefficient of the steam temperature needs to be updated and corrected to make the device cost simulated next time more accurate; update and correct the coefficient ω and . For example, when the coefficient ω is 0.4 and the real-time feedback score at this time is greater than the evaluation threshold, and the absolute pressure difference between the simulated steam pressure and the actual steam pressure is not within the pressure threshold range, correction and update are required. When the absolute pressure difference is greater than the upper limit of the pressure threshold range, the coefficient ω is increased, from 0.4 to 0.45. The specific numerical change needs to be determined by the staff according to the actual situation; the absolute pressure difference = |simulated steam pressure - actual steam pressure|, and the absolute temperature difference is calculated by |simulated steam temperature - actual steam temperature|.

[0090] Based on the same inventive concept, the embodiment of the present invention also provides an operation optimization system for the load of a secondary reheat unit based on big data. Refer to Figure 2 , Figure 2 which is a schematic structural diagram of the operation optimization system for the load of a secondary reheat unit based on big data provided by the embodiment of the present invention, including: a power consumption prediction module, a working plan determination module, and a working parameter operation module:

[0091] The power consumption prediction module is used to obtain the target power consumption collected in the target area in the current period, and input the target power consumption into the short-term power consumption prediction model to obtain the predicted power consumption in the next period;

[0092] The working plan determination module is used to determine a set of working plans according to the predicted power consumption, and calculate the device cost score for any one of the working plans in the set of working plans;

[0093] The working parameter operation module is used to determine the working parameters of the secondary reheat unit according to the target device cost score, so that the secondary reheat unit works according to the working parameters; the target device cost score is the device cost score with the serial number one in the set of working plans.

[0094] Based on the operation optimization system for the load of a secondary reheat unit based on big data provided by the embodiment of the present invention, by obtaining the target power consumption and using the prediction model to plan power resources, it can accurately estimate the power consumption demand in the next period, and then formulate multiple working plans and evaluate the device cost. Finally, the power generation plan with the best cost-benefit is selected to ensure that while meeting the power consumption demand, the equipment wear is minimized, and the power generation efficiency and economy are improved.

[0095] In one embodiment, the power consumption prediction module includes: a training data acquisition module, a model update and iteration module, and a model prediction module:

[0096] The training data acquisition module is configured to acquire the historical power consumption and historical meteorological data of the target area, align the historical power consumption and historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set;

[0097] The model update and iteration module is configured to input the feature data set into the NARX neural network model for training to obtain model parameters, and perform iterative updates on the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term power consumption prediction model;

[0098] The model prediction module is configured to acquire the predicted meteorological data for the next cycle in the current cycle of the target area, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption for the next cycle.

[0099] In one embodiment, the working plan determination module includes: a data simulation module and an equipment cost calculation module:

[0100] The data simulation module is configured to determine the working parameters of the secondary reheating unit according to the working plan, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature;

[0101] The equipment cost calculation module is configured to calculate the equipment cost score of each working plan in the working plan set according to the simulation data, and arrange the equipment cost scores in ascending order to obtain an equipment cost score table;

[0102] Equipment cost score calculation formula:

[0103]

[0104] Where F is the equipment cost score, T1 is the steam temperature, T0 is the preset standard steam temperature, P1 is the steam pressure, P0 is the preset standard steam pressure, t1 is the preset time period, and ω is a constant proportionality coefficient, both of which are not zero.

[0105] In one embodiment, the system further includes: a feedback score calculation module and an evaluation and update coefficient module

[0106] The feedback score calculation module is configured to monitor the operation data of the secondary reheating unit in real time, and calculate the real-time feedback score according to the operation data;

[0107] The evaluation and update coefficient module is configured to update the constant proportionality coefficient of the equipment cost score calculation formula according to the real-time feedback score.

[0108] In one embodiment, the evaluation update coefficient module includes: a coefficient judgment module, a first execution update module, and a second execution update module:

[0109] The coefficient judgment module is configured to, if the real-time feedback score is greater than the evaluation threshold, determine that the accuracy of the equipment cost score is missing, and update the constant proportional coefficient in the equipment cost score calculation formula;

[0110] The first execution update module is configured to, if the absolute temperature difference is greater than the temperature threshold range, update the coefficient in the equipment cost score calculation formula; The absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature;

[0111] The second execution update module is configured to, if the absolute pressure difference is greater than the pressure threshold range, update the ω coefficient in the equipment cost score calculation formula; the absolute pressure difference is calculated from the simulated steam pressure and the actual steam pressure.

[0112] The above has described in detail one embodiment of the present invention, but the content is only the preferred embodiment of the present invention and cannot be considered as limiting the implementation scope of the present invention. All equal changes and improvements made according to the scope of the present invention application shall still fall within the scope covered by the patent of the present invention.

Claims

1. An operation optimization method for the load of a secondary reheat unit based on big data, characterized in that The method includes: Obtain the target power consumption collected in the target area during the current period, and input the target power consumption into the short-term power consumption prediction model to obtain the predicted power consumption for the next period of the current period; Determine a set of working plans according to the predicted power consumption, and calculate the equipment cost score for any one set of working plans in the set of working plans; Determine the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit works according to the working parameters; the target equipment cost score is the equipment cost score with the serial number one in the set of working plans; The specific process of determining the set of working plans according to the predicted power consumption includes: Obtain the target power consumption collected in the target area during the current period, use the short-term power consumption prediction model to predict the power consumption for the next period, and then determine multiple working plans according to the prediction results, and calculate the equipment cost score for each plan, so as to select the plan with the best cost-benefit, that is, to minimize equipment wear while meeting the power consumption demand; the working plan is the coal feeding amount during the operation of the secondary reheat unit, that is, the coal conveying amount per unit time; Calculating the equipment cost score for any one set of working plans in the set of working plans includes: Determine the working parameters of the secondary reheat unit according to the working plan, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature; Calculate the equipment cost score for each set of working plans in the set of working plans according to the simulation data, and arrange the equipment cost scores in ascending order to obtain an equipment cost score table; Equipment cost score calculation formula: ； Among them, F is the equipment cost score, is the steam temperature, is the preset standard steam temperature, is the steam pressure, is the preset standard steam pressure, is the preset time period, and the constant proportionality coefficients are all non-zero.

2. The operation optimization method for the load of a secondary reheat unit based on big data according to claim 1, wherein, Before inputting the power consumption into the short-term power consumption prediction model to obtain the predicted power consumption for the next period, the method further includes: Obtain the historical power consumption and historical meteorological data of the target area, align the historical power consumption and the historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set; Input the feature data set into the NARX neural network model for training to obtain model parameters, and iteratively update the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term power consumption prediction model; Obtain the predicted meteorological data for the next period of the target area in the current period, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption for the next period.

3. The operation optimization method for the load of a secondary reheat unit based on big data according to claim 2, characterized in that After the secondary reheat unit works according to the working parameters, it further includes: Real-time monitor the secondary reheat unit to obtain operation data, and calculate the real-time feedback score according to the operation data; Update the constant proportionality coefficient of the equipment cost score calculation formula according to the real-time feedback score.

4. The operation optimization method for the load of a secondary reheat unit based on big data according to claim 3, characterized in that, Updating the constant proportionality coefficient of the equipment cost score calculation formula according to the real-time feedback score includes: If the real-time feedback score is greater than the evaluation threshold, it is determined that the accuracy of the equipment cost score is missing, and the constant proportionality coefficient in the equipment cost score calculation formula is updated; If the absolute temperature difference is greater than the temperature threshold range, then update the coefficient in the calculation formula for the equipment cost score; the absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature; If the absolute pressure difference is greater than the pressure threshold range, then update the coefficient in the calculation formula for the equipment cost score; the absolute pressure difference is calculated from the simulated steam pressure and the actual steam pressure.

5. An operation optimization system for the load of a secondary reheat unit based on big data, characterized in that, The system includes: a power consumption prediction module, a working plan determination module, and a working parameter operation module: The power consumption prediction module is used to obtain the target power consumption collected in the target area in the current period, and input the target power consumption into the short-term power consumption prediction model to obtain the predicted power consumption in the next period; The working plan determination module is used to determine a set of working plans according to the predicted power consumption, and calculate the equipment cost score for any set of working plans in the set of working plans; The working parameter operation module is used to determine the working parameters of the secondary reheat unit according to the target equipment cost score, so that the secondary reheat unit works according to the working parameters; the target equipment cost score is the equipment cost score with the serial number one in the set of working plans; The specific process of determining the set of working plans according to the predicted power consumption includes: Obtain the target power consumption collected in the target area in the current period, use the short-term power consumption prediction model to predict the power consumption in the next period, and then determine multiple working plans according to the prediction result, and calculate the equipment cost score of each plan, so as to select the plan with the best cost-benefit, that is, while meeting the power consumption demand, minimize equipment wear; the working plan is the coal feeding amount during the operation of the secondary reheat unit, that is, the coal conveying amount per unit time; The working plan determination module includes: a data simulation module and an equipment cost calculation module: The data simulation module is used to determine the working parameters of the secondary reheat unit according to the working plan, and perform simulation according to the working parameters to obtain simulation data; the simulation data includes: steam pressure and steam temperature; The equipment cost calculation module is used to calculate the equipment cost score of each set of working plans in the set of working plans according to the simulation data, and arrange the equipment cost scores in ascending order to obtain an equipment cost score table; Equipment cost score calculation formula: ； where F is the equipment cost score, is the steam temperature, is the preset standard steam temperature, is the steam pressure, is the preset standard steam pressure, is the preset time period, and are non-zero constant proportionality coefficients.

6. The operation optimization system for the load of a secondary reheat unit based on big data according to claim 5, characterized in that, The power consumption prediction module includes: a training data acquisition module, a model update and iteration module, and a model prediction module: The training data acquisition module is used to obtain the historical power consumption and historical meteorological data of the target area, align the historical power consumption and the historical meteorological data according to the time series to obtain a training data set, and perform fuzzy clustering on the training data set to obtain a feature data set; The model update and iteration module is used to input the feature data set into the NARX neural network model for training to obtain model parameters, and perform iterative updates on the weights and biases of each layer in the NARX neural network model according to the model parameters to obtain a short-term power consumption prediction model; The model prediction module is used to obtain the predicted meteorological data in the next period of the target area in the current period, and input the target power consumption and the predicted meteorological data into the short-term power consumption prediction model to obtain the predicted power consumption in the next period.

7. The operation optimization system for the load of a secondary reheat unit based on big data according to claim 6, characterized in that The system further includes: a feedback score calculation module and an evaluation update coefficient module The feedback score calculation module is used to monitor the operation data of the secondary reheat unit in real time, and calculate the real-time feedback score according to the operation data; The evaluation and update coefficient module is used to update the constant proportional coefficient in the device cost score calculation formula according to the real-time feedback score.

8. The operation optimization system for the load of a secondary reheat unit based on big data according to claim 7, characterized in that, The evaluation and update coefficient module includes: a coefficient judgment module, a first execution update module, and a second execution update module: The coefficient judgment module is used to determine that the accuracy of the device cost score is missing if the real-time feedback score is greater than the evaluation threshold, and update the constant proportional coefficient in the device cost score calculation formula; The first execution and update module is used to update the coefficient in the calculation formula of the equipment cost score if the absolute temperature difference is greater than the temperature threshold range; the absolute temperature difference is calculated from the simulated steam temperature and the actual steam temperature; The second execution update module is used to update the coefficient in the equipment cost scoring calculation formula if the absolute pressure difference is greater than the pressure threshold range; the absolute pressure difference is calculated from the simulated steam pressure and the actual steam pressure.

Images