Steam power system production optimization method, device, equipment and storage medium

Abstract

The application discloses a steam power system production scheduling optimization method, device, equipment and storage medium, wherein the method comprises the following steps: fitting the mathematical relationship between the steam demand data of each pressure level and the preset working condition data in the process of each production device; generating the steam pipe network mathematical model corresponding to each pressure level of the whole refinery, and generating the corresponding relationship between the loss calculation deviation and the weather data; calculating the predicted steam demand data of each level required by the process of each production device; obtaining the weather data of the target production period, and determining the predicted loss calculation deviation according to the weather data; generating the predicted steam pipe network loss of each production device corresponding to each pressure level in the target production period; calculating the total steam demand corresponding to each pressure level of each production device in the target production period, and carrying out power station production scheduling optimization according to the total steam demand. The total steam demand obtained by the application is accurate, and the optimization effect of production scheduling optimization is improved.

Description

Technical Field

[0001] This invention relates to the petrochemical field, and in particular to a method, apparatus, equipment, and storage medium for optimizing production scheduling of steam power systems. Background Technology

[0002] The steam power system of petrochemical enterprises converts primary energy sources such as coal, oil, and fuel gas into secondary energy sources such as steam and electricity to provide the heat and electricity required for the production process. While providing energy for the production equipment, it also consumes a large amount of energy itself. Its efficient operation is crucial for the enterprise to save energy and reduce carbon emissions.

[0003] The steam power system of a petrochemical enterprise includes three stages: steam production, steam transmission, and steam consumption. According to the stage classification, the steam production stage includes power boilers, waste heat boilers of the unit, etc.; the steam transmission stage includes steam pipeline network; and the steam consumption stage includes steam turbines of the unit, heating equipment, etc.

[0004] In the actual production process of petrochemical enterprises, the scheduling of steam power systems generally begins after the enterprise's production plan is finalized. Based on the start-up and shutdown status of production units, the total steam demand is determined, and then the matching of boilers and turbines is decided based on this total steam demand. This entire process relies on the experience of the scheduling personnel to make judgments, such as determining the steam demand of each unit, which boiler to operate, and which turbine to operate.

[0005] Current logistics scheduling is mostly based on mature commercial software, such as PIMS. However, the inventors have found that the existing technologies do not take into account all the factors that have a significant impact on the power system in practical applications, resulting in poor optimization accuracy and consequently, less than ideal optimization and energy-saving effects of the steam power system.

[0006] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this invention is to improve the optimization and energy-saving effect of steam power systems.

[0008] This invention provides a method for optimizing the production scheduling of a steam power system, comprising the following steps:

[0009] S11. Based on the historical data of each production unit in the entire refinery, fit the mathematical relationship between the steam demand data of each pressure level and the preset operating condition data in the process of each production unit; the preset operating condition data includes production unit load data, raw material property data, product structure data and unit advancement data.

[0010] S12. Generate a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0011] S13. Obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0012] S14. Obtain weather data for the target production cycle, and determine the prediction loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0013] S15. Based on the predicted loss calculation deviation and the steam pipeline mathematical model, generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the entire refinery during the target production cycle.

[0014] S16. Calculate the total steam demand for each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and optimize the power station scheduling based on the total steam demand.

[0015] Preferably, in this invention, the predicted steam demand data for each level required by the process of each of the production units is calculated based on the mathematical relationship, including:

[0016] The steam demand data for each stage of the process in each production unit is obtained by using an empirical formula fitting method for prediction, including:

[0017] The formulas used to calculate the steam demand data for a specific level of a production unit include:

[0018] F 蒸汽 =F 功耗 +F 热耗 -F 产汽 ;

[0019] Among them, F 蒸汽 This represents the total steam consumption of the production unit at a certain level; a positive number represents steam consumption, and a negative number represents steam production. F 功耗 This refers to the steam consumption of the production unit at a certain level for performing work; F 热耗 This refers to the steam consumption for heating in this production unit at a certain level of steam; F 产汽 This refers to the steam production rate of a specific grade of steam corresponding to this production unit.

[0020] The F功耗 The calculation formula, obtained under the reference working condition, includes:

[0021]

[0022] Among them, F 功耗i F represents the steam consumption of the i-th turbine in this production unit. 基准i η represents the power consumption of the i-th turbine under the baseline operating condition. 负荷 The production load rate of this production unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions; η 效率 η is the turbine's efficiency under current operating conditions divided by its efficiency under reference operating conditions. 第一修正系数 To account for correction coefficients that take into account the properties of raw materials and products, the correction coefficients are obtained using a neural network fitting method; n is the number of turbine units; the baseline operating condition includes the operating condition when the load of the production unit is 100%;

[0023] The F 热耗 The calculation formula, obtained under standard operating conditions, includes:

[0024]

[0025] Among them, F 热耗i Steam consumption for a specific process in a specific process unit; F 基准i η represents the steam consumption of this process under baseline operating conditions. 负荷 The production load rate of this process unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions; η 第二修正系数 To account for correction coefficients for the properties of raw materials and products, a neural network fitting method was used to obtain the value for the steam used in this process; n is the consumption of steam in this process.

[0026] Preferably, in this invention, the F 热耗 The following formula can also be used to calculate it:

[0027] F 热耗 =F 基准 ×η 负荷 ×η 第二修正系数 ;

[0028] Among them, F 基准 η represents the total steam consumption of a certain production unit's process. 第二修正系数 To account for the properties of raw materials and products, correction coefficients are obtained using a neural network fitting method for the overall process steam.

[0029] Preferably, in this invention, generating the mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery includes:

[0030] The mathematical models of the steam pipeline network at all levels of the entire refinery are modeled using a graph theory-based approach, and steam pipeline network loss prediction is carried out. The mathematical models of the steam pipeline network include hydraulic calculation equations and thermodynamic calculation equations.

[0031] The relationship between flow rate and pressure included in the hydraulic calculation equations for the pipeline network is as follows:

[0032] AG p A T p n =q n ;

[0033] Where, q n For pipeline flow rate, p n For node pressure, G p Here are the hydraulic characteristic parameters of the pipeline, and A is the pipeline network correlation matrix;

[0034] The relationship between flow rate and temperature drop included in the thermodynamic calculation equations for the pipeline network is as follows:

[0035] AG t A T T n =q n ;

[0036] Among them, T n For node temperature, G t These are the thermodynamic properties of the pipeline.

[0037] Among them, the thickness R of the pipeline insulation layer Q This represents the heat dissipation thermal resistance of the steam pipeline, and its expression is:

[0038]

[0039] Where η is the insulation reduction efficiency, obtained by fitting historical data of the steam pipeline; α w The convective heat transfer coefficient between the outer wall of the pipe and the environment is calculated based on the external environment and weather; d0 is the inner diameter of the pipe; α g λ is the convective heat transfer coefficient between steam and the inner wall of the pipe; Ti d is the thermal conductivity of the i-th layer of insulation material; di is the inner diameter of the i-th layer of insulation material; d n+1 It is the outer diameter of the outermost insulation layer.

[0040] Preferably, in this invention, the step of optimizing power station scheduling based on the total steam demand includes:

[0041] Optimize the production scheduling of boilers and steam turbines, including:

[0042] Fitting the efficiency of boilers and steam turbines includes:

[0043] The fitting method for the steam turbine adopts the Willan model. For a multi-stage steam turbine, its expression is:

[0044]

[0045] Where, N i Let W be the Willan coefficient for the i-th stage of the steam turbine, mi be the flow rate of the i-th stage of the steam turbine, and W be the flow rate of the i-th stage of the steam turbine. INT N is the intercept coefficient; i and W INT Obtained by fitting historical operating parameters of the steam turbine;

[0046] The expression for a boiler is:

[0047] η=a*(m / m max ) 2 +b*(m / m max )+c;

[0048] Where m is the actual steam production; m max The maximum steam production is represented by a; a, b, and c are dimensionless parameters obtained by fitting the historical operating parameters of the boiler.

[0049] Preferably, in this invention, the step of optimizing power station scheduling based on the total steam demand includes:

[0050] Based on the historical operating parameters of the boilers and turbines in the power station, the efficiency of each stage of steam extraction of each boiler and each turbine under each production load is obtained by fitting.

[0051] Under the premise of meeting the total demand for external steam supply at all levels, and under the current price system, the optimized start-up and shutdown status and load of each boiler and turbine are calculated based on the preset optimization model.

[0052] Preferably, in this invention, the optimization model includes:

[0053]

[0054] Where, q 电 The local electricity price; q 燃料 For fuel prices; Q 低 It is the lower heating value of fuel.

[0055] In another aspect of the invention, a steam power system scheduling optimization device is also provided, comprising:

[0056] The mathematical relationship generation unit is used to fit the mathematical relationship between the steam demand data at each pressure level and the preset operating condition data in the process of each production unit in the whole refinery, based on the historical data of each production unit. The preset operating condition data includes production unit load data, raw material property data, product structure data and unit advancement data.

[0057] The mathematical model generation unit is used to generate mathematical models of the steam pipeline network corresponding to each pressure level of the entire refinery, and to generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0058] The steam demand calculation unit is used to obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and to calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0059] The loss deviation calculation unit is used to acquire weather data for the target production cycle and determine the predicted loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0060] The predicted loss calculation unit is used to generate the predicted steam pipeline losses corresponding to each pressure level of each production unit in the entire refinery during the target production cycle, based on the predicted loss calculation deviation and the steam pipeline mathematical model.

[0061] The production scheduling optimization unit is used to calculate the total steam demand corresponding to each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and to carry out power station production scheduling optimization based on the total steam demand.

[0062] In another aspect of this invention, a steam power system scheduling optimization device is also provided, comprising:

[0063] Memory, used to store computer programs;

[0064] A processor is used to invoke and execute the computer program to implement the various steps of the steam power system scheduling optimization method as described in any of the preceding claims.

[0065] In another aspect of the present invention, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the various steps of the steam power system production scheduling optimization method as described in any of the preceding claims.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] In existing technologies, logistics scheduling is mostly based on mature commercial software, such as PIMS. In scheduling, process requirements are mostly the basic principle. However, power system optimization is mostly done by self-written programs, which makes it more difficult in actual operation.

[0068] On the other hand, the inventors discovered through research that one important reason why the production scheduling in the existing technology cannot achieve good optimization results is that it does not take into account the impact of the steam pipeline network, including steam pipeline network losses, as well as the impact of weather factors (such as temperature, humidity, wind speed, whether it is raining, and whether it is snowing). These factors will have a significant impact on the power system, thereby affecting the final optimization accuracy and optimization effect.

[0069] Based on the above research, this invention first fits the mathematical relationship between the steam demand data at each pressure level and the preset operating condition data in the process of each production unit; then, it generates a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generates the correspondence between the loss calculation deviation and weather data; in this invention, by using the correspondence between the loss calculation deviation and weather data, the predicted loss calculation deviation of the target production cycle can be determined, and the calculated steam pipeline network loss for the target production cycle can be corrected to obtain accurate predicted steam pipeline network losses for each pressure level of each production unit in the entire refinery during the target production cycle; then, based on the accurate predicted steam pipeline network loss, the accurate total steam demand can be obtained; since this invention generates the accurate total steam demand under the premise of considering weather data, better optimization results can be obtained when optimizing production scheduling, thereby effectively improving the energy saving and consumption reduction effect of the refinery.

[0070] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description

[0071] Figure 1 This is a flowchart illustrating the steps of the steam power system production scheduling optimization method described in this invention;

[0072] Figure 2 This is a schematic diagram of the steam power system production scheduling optimization device described in this invention;

[0073] Figure 3 This is a schematic diagram of the steam power system production scheduling optimization equipment described in this invention. Detailed Implementation

[0074] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.

[0075] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprises" shall be understood to include the stated elements or components without excluding other elements or other components.

[0076] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.

[0077] Example 1

[0078] To improve the optimization and energy-saving effects of steam power systems, such as Figure 1 As shown, this embodiment of the invention provides a method for optimizing the scheduling of a steam power system, including the following steps:

[0079] S11. Based on the historical data of each production unit in the entire refinery, fit the mathematical relationship between the steam demand data of each pressure level and the preset operating condition data in the process of each production unit; the preset operating condition data includes production unit load data, raw material property data, product structure data and unit advancement data.

[0080] In this invention, prediction can be made by using an empirical formula fitting method to obtain steam demand data for each stage of the process in each production unit. Specifically, this may include:

[0081] The formulas used to calculate the steam demand data for a specific level of a production unit include:

[0082] F 蒸汽 =F 功耗 +F 热耗 -F 产汽 ;

[0083] Among them, F 蒸汽 This represents the total steam consumption of the production unit at a certain level; a positive number represents steam consumption, and a negative number represents steam production. F 功耗 This refers to the steam consumption of the production unit at a certain level for performing work; F 热耗 This refers to the steam consumption for heating in this production unit at a certain level of steam; F 产汽 This refers to the steam production rate of a specific grade of steam corresponding to this production unit.

[0084] The F 功耗The calculation formula, obtained under the reference working condition, includes:

[0085]

[0086] Among them, F 功耗i F represents the steam consumption of the i-th turbine in this production unit. 基准i η represents the power consumption of the i-th turbine under the baseline operating condition. 负荷 The production load rate of this production unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions; η 效率 η is the turbine's efficiency under current operating conditions divided by its efficiency under reference operating conditions. 第一修正系数 To account for correction coefficients that take into account the properties of raw materials and products, the correction coefficients are obtained using a neural network fitting method; n is the number of turbine units; the baseline operating condition includes the operating condition when the load of the production unit is 100%;

[0087] The F 热耗 The calculation formula, obtained under standard operating conditions, includes:

[0088]

[0089] Among them, F 热耗i Steam consumption for a specific process in a specific process unit; F 基准i η represents the steam consumption of this process under baseline operating conditions. 负荷 The production load rate of this process unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions; η 第二修正系数 To account for correction coefficients for the properties of raw materials and products, a neural network fitting method was used to obtain the value for the steam used in this process; n is the consumption of steam in this process.

[0090] Furthermore, in this embodiment of the invention, the F 热耗 The following formula can also be used to calculate it:

[0091] F 热耗 =F 基准 ×η 负荷 ×η is the second correction factor;

[0092] Among them, F 基准 η represents the total steam consumption of a certain production unit's process. 第二修正系数 To account for the properties of raw materials and products, correction coefficients are obtained using a neural network fitting method for the overall process steam.

[0093] The formulas used in the above process of calculating steam demand data represent the mathematical relationship between the graded steam demand data and the preset operating condition data.

[0094] S12. Generate a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0095] In practical applications, the mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery can be generated according to the following process:

[0096] The mathematical models of the steam pipeline network at all levels of the entire refinery are modeled using a graph theory-based approach, and steam pipeline network loss prediction is carried out. The mathematical models of the steam pipeline network include hydraulic calculation equations and thermodynamic calculation equations.

[0097] The relationship between flow rate and pressure included in the hydraulic calculation equations for the pipeline network is as follows:

[0098] AG p A T p n =q n ;

[0099] Where, q n For pipeline flow rate, p n For node pressure, G p Here are the hydraulic characteristic parameters of the pipeline, and A is the pipeline network correlation matrix. T It is the transpose of matrix A.

[0100] The relationship between flow rate and temperature drop included in the thermodynamic calculation equations for the pipeline network is as follows:

[0101] AG t A T T n =q n ;

[0102] Among them, T n For node temperature, G t These are the thermodynamic properties of the pipeline.

[0103] Among them, the thickness R of the pipeline insulation layer Q This represents the heat dissipation thermal resistance of the steam pipeline, and its expression is:

[0104]

[0105] Where η is the insulation reduction efficiency, obtained by fitting historical data of the steam pipeline; α w α is the convective heat transfer coefficient between the outer wall of the pipe and the environment, calculated based on external environmental and weather data (including temperature and humidity data); d0 is the inner diameter of the pipe; α g λ is the convective heat transfer coefficient between steam and the inner wall of the pipe; Tid is the thermal conductivity of the i-th layer of insulation material; di is the inner diameter of the i-th layer of insulation material; d n+1 It is the outer diameter of the outermost insulation layer.

[0106] Based on historical weather data and actual historical steam pipeline network losses, the corresponding relationship between the loss calculation deviation of the steam pipeline network mathematical model and the weather data is generated according to the steam pipeline network mathematical model.

[0107] The steam pipeline loss obtained through the mathematical model of the steam pipeline network does not consider the deviations caused by environmental and weather factors (such as temperature data, humidity data, wind speed, whether it is raining, and whether it is snowing). In this embodiment of the invention, the theoretical steam pipeline loss and the actual steam pipeline loss calculated by historical data are used to obtain the loss calculation deviation under various weather data (in the general embodiment, weather data includes temperature data, humidity data, wind speed, whether it is raining, and whether it is snowing, etc.). This allows for the determination of the correspondence between various weather data and the loss calculation deviation, which can then be used to correct the calculated steam pipeline loss to eliminate the calculation deviation. In practical applications, historical data including weather data can be used as modeling data for training to generate a predictive model for predicting the calculation deviation based on the calculated steam pipeline loss and weather data. This predictive model serves as the correspondence between weather data and the loss calculation deviation.

[0108] S13. Obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0109] In this embodiment of the invention, the target production cycle refers to the production cycle that needs to be scheduled. For the production cycle to be scheduled (i.e., the target production cycle), the planned start-up and shutdown status, production load, raw material properties, product structure and other relevant operating condition data of each production unit are obtained through logistics planning. Then, based on the mathematical relationship between the above-mentioned grade steam demand data and the preset operating condition data, the predicted steam demand data of each grade required by the process of each production unit can be obtained.

[0110] S14. Obtain weather data for the target production cycle, and determine the prediction loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0111] In this embodiment of the invention, for a target production cycle, weather data (i.e., predicted weather data) is obtained during the target production cycle. After calculating the steam pipeline network loss using the steam pipeline network mathematical model, the predicted loss calculation deviation of the steam pipeline network mathematical model during the target production cycle needs to be determined based on the correspondence between the weather data and the loss calculation deviation.

[0112] S15. Based on the predicted loss calculation deviation and the steam pipeline mathematical model, generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the entire refinery during the target production cycle.

[0113] By calculating the deviation through loss prediction, the predicted steam network loss obtained from the mathematical model of the steam network can be corrected, thus obtaining a more accurate steam network loss.

[0114] S16. Calculate the total steam demand for each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and optimize the power station scheduling based on the total steam demand.

[0115] Specifically, in this embodiment of the invention, the process of optimizing the power station scheduling may include optimizing the scheduling of boilers and steam turbines:

[0116] Optimizing boiler and turbine scheduling requires fitting the existing boiler and turbine efficiencies. The Willan model is used for turbine fitting; for multi-stage turbines, its expression is:

[0117]

[0118] Where, N i Let W be the Willan coefficient for the i-th stage of the steam turbine, mi be the flow rate of the i-th stage of the steam turbine, and W be the flow rate of the i-th stage of the steam turbine. INT N is the intercept coefficient; i and W INT Obtained by fitting historical operating parameters of the steam turbine;

[0119] For boilers, the expression is:

[0120] η=a*(m / m max ) 2 +b*(m / m max )+c;

[0121] Where m is the actual steam production; m max The maximum steam production is represented by a; a, b, and c are dimensionless parameters obtained by fitting the historical operating parameters of the boiler.

[0122] In addition, this step may specifically include:

[0123] Based on the historical operating parameters of the boilers and turbines in the power station, the efficiency of each stage of steam extraction of each boiler and each turbine under each production load is obtained by fitting.

[0124] Under the premise of meeting the total demand for external steam supply at all levels, and under the current price system, the optimized start-up and shutdown status and load of each boiler and turbine are calculated based on the preset optimization model.

[0125] The optimization model constructed in this embodiment of the invention aims to maximize economic benefits. It can optimize the production schedule of boiler production load, turbine load and extraction steam at each stage, while meeting the requirements of boiler maximum / minimum production load, turbine maximum / minimum load and maximum / minimum extraction steam volume at each stage.

[0126] The optimization model may specifically include:

[0127]

[0128] Where, q 电 The local electricity price; q 燃料 For fuel prices; Q 低 It is the lower heating value of fuel.

[0129] In summary, the inventive concept in the embodiments of the present invention includes:

[0130] In existing technologies, logistics scheduling is mostly based on mature commercial software, such as PIMS. In scheduling, process requirements are mostly the basic principle. However, power system optimization is mostly done by self-written programs, which makes it more difficult in actual operation.

[0131] On the other hand, the inventors discovered through research that one important reason why the production scheduling in the existing technology cannot achieve good optimization results is that it does not take into account the impact of the steam pipeline network, including steam pipeline network losses and the impact of weather factors (such as temperature and humidity). These factors will have a significant impact on the power system, thereby affecting the final optimization accuracy and optimization effect.

[0132] Based on the above research, in this embodiment of the invention, the mathematical relationship between the steam demand data at each pressure level and the preset operating condition data in the process of each production unit is first fitted; then, a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery is generated, and the correspondence between the loss calculation deviation and the weather data is generated; in this embodiment of the invention, by the correspondence between the loss calculation deviation and the weather data, the predicted loss calculation deviation of the target production cycle can be determined, and then the calculated steam pipeline network loss of the target production cycle can be corrected to obtain an accurate predicted steam pipeline network loss for each pressure level of each production unit in the entire refinery during the target production cycle; then, based on the accurate predicted steam pipeline network loss, the accurate total steam demand can be obtained; since this embodiment of the invention generates an accurate total steam demand under the premise of considering weather data, better optimization results can be obtained when optimizing production scheduling, thereby effectively improving the energy saving and consumption reduction effect of the refinery.

[0133] Example 2

[0134] In another aspect of this invention, a steam power system production scheduling optimization device is also provided. Figure 2 This diagram illustrates the structure of a steam power system production scheduling optimization device provided in an embodiment of the present invention. The steam power system production scheduling optimization device is... Figure 1 The device corresponding to the steam power system production scheduling optimization method described in the corresponding embodiment is implemented through a virtual device. Figure 1 In the corresponding embodiment of the steam power system scheduling optimization method, each virtual module constituting the steam power system scheduling optimization device can be executed by electronic devices, such as network devices, terminal devices, or servers. Specifically, the steam power system scheduling optimization device in this embodiment of the invention includes:

[0135] The mathematical relationship generation unit 01 is used to fit the mathematical relationship between the steam demand data at each pressure level and the preset operating condition data in the process of each production unit in the whole refinery, based on the historical data of each production unit in the whole refinery. The preset operating condition data includes production unit load data, raw material property data, product structure data and equipment advancement data.

[0136] Mathematical model generation unit 02 is used to generate mathematical models of steam pipeline networks corresponding to each pressure level of the entire refinery, and to generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0137] Steam demand calculation unit 03 is used to obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and to calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0138] Loss deviation calculation unit 04 is used to acquire weather data for the target production cycle and determine the predicted loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0139] The predicted loss calculation unit 05 is used to generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the whole refinery during the target production cycle based on the predicted loss calculation deviation and the steam pipeline mathematical model.

[0140] The production scheduling optimization unit 06 is used to calculate the total steam demand corresponding to each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and to carry out power station production scheduling optimization based on the total steam demand.

[0141] It should be noted that the specific implementation and technical effects of the steam power system production scheduling optimization method in the embodiments of the present invention can be found by referring to... Figure 1 The corresponding steam power system scheduling optimization methods will not be elaborated here.

[0142] Example 3

[0143] Corresponding to the above method embodiments, this application also provides a steam power system scheduling optimization device, such as a terminal and a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these.

[0144] An example diagram of the hardware structure block diagram of the steam power system production scheduling optimization equipment provided in this embodiment of the invention is shown below. Figure 3 As shown, it may include:

[0145] Processor 1, communication interface 2, memory 3, and communication bus 4;

[0146] The processor 1, communication interface 2, and memory 3 communicate with each other via communication bus 4.

[0147] Optionally, communication interface 2 can be an interface of a communication module, such as the interface of a GSM module;

[0148] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0149] Memory 3 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0150] Specifically, processor 1 is used to execute the computer program stored in memory 3 to perform the following steps:

[0151] S11. Based on the historical data of each production unit in the entire refinery, fit the mathematical relationship between the steam demand data of each pressure level and the preset operating condition data in the process of each production unit; the preset operating condition data includes production unit load data, raw material property data, product structure data and unit advancement data.

[0152] S12. Generate a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0153] S13. Obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0154] S14. Obtain weather data for the target production cycle, and determine the prediction loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0155] S15. Based on the predicted loss calculation deviation and the steam pipeline mathematical model, generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the entire refinery during the target production cycle.

[0156] S16. Calculate the total steam demand for each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and optimize the power station scheduling based on the total steam demand.

[0157] The steam power system scheduling optimization equipment in this embodiment of the invention, when the program instructions included in its computer program product are executed by a computer, can enable the computer to execute the steam power system scheduling optimization method described in the above aspects and achieve the same technical effect.

[0158] Example 4

[0159] In this embodiment of the invention, a storage medium is also provided, which can store a program suitable for execution by a processor, the program being used for:

[0160] S11. Based on the historical data of each production unit in the entire refinery, fit the mathematical relationship between the steam demand data of each pressure level and the preset operating condition data in the process of each production unit; the preset operating condition data includes production unit load data, raw material property data, product structure data and unit advancement data.

[0161] S12. Generate a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data and historical actual steam pipeline network losses.

[0162] S13. Obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship.

[0163] S14. Obtain weather data for the target production cycle, and determine the prediction loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship.

[0164] S15. Based on the predicted loss calculation deviation and the steam pipeline mathematical model, generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the entire refinery during the target production cycle.

[0165] S16. Calculate the total steam demand for each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and optimize the power station scheduling based on the total steam demand.

[0166] Optionally, the refined and extended functions of the program can be found in the description above.

[0167] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0168] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0170] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0172] It should be understood that in the embodiments of this application, the claims, various embodiments, and features can be combined with each other to solve the aforementioned technical problems.

[0173] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0174] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing production scheduling in a steam power system, characterized in that, Including the following steps: S11. Based on the historical data of each production unit in the whole refinery, fit the mathematical relationship between the steam demand data of each pressure level and the preset operating condition data in the process of each production unit. The preset operating condition data includes production unit load data, raw material property data, and product structure data; S12. Generate a mathematical model of the steam pipeline network corresponding to each pressure level of the entire refinery, and generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data, historical actual steam pipeline network losses and the steam pipeline network mathematical model. S13. Obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship. S14. Obtain weather data for the target production cycle, and determine the prediction loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship. S15. Based on the predicted loss calculation deviation and the steam pipeline mathematical model, generate the predicted steam pipeline loss corresponding to each pressure level of each production unit in the entire refinery during the target production cycle. S16. Calculate the total steam demand for each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and optimize the power station scheduling based on the total steam demand. The optimization of power station production scheduling based on the total steam demand includes: Based on the historical operating parameters of the boilers and turbines in the power station, the efficiency of each stage of steam extraction of each boiler and each turbine under each production load is obtained by fitting. Under the premise of meeting the total demand for external steam supply at all levels, and under the current price system, the optimized start-up and shutdown status and load of each boiler and each steam turbine are calculated according to the preset optimization model. The calculation process for optimizing power station production scheduling based on the total steam demand includes: Optimize the production scheduling of boilers and steam turbines, including: Fitting the efficiency of boilers and steam turbines includes: The fitting method for the steam turbine adopts the Willan model. For a multi-stage steam turbine, its expression is: ； Where, N i Let W be the Willan coefficient for the i-th stage of the steam turbine, mi be the flow rate of the i-th stage of the steam turbine, and W be the flow rate of the i-th stage of the steam turbine. INT N is the intercept coefficient; i and W INT Obtained by fitting historical operating parameters of the steam turbine; The expression for a boiler is: ； Where m is the actual steam production; m max The maximum steam production is represented by a; a, b, and c are dimensionless parameters obtained by fitting the historical operating parameters of the boiler. The optimization model includes: ； Where, q 电 The local electricity price; q 燃料 For fuel prices; Q 低 It is the lower heating value of fuel.

2. The steam power system production scheduling optimization method according to claim 1, characterized in that, Based on the mathematical relationships, the predicted steam demand data for each level required by the process of each of the aforementioned production units are calculated, including: The steam demand data for each stage of the process in each production unit is obtained by using an empirical formula fitting method for prediction, including: The formulas used to calculate the steam demand data for a specific level of a production unit include: ； in, F 蒸汽 This represents the total steam consumption of the production unit at a certain level; a positive number represents steam consumption, and a negative number represents steam production. F 功耗 This refers to the amount of steam consumed by the production unit at a certain level of steam to perform work. F 热耗 This refers to the steam consumption of the production unit for heating at a certain level of steam. F 产汽 This refers to the steam production rate of a specific grade of steam corresponding to this production unit. The F 功耗 The calculation formula, obtained under the reference working condition, includes: ； in, F 功耗i This represents the steam consumption of the i-th turbine in the production unit. F 基准i This represents the consumption of the i-th steam turbine under the baseline operating conditions. η 负荷 The production load rate of this production unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions. η 效率 The efficiency of the steam turbine under the current operating conditions is divided by the efficiency under the reference operating conditions; η 第一修正系数 To account for correction coefficients for raw material and product properties, these correction coefficients are obtained using a neural network fitting method; n represents the number of turbine units; the baseline operating condition includes the condition where the production unit is at 100% load. The F 热耗 The calculation formula, obtained under standard operating conditions, includes: ； in, F 热耗i Steam consumption in a specific process of a specific process unit; F 基准i This represents the steam consumption of the process under baseline operating conditions. η 负荷 The production load rate of this process unit is equal to the load under the current operating conditions divided by the load under the reference operating conditions. η 第二修正系数 To account for correction coefficients for the properties of raw materials and products, a neural network fitting method was used to obtain the value for the steam used in this process; n is the consumption of steam in this process.

3. The steam power system production scheduling optimization method according to claim 2, characterized in that, The F 热耗 The following formula can also be used to calculate it: ； in, F 基准 The total steam consumption of a certain production unit in the process; η 第二修正系数 To account for the properties of raw materials and products, correction coefficients are obtained using a neural network fitting method for the overall process steam.

4. The steam power system production scheduling optimization method according to claim 1, characterized in that, The mathematical model for generating the steam pipeline network corresponding to each pressure level of the entire refinery includes: The mathematical models of the steam pipeline network at all levels of the entire refinery are modeled using a graph theory-based approach, and steam pipeline network loss prediction is carried out. The mathematical models of the steam pipeline network include hydraulic calculation equations and thermodynamic calculation equations. The relationship between flow rate and pressure included in the hydraulic calculation equations for the pipeline network is as follows: ； Where, q n For pipeline flow rate, p n For node pressure, G p These are the hydraulic characteristic parameters of the pipeline. This is the pipeline network correlation matrix; The relationship between flow rate and temperature drop included in the thermodynamic calculation equations for the pipeline network is as follows: ； Among them, T n For node temperature, G t These are the thermodynamic properties of the pipeline. Among them, the thickness of the pipeline insulation layer This represents the heat dissipation thermal resistance of the steam pipeline, and its expression is: ； Where η is the insulation reduction efficiency, obtained by fitting historical data of the steam pipeline; α w The convective heat transfer coefficient between the outer wall of the pipe and the environment is calculated based on the external environment and weather. This refers to the inner diameter of the pipeline. The convective heat transfer coefficient between steam and the inner wall of the pipe; Let be the thermal conductivity of the i-th layer of insulation material; Let be the inner diameter of the i-th layer of insulation material; It is the outer diameter of the outermost insulation layer.

5. A production scheduling optimization device for a steam power system, characterized in that, include: The mathematical relationship generation unit is used to fit the mathematical relationship between the steam demand data at each pressure level and the preset operating condition data in the process of each production unit in the whole refinery, based on the historical data of each production unit in the whole refinery. The preset operating condition data includes production unit load data, raw material property data, and product structure data; The mathematical model generation unit is used to generate mathematical models of the steam pipeline network corresponding to each pressure level of the entire refinery, and to generate the correspondence between the loss calculation deviation of the steam pipeline network mathematical model and the weather data based on historical weather data, historical actual steam pipeline network losses and the steam pipeline network mathematical model. The steam demand calculation unit is used to obtain the operating condition data of each production unit in the target production cycle through logistics scheduling; and to calculate the predicted steam demand data of each level required by the process of each production unit according to the mathematical relationship. The loss deviation calculation unit is used to acquire weather data for the target production cycle and determine the predicted loss calculation deviation of the steam pipeline mathematical model in the target production cycle based on the weather data and the corresponding relationship. The predicted loss calculation unit is used to generate the predicted steam pipeline losses corresponding to each pressure level of each production unit in the entire refinery during the target production cycle, based on the predicted loss calculation deviation and the steam pipeline mathematical model. The production scheduling optimization unit is used to calculate the total steam demand corresponding to each pressure level of each production unit in the target production cycle based on the predicted steam demand data and the predicted steam pipeline loss, and to carry out power station production scheduling optimization based on the total steam demand. The optimization of power station production scheduling based on the total steam demand includes: Based on the historical operating parameters of the boilers and turbines in the power station, the efficiency of each stage of steam extraction of each boiler and each turbine under each production load is obtained by fitting. Under the premise of meeting the total demand for external steam supply at all levels, and under the current price system, the optimized start-up and shutdown status and load of each boiler and each steam turbine are calculated according to the preset optimization model. The calculation process for optimizing power station production scheduling based on the total steam demand includes: Optimize the production scheduling of boilers and steam turbines, including: Fitting the efficiency of boilers and steam turbines includes: The fitting method for the steam turbine adopts the Willan model. For a multi-stage steam turbine, its expression is: ； Where, N i Let W be the Willan coefficient for the i-th stage of the steam turbine, mi be the flow rate of the i-th stage of the steam turbine, and W be the flow rate of the i-th stage of the steam turbine. INT N is the intercept coefficient; i and W INT Obtained by fitting historical operating parameters of the steam turbine; The expression for a boiler is: ； Where m is the actual steam production; m max The maximum steam production is represented by a; a, b, and c are dimensionless parameters obtained by fitting the historical operating parameters of the boiler. The optimization model includes: ； Where, q 电 The local electricity price; q 燃料 For fuel prices; Q 低 It is the lower heating value of fuel.

6. A production scheduling optimization device for a steam power system, characterized in that, include: Memory, used to store computer programs; A processor is used to call and execute the computer program to implement the various steps of the steam power system production scheduling optimization method as described in any one of claims 1-4.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the steam power system production scheduling optimization method as described in any one of claims 1-4.

Images