Unit piecewise linearization optimization method and system based on improved Friedel-Gel formula

Abstract

The invention belongs to the technical field of unit optimization, and discloses a unit piecewise linearization optimization method and system based on an improved Friedel-Gel formula, and the method comprises the steps: obtaining the historical operation data of a unit, segmenting the working region of the unit according to the physical characteristics of the unit, and obtaining a plurality of subintervals; calculating a fuel consumption function of each sub-interval by utilizing an improved Friedel-Gel formula, and constructing a unit fuel planning decision optimization model by taking the minimum total fuel consumption as an objective function; solving the unit fuel planning decision optimization model by using an intelligent algorithm to obtain the optimal fuel consumption of each subinterval; and according to the optimal fuel consumption amount of each subinterval, a fuel consumption strategy of the unit is updated and implemented. According to the method, a complex optimization problem can be processed, a globally optimal solution or an approximately optimal solution is found, and the accuracy and robustness of solution are further improved by fusing results of different algorithms.

Description

Technical Field

[0001] The invention relates to the technical field of unit optimization, and in particular to a unit piecewise linear optimization method and system based on an improved Flugel formula. Background Art

[0002] With the acceleration of industrial modernization, the proportion of large thermal power units in the power grid has gradually increased. Due to changes in the electricity consumption structure, the difference between the peak and the trough of the daily load curve of the power grid is getting bigger and bigger. In some areas, the difference between the peak and the trough of electricity consumption has exceeded 50%, and this gap continues to expand. The challenges brought by this load fluctuation require the thermal power units in the power grid to have stronger regulation capabilities, especially in peak load regulation and frequency regulation. To this end, the combustion control system of the thermal power unit has become an important part of achieving stable operation of the power grid, and is responsible for timely adjusting fuel consumption when the load fluctuates and the power grid frequency changes.

[0003] The optimization of the fuel consumption of the unit is a typical complex nonlinear optimization problem. In actual operation, the load change of the unit will cause significant fluctuations in the operating state, and the fuel consumption function will also change accordingly. Therefore, the optimization model must be able to flexibly adapt to these dynamic changes. However, traditional fuel consumption optimization methods often have certain limitations, especially in how to deal with different load ranges of the unit. Most existing methods do not make a fine division of the operating area of ​​the unit, but adopt a simplified global optimization strategy, which makes the optimization results lack accuracy and applicability.

[0004] Therefore, how to provide a unit piecewise linearization optimization method and system based on the improved Flugel formula is a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiment of the present invention provides a unit piecewise linearization optimization method and system based on an improved Flugel formula to solve the problems in the prior art.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor is it intended to identify key / important components or to describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a unit piecewise linearization optimization method based on an improved Flugel formula is provided.

[0008] In one embodiment, the unit piecewise linearization optimization method based on the improved Flugel formula includes:

[0009] Obtain the historical operation data of the unit, and divide the working area of ​​the unit into several sub-intervals according to the physical characteristics of the unit;

[0010] The improved Flugel formula is used to calculate the fuel consumption function of each sub-interval, and the minimum total fuel consumption is taken as the objective function to build the unit fuel planning decision optimization model.

[0011] The intelligent algorithm is used to solve the unit fuel planning decision optimization model to obtain the optimal fuel consumption in each sub-interval;

[0012] According to the optimal fuel consumption of each sub-interval, the fuel consumption strategy of the unit is updated and implemented.

[0013] In one embodiment, the historical operation data of the unit is obtained, and the working area of ​​the unit is segmented according to the physical characteristics of the unit to obtain several sub-intervals including:

[0014] Based on the preset monitoring equipment, the historical operation data of the unit is collected and preprocessed, and the preprocessed historical operation data is screened and processed to obtain the operation data of the unit in a stable state;

[0015] Determine the load parameters of the unit based on the operating data of the unit in a stable state and in combination with the physical characteristics of the unit;

[0016] According to the load parameters of the unit, the working area of ​​the unit is divided into several sub-intervals.

[0017] In one embodiment, the filtering and processing of the pre-processed historical operation data to obtain the operation data of the unit in a stable state includes:

[0018] Divide the preprocessed historical operation data into multiple data segments, and construct a vector for each data;

[0019] According to the vector of each data segment, the mutual approximation entropy value between each data segment and the reference data segment is calculated;

[0020] According to the size of the mutual approximate entropy value, the preset mutual approximate entropy threshold is used to filter the stable data segment to obtain the operating data of the unit in a stable state.

[0021] In one embodiment, calculating the mutual approximation entropy value between each data segment and the reference data segment according to the vector of each data segment includes:

[0022] Collect reference data segments when the unit is in a stable state, and construct a subsequence of a preset length for each data segment and the reference data segment;

[0023] Calculate the distance between each subsequence of each data segment and each subsequence of the reference data segment, and count the number of subsequences whose distance between the subsequences of each data segment and the subsequences of the reference data segment is less than a preset distance threshold to obtain a statistical result;

[0024] Calculate the mutual approximate entropy value of each data segment and the reference data segment according to the statistical result.

[0025] In one embodiment, the calculation formula for calculating the mutual approximate entropy value of each data segment and the reference data segment according to the statistical result is:

[0026] ;

[0027] In the formula, C represents the mutual approximate entropy value of the data segment and the reference data segment, N represents the total length of the data segment, m represents the subsequence length, r represents the distance threshold, p represents the position index of the subsequence, x p represents the subsequence starting from position p in the data segment, x q represents the subsequence starting from position q in the data segment, d(x p , x q ) represents the distance between two subsequences, and numberof d(x p , x q ) < r represents the number of subsequences whose distance between the subsequences in the data segment and the subsequences in the reference data segment is less than the distance threshold r.

[0028] In one embodiment, the load parameters of the unit include the minimum load, the maximum load, and the rated load.

[0029] In one embodiment, the method of using the improved Flügel formula to calculate the fuel consumption function of each sub-interval and constructing an optimization model for the unit fuel planning decision with the lowest total fuel consumption includes:

[0030] For each sub-interval, use the improved Flügel formula to calculate the energy change value, and combine the density of the fluid in the unit and the acceleration due to gravity to calculate the power of each sub-interval;

[0031] According to the power of each sub-interval, obtain the efficiency corresponding to each sub-interval through characteristic curve fitting; calculate the fuel consumption of each sub-interval based on the power and efficiency of each sub-interval;

[0032] Add the fuel consumption functions of each sub-interval to construct an objective function with the lowest total fuel consumption, and obtain an optimization model for the unit fuel planning decision by adding unit constraint conditions.

[0033] In one embodiment, the calculation formula for using the improved Flügel formula to calculate the energy change value for each sub-interval is:

[0034] ΔE=m*(h in −h out );

[0035] In the formula, ΔE represents the energy change per unit time, m represents the mass flow rate of the fluid, and h in Indicates the enthalpy of the fluid when it enters the unit, h out It represents the enthalpy of the fluid when it leaves the unit.

[0036] In one embodiment, the intelligent algorithm is used to solve the unit fuel planning decision optimization model to obtain the optimal fuel consumption of each sub-interval, including:

[0037] The unit fuel planning decision optimization model is solved by using the Monte Carlo algorithm and the particle swarm algorithm respectively, and a first solution result and a second solution result are obtained;

[0038] The first solution result and the second solution result are averaged to obtain a fusion result;

[0039] The fusion result is taken as the optimal fuel consumption of each subinterval.

[0040] According to a second aspect of the embodiments of the present invention, a unit piecewise linearization optimization system based on an improved Flugel formula is provided.

[0041] In one embodiment, the unit piecewise linearization optimization system based on the improved Flugel formula includes:

[0042] The regional segmentation module is used to obtain the historical operation data of the unit and segment the working area of ​​the unit according to the physical characteristics of the unit to obtain several sub-intervals;

[0043] A model building module is used to calculate the fuel consumption function of each sub-interval by using the improved Flugel formula, and to build a unit fuel planning decision optimization model with the minimum total fuel consumption as the objective function;

[0044] The consumption calculation module is used to solve the unit fuel planning decision optimization model using intelligent algorithms to obtain the optimal fuel consumption of each sub-interval;

[0045] The strategy updating module is used to update the fuel consumption strategy of the unit and implement it according to the optimal fuel consumption of each sub-interval.

[0046] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0047] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0048] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0049] In one embodiment, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0050] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0051] The present invention divides the working area of ​​the unit into segments and applies the improved Flügel formula to each sub-interval to calculate the fuel consumption function, which can more accurately reflect the operating characteristics of the unit under different loads. The historical operating data of the unit is used for segmentation and screening, which ensures that the optimization process is based on actual operating conditions and enhances the practicability and accuracy of the model. Stable data segments are screened by methods such as mutual approximate entropy values, which further improves the quality and reliability of the data and provides a solid foundation for optimization. The optimization model is solved by an intelligent algorithm, which can handle complex optimization problems and find the global optimal solution or the approximate optimal solution. The accuracy and robustness of the solution are further improved by fusing the results of different algorithms.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0054] Figure 1 is a flow chart of a unit piecewise linearization optimization method based on an improved Flugel formula according to an exemplary embodiment;

[0055] Figure 2 is a principle block diagram of a unit piecewise linearization optimization system based on an improved Flugel formula according to an exemplary embodiment;

[0056] Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0058] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0059] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0060] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0061] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0062] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0063] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0064] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0065] Figure 1 An embodiment of the unit piecewise linearization optimization method based on the improved Frugel formula of the present invention is shown.

[0066] In this optional embodiment, the unit piecewise linearization optimization method based on the improved Flugel formula includes:

[0067] Step S101, obtaining historical operation data of the unit, and segmenting the working area of ​​the unit according to the physical characteristics of the unit to obtain a number of sub-intervals;

[0068] In this optional embodiment, the historical operation data of the unit is obtained, and the working area of ​​the unit is segmented according to the physical characteristics of the unit to obtain several sub-intervals including:

[0069] Based on the preset monitoring equipment, the historical operation data of the unit is collected and preprocessed, and the preprocessed historical operation data is screened and processed to obtain the operation data of the unit in a stable state;

[0070] It should be noted that data preprocessing is to remove noise, fill missing values, process abnormal data, etc., so that the data is more in line with the needs of subsequent analysis. The preprocessed data is more standardized and consistent, providing a basis for subsequent screening of data in a stable state.

[0071] In this optional embodiment, the filtering and processing of the pre-processed historical operation data to obtain the operation data of the unit in a stable state includes:

[0072] Divide the preprocessed historical operation data into multiple data segments, and construct a vector for each data;

[0073] Specifically, when dividing into multiple data segments, the data is divided into multiple segments according to a time window, for example, one data segment per hour, day, or week. This method is suitable for regular data collection.

[0074] For each data segment, the key features of the segment need to be extracted and represented as a vector (vector). Usually, the dimensions of the vector correspond to multiple parameters of the data segment. Common parameters include:

[0075] Load: The output power or load of the unit during this time period.

[0076] Fuel Consumption: The fuel consumption of the unit during this period of time.

[0077] Temperature: The coolant temperature or steam temperature when the unit is operating.

[0078] Pressure: The pressure of key equipment (such as boilers and turbines) when the unit is running.

[0079] Efficiency: The working efficiency of the unit within this data range.

[0080] The values ​​of these parameters will serve as eigenvalues ​​and constitute the vector of the data segment.

[0081] For example, for each data segment, if the following parameters are collected: load (L), fuel consumption (F), temperature (T), pressure (P), efficiency (η).

[0082] Then the vector of the data segment can be expressed as: v=[L,F,T,P,η], where v represents the vector of the data segment.

[0083] According to the vector of each data segment, the mutual approximation entropy value between each data segment and the reference data segment is calculated;

[0084] According to the size of the mutual approximate entropy value, the preset mutual approximate entropy threshold is used to filter the stable data segment to obtain the operating data of the unit in a stable state.

[0085] In this optional embodiment, calculating the mutual approximation entropy value between each data segment and the reference data segment according to the vector of each data segment includes:

[0086] Collect reference data segments when the unit is in a stable state, and construct a subsequence of a preset length for each data segment and the reference data segment;

[0087] Calculate the distance between each subsequence of each data segment and each subsequence of the reference data segment, and count the number of subsequences in each data segment whose distance from the subsequences of the reference data segment is less than a preset distance threshold to obtain a statistical result;

[0088] Calculate the mutual approximate entropy value of each data segment and the reference data segment according to the statistical result.

[0089] Determine the load parameter of the unit according to the operating data of the unit in a stable state and in combination with the physical characteristics of the unit;

[0090] Divide the working area of the unit into several sub-intervals according to the load parameter of the unit.

[0091] It should be noted that according to the load parameters of the unit (minimum load, maximum load and rated load), the working area of the unit is divided into several sub-intervals. Each sub-interval represents the operating state of the unit within a specific load range. For example, the unit can be divided into:

[0092] Low load interval: the range close to the minimum load.

[0093] Medium load interval: the range near the rated load.

[0094] High load interval: the range close to the maximum load.

[0095] Through this division, the performance and fuel consumption law of the unit under different loads can be analyzed more carefully, and thus support can be provided for subsequent fuel consumption optimization and decision-making.

[0096] In this alternative embodiment, the calculation formula for calculating the mutual approximate entropy value of each data segment and the reference data segment according to the statistical result is:

[0097] ;

[0098] In the formula, C represents the mutual approximate entropy value of the data segment and the reference data segment, N represents the total length of the data segment, m represents the subsequence length, r represents the distance threshold, p represents the position index of the subsequence, x p represents the subsequence starting from position p in the data segment, x q represents the subsequence starting from position q in the data segment, d(x p , x q ) represents the distance between two subsequences, numberof d(x p , x q ) < r represents the number of subsequences in the data segment whose distance from the subsequences in the reference data segment is less than the distance threshold r.

[0099] Step S102, using the improved Flugel formula, calculate the fuel consumption function of each sub-interval, and take the minimum total fuel consumption as the objective function to build a unit fuel planning decision optimization model;

[0100] In this optional embodiment, the improved Flugel formula is used to calculate the fuel consumption function of each sub-interval, and the minimum total fuel consumption is used as the objective function to construct the unit fuel planning decision optimization model, which includes:

[0101] For each sub-interval, the energy change value is calculated using the improved Flugel formula, and the power of each sub-interval is calculated by combining the density and gravity acceleration of the fluid in the unit;

[0102] In this optional embodiment, for each sub-interval, the energy change value is calculated using the improved Flugel formula as follows:

[0103] ΔE=m*(h in −h out );

[0104] In the formula, ΔE represents the energy change per unit time, m represents the mass flow rate of the fluid, and h in Indicates the enthalpy of the fluid when it enters the unit, h out It represents the enthalpy of the fluid when it leaves the unit.

[0105] When it is necessary to explain, the energy change value is used to calculate the effective power output of the computer group, considering the density ρ of the fluid and the gravitational acceleration g, P = ΔE / Δt;

[0106] Where P represents the power of the unit in this sub-interval (W or kW), and t represents the time interval (s).

[0107] Since power is the rate of change of energy, the power of the computer group can be calculated by the energy change value per unit time.

[0108] According to the power of each sub-interval, the efficiency corresponding to each sub-interval is obtained by fitting the characteristic curve; the power and efficiency of each sub-interval are used to calculate the fuel consumption of each sub-interval;

[0109] It should be noted that the unit's operating efficiency η is a key parameter in the calculation of fuel consumption, which can be obtained through experimental data or characteristic curve fitting: η = f(P);

[0110] η represents the efficiency of the unit in this sub-interval (unitless, 0~1). P represents the power of the unit (kW). f(P) represents the characteristic curve function of empirical or experimental fitting.

[0111] The characteristic curve is usually fitted by experimental data, such as polynomial fitting or interpolation, and exhibits nonlinear characteristics. For example, a common fitting model can be: η = aP 2 +bP+c;

[0112] Among them, a, b, and c are fitting coefficients.

[0113] The fuel consumption functions of each subinterval are added together to construct the objective function with the lowest total fuel consumption, and the unit fuel planning decision optimization model is obtained by adding unit constraints.

[0114] It should be noted that in order to ensure that the optimization results meet the actual unit operation requirements, constraints need to be added: the unit operating load must be between the minimum load and the maximum load, the unit's fuel consumption cannot exceed the predetermined supply range, and the unit's total power output needs to meet the system load requirements.

[0115] Step S103, using an intelligent algorithm to solve the unit fuel planning decision optimization model to obtain the optimal fuel consumption of each sub-interval;

[0116] In this optional embodiment, the use of an intelligent algorithm to solve the unit fuel planning decision optimization model to obtain the optimal fuel consumption of each sub-interval includes:

[0117] The unit fuel planning decision optimization model is solved by using the Monte Carlo algorithm and the particle swarm algorithm respectively, and a first solution result and a second solution result are obtained;

[0118] The first solution result and the second solution result are averaged to obtain a fusion result;

[0119] The fusion result is taken as the optimal fuel consumption of each subinterval.

[0120] It should be noted that the Monte Carlo algorithm is an optimization method based on random sampling, which is usually used in complex or high-dimensional optimization problems. Its core idea is to estimate the expected value or optimal solution of certain variables or functions through a large number of random samplings, which specifically includes the following steps:

[0121] Generate random samples: Randomly generate multiple solutions in the feasible solution space of the optimization problem. For each subinterval, randomly select a load allocation scheme (power allocation) and calculate its corresponding fuel consumption.

[0122] Calculate the fitness: According to the load distribution scheme of each random solution, calculate its corresponding fuel consumption (using the aforementioned fuel consumption function), and then evaluate the fitness of each solution, that is, the size of its fuel consumption. The smaller the fitness, the better the quality of the solution.

[0123] Iterative sampling: Repeat the above process, continuously generate new random samples and calculate the fitness until the set maximum number of iterations is reached or the convergence condition is met.

[0124] The first solution result is obtained: the fuel consumption of each sub-interval is obtained by solving the Monte Carlo algorithm.

[0125] Particle swarm optimization (PSO) is an optimization method that simulates swarm intelligence, inspired by the foraging behavior of bird flocks. PSO searches the solution space by updating the particle position and velocity to find the optimal solution, which includes the following steps:

[0126] Initialize particle swarm: Initialize a set of particles, each particle represents a potential solution (i.e., the power allocation scheme for each subinterval). The speed and position of the particles are randomly generated.

[0127] Calculate fitness: For each particle, calculate the fuel consumption corresponding to its current position, and update the particle's fitness value based on the fuel consumption. The smaller the fitness, the better the solution.

[0128] Update the position and velocity of the particle: Update the position and velocity of the particle based on the particle's own experience (personal best position) and the group's experience (global best position):

[0129] Iterative update: Continuously update the position and velocity of the particles, and find the optimal solution through multiple iterations until the convergence condition is met or the maximum number of iterations is reached.

[0130] The second solution result is obtained: the fuel consumption of each sub-interval is obtained by solving the particle swarm optimization algorithm.

[0131] Step S104: updating the fuel consumption strategy of the unit and implementing it according to the optimal fuel consumption of each sub-interval.

[0132] Specifically, according to the optimal fuel consumption of each sub-interval, the fuel consumption strategy of the unit is updated and implemented, including:

[0133] For the optimal fuel consumption of each sub-interval, the existing fuel consumption strategy should be reviewed in combination with the actual operating environment, load demand and fuel supply of the unit. If there is a large difference between the optimal fuel consumption and the existing strategy, it may be necessary to optimize the load distribution, fuel scheduling, energy efficiency adjustment and other aspects of the unit.

[0134] Adjust the unit's operating strategy at different load levels according to the optimal fuel consumption in each sub-interval. Generally, the goal of load distribution is to minimize total fuel consumption while ensuring stable operation of the unit. In each sub-interval, adjust the power output to make it fit the optimal fuel consumption strategy as much as possible; optimize the unit's power output and fuel consumption by reasonably distributing the load.

[0135] Figure 2 An embodiment of the unit piecewise linearization optimization system based on the improved Frugel formula of the present invention is shown.

[0136] In this optional embodiment, the unit piecewise linearization optimization system based on the improved Flugel formula includes:

[0137] The area segmentation module 201 is used to obtain the historical operation data of the unit and segment the working area of ​​the unit according to the physical characteristics of the unit to obtain a plurality of sub-intervals;

[0138] The model building module 202 is used to calculate the fuel consumption function of each sub-interval by using the improved Flugel formula, and to build a unit fuel planning decision optimization model with the minimum total fuel consumption as the objective function;

[0139] The consumption calculation module 203 is used to solve the unit fuel planning decision optimization model using an intelligent algorithm to obtain the optimal fuel consumption of each sub-interval;

[0140] The strategy updating module 204 is used to update the fuel consumption strategy of the unit and implement it according to the optimal fuel consumption of each sub-interval.

[0141] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0142] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0144] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0146] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A unit piecewise linearization optimization method based on the improved Frugel formula, characterized in that: include: Obtain the historical operation data of the unit, and divide the working area of ​​the unit into several sub-intervals according to the physical characteristics of the unit; The improved Flugel formula is used to calculate the fuel consumption function of each sub-interval, and the minimum total fuel consumption is taken as the objective function to build the unit fuel planning decision optimization model. The intelligent algorithm is used to solve the unit fuel planning decision optimization model to obtain the optimal fuel consumption in each sub-interval; According to the optimal fuel consumption of each sub-interval, the fuel consumption strategy of the unit is updated and implemented.

2. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 1 is characterized in that: The historical operation data of the unit is obtained, and the working area of ​​the unit is segmented according to the physical characteristics of the unit to obtain several sub-intervals including: Based on the preset monitoring equipment, the historical operation data of the unit is collected and preprocessed, and the preprocessed historical operation data is screened and processed to obtain the operation data of the unit in a stable state; Determine the load parameters of the unit based on the operating data of the unit in a stable state and in combination with the physical characteristics of the unit; According to the load parameters of the unit, the working area of ​​the unit is divided into several sub-intervals.

3. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 2 is characterized in that: The screening of the pre-processed historical operation data to obtain the operation data of the unit in a stable state includes: Divide the preprocessed historical operation data into multiple data segments, and construct a vector for each data; According to the vector of each data segment, the mutual approximation entropy value between each data segment and the reference data segment is calculated; According to the size of the mutual approximate entropy value, the preset mutual approximate entropy threshold is used to filter the stable data segment to obtain the operating data of the unit in a stable state.

4. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 3 is characterized in that: Calculating the mutual approximation entropy value between each data segment and the reference data segment according to the vector of each data segment includes: Collect reference data segments when the unit is in a stable state, and construct a subsequence of a preset length for each data segment and the reference data segment; Calculating the distance between the subsequence of each data segment and each subsequence of the reference data segment, and counting the number of subsequences whose distance between the subsequence of each data segment and the subsequence of the reference data segment is less than a preset distance threshold, to obtain a statistical result; The mutual approximation entropy value between each data segment and the reference data segment is calculated based on the statistical results.

5. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 4 is characterized in that: The calculation formula for calculating the mutual approximation entropy value of each data segment and the reference data segment according to the statistical results is: ； Wherein, C represents the cross approximate entropy value between the data segment and the reference data segment, N represents the total length of the data segment, m represents the subsequence length, r represents the distance threshold, p represents the position index of the subsequence, and x p represents the subsequence starting from position p in the data segment, and x q represents the subsequence starting from position q in the data segment, and d(x p , x q ) represents the distance between two subsequences, and the number of d(x p , x q ) < r represents the number of subsequences in the data segment whose distance from the subsequences in the reference data segment is less than the distance threshold r.

6. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 2 is characterized in that: The load parameters of the unit include minimum load, maximum load and rated load.

7. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 1 is characterized in that: The improved Flugel formula is used to calculate the fuel consumption function of each sub-interval, and the minimum total fuel consumption is used as the objective function to construct the unit fuel planning decision optimization model, which includes: For each sub-interval, the energy change value is calculated using the improved Flugel formula, and the power of each sub-interval is calculated by combining the density and gravity acceleration of the fluid in the unit; According to the power of each sub-interval, the efficiency corresponding to each sub-interval is obtained by fitting the characteristic curve; the power and efficiency of each sub-interval are used to calculate the fuel consumption of each sub-interval; The fuel consumption functions of each subinterval are added together to construct the objective function with the lowest total fuel consumption, and the unit fuel planning decision optimization model is obtained by adding unit constraints.

8. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 7 is characterized in that: For each sub-interval, the calculation formula for calculating the energy change value using the improved Flugel formula is: ΔE=m*(h in −h out ); In the formula, ΔE represents the energy change per unit time, m represents the mass flow rate of the fluid, and h in Indicates the enthalpy of the fluid when it enters the unit, h out It represents the enthalpy of the fluid when it leaves the unit.

9. The unit piecewise linearization optimization method based on the improved Frugel formula according to claim 1, characterized in that: The method of solving the unit fuel planning decision optimization model by using an intelligent algorithm to obtain the optimal fuel consumption of each sub-interval includes: The unit fuel planning decision optimization model is solved by using the Monte Carlo algorithm and the particle swarm algorithm respectively, and a first solution result and a second solution result are obtained; The first solution result and the second solution result are averaged to obtain a fusion result; The fusion result is taken as the optimal fuel consumption of each subinterval.

10. The unit piecewise linear optimization system based on the improved Frugel formula is characterized by: include: The regional segmentation module is used to obtain the historical operation data of the unit and segment the working area of ​​the unit according to the physical characteristics of the unit to obtain several sub-intervals; A model building module is used to calculate the fuel consumption function of each sub-interval by using the improved Flugel formula, and to build a unit fuel planning decision optimization model with the minimum total fuel consumption as the objective function; The consumption calculation module is used to solve the unit fuel planning decision optimization model using intelligent algorithms to obtain the optimal fuel consumption of each sub-interval; The strategy updating module is used to update the fuel consumption strategy of the unit and implement it according to the optimal fuel consumption of each sub-interval.

Images