Thermal power generating unit valve flow characteristic optimization method and system based on particle swarm optimization

Abstract

The invention belongs to the technical field of thermal power generating unit valve flow characteristic optimization. According to the thermal power generating unit valve flow characteristic optimization method and system based on the particle swarm optimization algorithm, the excellent optimization searching capability, the global searching capability and the local jumping-out capability of a PSO-CS-SOA fusion searching method are comprehensively utilized, the particle activity is increased, particles jump out of the local part to conduct larger-range searching, then a global optimal solution is obtained through searching, and therefore the optimization efficiency of the thermal power generating unit valve flow characteristic is improved. Further optimizing the optimization model; the PSO algorithm is improved by adopting a nonlinear dynamic updating inertia weight, so that the convergence speed of an inertia weight value can be stabilized, and the global search capability and the local search capability of particles can be well balanced; an initial population position is processed into a collision avoidance position by introducing a CS algorithm additional variable A, particles are classified, the particles with high fitting degree are updated according to a PSO algorithm position updating formula, the convergence speed of the algorithm is ensured, the particles with low fitting degree are added into a CS algorithm spiral attack behavior to perform local spiral search, and the local spiral search efficiency is improved. The local search capability of the algorithm is enhanced, and the algorithm is effectively prevented from falling into local optimum.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power unit valve flow characteristic optimization, and in particular to a thermal power unit valve flow characteristic optimization method and system based on particle swarm algorithm. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] The flow characteristics of each valve in the thermal power unit are set according to the requirements when it is put into operation. However, due to the continuous operation of the unit, the valve opening is constantly adjusted. In addition, the valve is in a harsh environment, which leads to the continuous deterioration of the valve fatigue state and even damage, resulting in a large difference between the actual flow characteristics of the valve and the ideal flow characteristics. If the unit control system controls the valve opening according to the ideal flow characteristics set previously, it is difficult to achieve the expected effect, and there may even be misadjustment or reverse adjustment, resulting in the deterioration of the unit's primary frequency regulation performance, which in turn affects the economy and safety of the unit's operation.

[0004] At present, the optimization of valve flow characteristics is mostly based on field tests, which has many shortcomings such as long time consumption and poor accuracy. Based on this, the use of intelligent algorithms to optimize valve flow characteristics has become a current research hotspot. Particle Swarm Optimization (PSO) realizes the search for the optimal solution in a complex space through the interactive behaviors of the community composed of individual particles and the environment and the cooperation and competition between individuals. It has the advantages of fast search speed and high optimization efficiency, but in the later stage of calculation, most particles tend to concentrate near an optimal solution, resulting in premature and local optimal situations. Cuckoo Algorithm (CS) is mainly based on the parasitic nature of cuckoo nests and the Levy flight mechanism strategy. It searches for the optimal solution through random walks. It has the advantages of good random search paths and strong global optimization capabilities, but it also has the disadvantages of fixed parameter settings, lack of internal communication mechanisms in the population, and poor local search performance. Seagull Algorithm (SOA) iteratively optimizes by simulating the foraging behavior of seagulls. It has low algorithm complexity and efficient computing power. It is easy to implement and has strong adaptability. However, it is easy to fall into local optimality when solving complex identification problems. Summary of the invention

[0005] In order to solve the shortcomings of the prior art, the present invention provides a method and system for optimizing the valve flow characteristics of a thermal power unit based on a particle swarm algorithm, which combines the cuckoo algorithm (CS) with the seagull algorithm (SOA), improves the particle swarm algorithm (PSO), and fully utilizes the respective advantages of the three algorithms to improve the global optimization ability of the algorithm, thereby being able to obtain the global optimal solution of the valve flow characteristics, thereby improving the optimization ability of the valve flow characteristics of the thermal power unit.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm.

[0008] A method for optimizing valve flow characteristics of thermal power units based on particle swarm algorithm includes the following processes:

[0009] Acquire historical data of valve flow characteristics of multiple signal points of the thermal power unit, establish an optimized data set, and construct a total flow-total valve position fitting curve before optimization and a valve opening-total valve position fitting curve based on the optimized data set;

[0010] According to the particle swarm algorithm, the initial parameters are set and the particle population X is randomly generated. (t＝t) ;

[0011] According to the particle population X (t＝t) , using the optimization algorithm combined with the particle swarm algorithm and the cuckoo algorithm to calculate the curve fitness value and find the optimal position x of the individual particle pbest (t＝t) and the global optimal position x gbest (t＝t) , get the optimal particle population;

[0012] The additional variable A is calculated according to the Seagull algorithm, and the optimal particle population is optimized by using the additional variable A to obtain the particle population after the position is reset. Generate updated total flow-total valve position fitting curve and each valve opening-total valve position fitting curve;

[0013] The particle population after resetting the position Substitute into the valve flow characteristic function, and optimize the data set, calculate the error between the function output value of each particle and the historical data, and then obtain the average error of the particle population. According to the average error of the particle population, the particles are divided into two groups. The particle population of the first group returns the process of calculating the curve adaptation value, and the particle population of the second group uses the nonlinear inertia weight to update the classification position;

[0014] Determine whether the maximum number of iterations has been reached: if not, return to the process of calculating the curve adaptation value; if yes, output the population optimal value, which is the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0015] In a second aspect, the present invention provides a system for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm.

[0016] A valve flow characteristic optimization system for thermal power units based on particle swarm algorithm, comprising:

[0017] The optimization data set generation unit is configured to: obtain valve flow characteristic historical data of multiple signal points of the thermal power unit, establish an optimization data set, and construct a total flow-total valve position fitting curve before optimization and a valve opening-total valve position fitting curve based on the optimization data set;

[0018] The particle population random generation unit is configured to: set initial parameters according to the particle swarm algorithm and randomly generate a particle population X (t＝t) ;

[0019] The optimal particle population generating unit is configured to: (t＝t) , using the optimization algorithm combined with the particle swarm algorithm and the cuckoo algorithm to calculate the curve fitness value and find the optimal position x of the individual particle pbest (t＝t) and the global optimal position x gbest (t＝t) , get the optimal particle population;

[0020] The optimal particle population resetting unit is configured to: calculate the additional variable A according to the Seagull algorithm, and use the additional variable A to optimize the optimal particle population to obtain the particle population after the reset position Generate updated total flow-total valve position fitting curve and each valve opening-total valve position fitting curve;

[0021] The classification position updating unit is configured to: reset the particle population after the position Substitute into the valve flow characteristic function, and optimize the data set, calculate the error between the function output value of each particle and the historical data, and then obtain the average error of the particle population. According to the average error of the particle population, the particles are divided into two groups. The particle population of the first group returns the process of calculating the curve adaptation value, and the particle population of the second group uses the nonlinear inertia weight to update the classification position;

[0022] The population optimal value generating unit is configured to: determine whether the maximum number of iterations has been reached: if not, return to the process of calculating the curve adaptation value; if yes, output the population optimal value, which is the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0023] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium;

[0024] a processor adapted to execute a computer program;

[0025] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for optimizing the flow characteristics of a valve of a thermal power unit based on a particle swarm algorithm as described in the first aspect of the present invention is implemented.

[0026] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm as described in the first aspect of the present invention.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention increases particle vitality by comprehensively utilizing the excellent optimization ability, global search ability and local jump-out ability of the PSO-CS-SOA fusion search method, allowing particles to jump out of the local area to search in a larger range, and then search for the global optimal solution, further optimizing the optimization model.

[0029] 2. The present invention improves the PSO algorithm by adopting nonlinear dynamic updating of inertia weight, which can stabilize the convergence speed of the inertia weight value and enable a good balance between the global search ability and the local search ability of the particles.

[0030] 3. The present invention introduces an additional variable A in the CS algorithm, processes the initial population position to avoid collision positions, and classifies the particles. The particles with high fitting degree are updated according to the position update formula of the PSO algorithm to ensure the convergence speed of the algorithm. The particles with low fitting degree are added to the spiral attack behavior of the CS algorithm for local spiral search, which enhances the local search ability of the algorithm and effectively prevents the algorithm from falling into the local optimum.

[0031] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0033] Figure 1 A flow chart of a valve flow characteristic optimization method based on an improved particle swarm algorithm provided in Example 1 of the present invention;

[0034] Figure 2 A flow chart of an embodiment of valve flow characteristic optimization provided in Embodiment 1 of the present invention;

[0035] Figure 3 The nonlinear inertia weight change curve provided in Example 1 of the present invention;

[0036] Figure 4 The curve showing the change of the optimal value of the population with the number of iterations provided in Example 1 of the present invention;

[0037] Figure 5 The curve of the population optimal value error versus the number of iterations provided in Example 1 of the present invention;

[0038] Figure 6 The valve opening-total valve position command characteristic curve before and after optimization provided in Example 1 of the present invention;

[0039] Figure 7 The total flow-total valve position instruction characteristic curve before and after optimization provided in Example 1 of the present invention;

[0040] Figure 8 A schematic diagram of a valve flow characteristic optimization system based on an improved particle swarm algorithm provided in Example 2 of the present invention;

[0041] Fig. 9 A schematic diagram of a computer device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0044] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0045] Embodiment 1:

[0046] This implementation proposes a valve flow characteristic optimization method based on an improved particle swarm algorithm, such as Figure 1 As shown, the following process is included:

[0047] S1: Collect the historical data of valve flow characteristics of M signal points of the thermal power unit, establish an optimization data set, and construct the total flow-total valve position and each valve opening-total valve position fitting curve before optimization based on the data set;

[0048] S2: Set initial parameters according to the particle swarm algorithm (PSO) and randomly generate particle population X according to the range limit (t ＝t) , the particle position and velocity in the vertical direction of the key point are initialized;

[0049] S3: Use the optimization algorithm (PSO-CS) that combines PSO and Cuckoo Algorithm (CS) to calculate the curve fitness value and find the optimal position x of the individual particle. pbest (t＝t) and the global optimal position x gbest(t＝t) ;

[0050] S4: Calculate the additional variable A according to the Seagull Algorithm (SOA), and use the additional variable A to further optimize the optimal particle population obtained in S3 to obtain the particle population after resetting the position Generate an updated curve;

[0051] S5: The particle population after resetting the position of the tth generation of S3 Substitute it into the valve flow characteristic function, and combine it with the optimized data set established in S1 to calculate the error between the function output value of each particle and the historical data, and then get the average error of the particle population. Based on this, the particles are divided into two groups. The first group goes to S3, and the second group uses the optimization algorithm combining PSO-CS and nonlinear inertia weight in SOA (PSO-CS-SOA) to update the classified position.

[0052] S6: Determine whether the maximum number of iterations has been reached: if not, return to S3; if yes, output the optimal value of the population, that is, the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0053] In this implementation, preferably, the valve flow characteristic data includes: the total valve position instruction of the thermal power unit, the valve opening before optimization, the main steam flow, the main steam pressure, and the regulating stage pressure signal.

[0054] In this implementation, S2 specifically includes:

[0055] S2.1: First set the population size (number of particles) N, the maximum number of iterations T max , population dimension D, position range limit (learning factor) c1, c2, speed limit (inertia weight, acceleration constant) ω max ,ω min , initial population and individual historical optimal fit, step size control factor α, discovery probability p α , search for the upper bound U b And search lower bound L b , where N, T max , D is a positive integer greater than 0;

[0056] S2.2: Randomly generate N D-dimensional arrays within the upper and lower limits of the position range, the arrays are particle populations X t , is the particle population after t iterations, t∈[0,T max ] and is an integer with an initial value of 0, which means that the particle population is randomly generated for the first time without iteration.

[0057] In this implementation, S3 specifically includes:

[0058] S3.1: At the initial time (t=0), the particle position x is randomly initialized i (t＝0) =(x i1 (t＝0) ,x i2 (t＝0) ,...,x iD (t＝0) ), i = 1, 2, ..., N, calculate the objective function value of each particle and determine the optimal position x of the initial particle pbest (t＝t) And the optimal value of the objective function x gbest (t＝t) ;

[0059] S3.2: Further update the particle velocity and position according to the following formula and calculate the objective function value;

[0060] v i (t＝t+1) =ωv i (t＝t) +c1r1[p i (t＝t) -x i (t＝t) ]+c2r2[g (t＝t) -x i (t＝t) ] (1);

[0061] x i (t＝t+1) =x i (t＝t) +v i (t＝t+1) (2);

[0062]

[0063] Where: i∈[1,N], t∈[1,T max ];v i represents the velocity of the particle, x i represents the position of the particle; ω represents the inertia weight factor; c1 and c2 are acceleration constants, also known as learning factors; r1 and r2 are random numbers uniformly distributed between [0, 1]; p i (t ＝t) represents the best position of the ith particle after t iterations, also known as the individual optimum; g (t＝t) represents the best position searched by all particles after t iterations, also known as the global optimum; v max Indicates the boundary value set by the velocity vector;

[0064] S3.3: Compare the calculated optimal value of the objective function of the tth generation with that of the tth generation. If the optimal value of the objective function of the t+1th generation is better than that of the tth generation, then the optimal position of the current particle is recorded as x. pbest (t＝t+1) , otherwise it is still x pbest (t＝t) ;

[0065] The current particle's optimal position x pbest (t＝t / t+1) With the discovery probability p α For comparison, if x pbest (t＝t / t+1) <p α , it means that the particle has not been eliminated. If x pbest (t＝t / t+1) >p α , it means that the particle is eliminated, the particle position is updated, the new objective function value is calculated, and the optimal position of the t+1 / t+2 generation particle is determined by comparison as x pbest (t＝t+1 / t+2) , update the global optimal position to x gbest (t＝t+1 / t+2) ;

[0066] Specifically, the particle position is updated using the position update method in the CS algorithm, and the formula is:

[0067]

[0068] in:

[0069]

[0070] Where: x i (t＝t) is the position of the i-th bird's nest at the t-th iteration; a is the step size proportional factor; L(s,λ) obeys the Levy distribution, indicating the random path of Levy flight; s is the random flight step size; λ is the power coefficient, 1<λ<3; Γ(λ) is the standard Gamma function with unbounded mean and variance; a is 0.01 and λ is 1.5.

[0071] In this implementation, S4 specifically includes:

[0072] S4.1: Calculate the additional variable A according to the following formula:

[0073] A=f c -[t×(f c / T max )] (6);

[0074] Where: f c is the frequency of the additional variable A, which ranges from [0,2], and realizes a linear decrease of A from 2 to 0.

[0075] S4.2: Substitute the obtained additional variable A into formula (7) and combine it with the particle population X generated in S2) (t＝t) Get the particle population after resetting the position The formula is:

[0076]

[0077] Where, X (t＝t) is the t-th generation particle population; is the particle population after the positions are reset in the tth generation.

[0078] In this implementation, S5 specifically includes:

[0079] S5.1: Substitute the particle population after resetting the position into the valve flow characteristic function, identify the total valve position command signal data in the data set as input, and obtain the corresponding output O through transfer function calculation. fzzr , the particle error value after the tth generation reset position is calculated by formula (8):

[0080]

[0081] In the formula, O zr To identify the valve opening signal value in the data set, O fzzr (X i (t＝t*) ) is the calculated value of valve opening after the particle at the ith reset position of the tth generation is substituted into the transfer function, O fzzr (X i (t＝t*) ), i is any integer value between 1 and N;

[0082] S5.2: Through formula (9) Calculate the average and get the average error value of the valve opening after the particles after the tth generation N reset positions are substituted into the transfer function Will The average error In comparison, the error value is lower than The first group is higher than The second group is:

[0083]

[0084] S5.3: Return the particle population of the second group in S5.2 to S3, and update the position of the particle population of the first group in combination with the nonlinear inertia weight in the CS algorithm. The formula is as follows:

[0085]

[0086] V i (t＝(t+1)*) =ωV i (t＝t*) +c1r1(p i (t＝t*) -X i (t＝t*) )+c2r2(g (t＝t*) -X i (t＝t*) )(11);

[0087] Where, X i (t＝t+1) is the i-th particle of the t+1th generation; is the i-th particle after the position is reset in the t-th generation; is the global optimal particle; x, y, z are the parameters related to the spiral attack behavior of the CS algorithm; are the moving speeds of the i-th particle after the position is reset in the t+1th and tth generations respectively; is the individual optimal particle after resetting the position in the tth generation; r1 and r2 are random numbers between 0 and 1; c1 and c2 are constants between 0 and 1, and ω is the nonlinear inertia weight.

[0088] S5.4: Get the individual and global optimal particles of the particle population after resetting the position;

[0089] The nonlinear inertia weight factor calculation formula in S5.3 is:

[0090]

[0091] In the formula, ω (t＝t) represents the nonlinear inertia weight at iteration t, ω max ,ω min Represent the maximum and minimum inertia weights respectively.

[0092] This implementation provides a specific example, such as Figure 2 As shown, including:

[0093] Step 1: Collect historical signals such as total valve position command, total flow, valve opening, main steam pressure, and regulating stage pressure of the thermal power unit. After preprocessing, a total of 50,000 data points are obtained. Cluster the sampled data and take 3,000 data points after clustering as the data set for valve flow characteristic optimization. Based on the data set, construct the total flow-total valve position and valve opening-total valve position characteristic curves before optimization.

[0094] Step 2: Set the population size N to 500 and the maximum number of iterations T max is 500, the population dimension D is 11, ω max=0.8,ω min is 0.2, the position range is limited to [0,100], the speed limit is set to [-1,1], c1 and c2 are both 0.5, and the probability of finding p α = 0.3, set the initial population fitness and individual historical optimal fitness to infinity, randomly generate particle population X according to the range limit, and start iteration.

[0095] Step 3: When the 500 particle swarms are continuously iterating, the PSO algorithm, i.e., formulas (1) and (2), is used to update the speed and position of each particle to obtain the optimal position of a group of particles; then, the optimal position x of the current particle is calculated. pbest (t＝t / t+1) With the discovery probability p α For comparison, if x pbest (t＝t / t+1) <p α , indicating that the particle has not been eliminated. If x pbest (t＝t / t+1) >p α , it means that the particle is eliminated, and the optimal position of the current particle is substituted into the instruction formula (4) and (5) for updating. In this way, the eliminated particle group will increase the update and calculation of the CS algorithm once, and the difference in iteration time can be ignored.

[0096] Step 4: Calculate the additional variable A through formula (6) and calculate the reset population position X (t = t*) through formula (7).

[0097] Step 5: Take the 3000 total valve position instructions in the data set as input, and output 3000 corresponding valve opening calculation values ​​after the transfer function. fzzr , the measured value of valve opening O zr With O fzzr Calculate the error e' using formula (8) and record it;

[0098] The valve opening error values ​​after 3000 reset particles are substituted into the transfer function by the following formula to obtain the average error value of the valve opening e' avg :

[0099]

[0100] The opening error value e' of each valve is compared with the average error value e' avg By comparison, e' is lower than e' avg The first group is higher than e' avgThe second group of particle populations returns to step 3 for the next iteration; the first group of particle populations continues to combine the nonlinear inertia weight in the SOA algorithm, that is, formula (12), to update the position after classification. The position update formula is as shown in formulas (9) and (10). In formula (12), T max is the maximum number of iterations, which is 500; ω max and ω min The values ​​are 0.8 and 0.2 respectively. The inertia weight changes with the number of iterations as shown in Figure 3 As shown in the figure, it can be seen that the inertia weight changes nonlinearly. It decreases slowly in the early stage of iteration. The particles have a large inertia weight, the population particles have a strong search ability, it is easy to explore a larger area, and it is beneficial to the global search of the particle population; in the middle and late stages of iteration, the inertia weight decreases rapidly, the evolution direction of the particles is more affected by the extreme value, the search target is more refined, and the local search ability is strong.

[0101] Step 6: Determine whether the maximum number of iterations has been reached. If not, return to step 3 for the next iteration; if it has been reached, the iteration is terminated and the optimization result is output, that is, the optimized total flow-total valve position and each valve opening-total valve position characteristic curve.

[0102] According to the above steps, the optimal value of the population in the iterative process of this embodiment changes with the number of iterations as follows: Figure 4 As shown in the figure, after 21 iterations, when the current total valve position instruction is 68 (%), the optimized total flow value is 67.25 (%). The variation of the population optimal value error with the number of iterations in the iterative process of this embodiment is shown in Figure 5 As shown in the figure, it can be seen that after 21 iterations, the error of the optimal value of the population decreases sharply and tends to be stable, and its value is about 0, indicating that the algorithm of the present invention has good convergence speed and accuracy. Figure 6 The valve opening-total valve position instruction characteristic curve before and after optimization is shown in the figure. When the total valve position is less than 50%, the actual valve opening before optimization and the ideal valve opening curve can be well matched. When the total valve position is greater than 50%, the actual valve opening before optimization and the ideal valve opening curve have a large deviation. The optimized valve opening and the ideal valve opening curve can be well matched under different total valve positions, and the error is very small. Figure 7 The total flow-total valve position command characteristic curve before and after optimization. It can be seen from the figure that the total flow and the total valve position command before optimization are in a nonlinear relationship, while the total flow and the total valve position command after optimization are in a positive proportional relationship, which is very close to the theoretical total flow-total valve position curve. This shows that the optimization accuracy of the algorithm of the present invention is very high, proving the rationality and feasibility of the algorithm of the present invention for optimizing valve flow characteristics.

[0103] Embodiment 2:

[0104] like Figure 8 As shown, this implementation provides a valve flow characteristic optimization system for thermal power units based on a particle swarm algorithm, including:

[0105] The optimization data set generation unit is configured to: obtain valve flow characteristic historical data of multiple signal points of the thermal power unit, establish an optimization data set, and construct a total flow-total valve position fitting curve before optimization and a valve opening-total valve position fitting curve based on the optimization data set;

[0106] The particle population random generation unit is configured to: set initial parameters according to the particle swarm algorithm and randomly generate a particle population X (t＝t) ;

[0107] The optimal particle population generating unit is configured to: (t＝t) , using the optimization algorithm combined with the particle swarm algorithm and the cuckoo algorithm to calculate the curve fitness value and find the optimal position x of the individual particle pbest (t＝t) and the global optimal position x gbest (t＝t) , get the optimal particle population;

[0108] The optimal particle population resetting unit is configured to: calculate the additional variable A according to the Seagull algorithm, and use the additional variable A to optimize the optimal particle population to obtain the particle population after the reset position Generate updated total flow-total valve position fitting curve and each valve opening-total valve position fitting curve;

[0109] The classification position updating unit is configured to: reset the particle population after the position Substitute into the valve flow characteristic function, and optimize the data set, calculate the error between the function output value of each particle and the historical data, and then obtain the average error of the particle population. According to the average error of the particle population, the particles are divided into two groups. The particle population of the first group returns the process of calculating the curve adaptation value, and the particle population of the second group uses the nonlinear inertia weight to update the classification position;

[0110] The population optimal value generating unit is configured to: determine whether the maximum number of iterations has been reached: if not, return to the process of calculating the curve adaptation value; if yes, output the population optimal value, which is the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0111] It is understandable that the above-mentioned various units can be separately or all combined into one or several other units to constitute, or some (some) units therein can also be split into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the function of a unit can also be realized by multiple units, or the function of multiple units can be realized by one unit. In other embodiments of the present application, the system can also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0112] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the method of Example 1 of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general computing device such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0113] Embodiment 3:

[0114] like Fig. 9 As shown, this implementation provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0115] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0116] Processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0117] The processor 1001 is configured to execute the following process:

[0118] S1: Collect the historical data of valve flow characteristics of M signal points of the thermal power unit, establish an optimization data set, and construct the total flow-total valve position and each valve opening-total valve position fitting curve before optimization based on the data set;

[0119] S2: Set initial parameters according to the particle swarm algorithm (PSO) and randomly generate particle population X according to the range limit (t ＝t) , the particle position and velocity in the vertical direction of the key point are initialized;

[0120] S3: Use the optimization algorithm (PSO-CS) that combines PSO and Cuckoo Algorithm (CS) to calculate the curve fitness value and find the optimal position x of the individual particle. pbest (t＝t) and the global optimal position x gbest (t＝t) ;

[0121] S4: Calculate the additional variable A according to the Seagull Algorithm (SOA), and use the additional variable A to further optimize the optimal particle population obtained in S3 to obtain the particle population after resetting the position Generate an updated curve;

[0122] S5: The particle population after resetting the position of the tth generation of S3 Substitute it into the valve flow characteristic function, and combine it with the optimized data set established in S1 to calculate the error between the function output value of each particle and the historical data, and then get the average error of the particle population. Based on this, the particles are divided into two groups. The first group goes to S3, and the second group uses the optimization algorithm combining PSO-CS and nonlinear inertia weight in SOA (PSO-CS-SOA) to update the classified position.

[0123] S6: Determine whether the maximum number of iterations has been reached: if not, return to S3; if yes, output the optimal value of the population, that is, the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0124] Embodiment 4:

[0125] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0126] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor, and these instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0127] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process:

[0128] S1: Collect the historical data of valve flow characteristics of M signal points of the thermal power unit, establish an optimization data set, and construct the total flow-total valve position and each valve opening-total valve position fitting curve before optimization based on the data set;

[0129] S2: Set initial parameters according to the particle swarm algorithm (PSO) and randomly generate particle population X according to the range limit (t ＝t) , the particle position and velocity in the vertical direction of the key point are initialized;

[0130] S3: Use the optimization algorithm (PSO-CS) that combines PSO and Cuckoo Algorithm (CS) to calculate the curve fitness value and find the optimal position x of the individual particle. pbest (t＝t) and the global optimal position x gbest (t＝t) ;

[0131] S4: Calculate the additional variable A according to the Seagull Algorithm (SOA), and use the additional variable A to further optimize the optimal particle population obtained in S3 to obtain the particle population after resetting the position Generate an updated curve;

[0132] S5: The particle population after resetting the position of the tth generation of S3 Substitute it into the valve flow characteristic function, and combine it with the optimized data set established in S1 to calculate the error between the function output value of each particle and the historical data, and then get the average error of the particle population. Based on this, the particles are divided into two groups. The first group goes to S3, and the second group uses the optimization algorithm combining PSO-CS and nonlinear inertia weight in SOA (PSO-CS-SOA) to update the classified position.

[0133] S6: Determine whether the maximum number of iterations has been reached: if not, return to S3; if yes, output the optimal value of the population, that is, the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

[0134] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0135] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instruction can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instruction can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (for example, coaxial cable, optical fiber, digital line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that contains one or more available media integration. Available media can be magnetic media (for example, floppy disk, hard disk, tape), optical media (for example, DVD), or semiconductor media (for example, solid-state drive (Solid State Disk, SSD)) and the like.

[0136] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for optimizing valve flow characteristics of thermal power units based on particle swarm algorithm, characterized in that: The process includes: Acquire historical data of valve flow characteristics of multiple signal points of the thermal power unit, establish an optimized data set, and construct a total flow-total valve position fitting curve before optimization and a valve opening-total valve position fitting curve based on the optimized data set; According to the particle swarm algorithm, the initial parameters are set and the particle population X is randomly generated. (t＝t) ; According to the particle population X (t＝t) , using the optimization algorithm combined with the particle swarm algorithm and the cuckoo algorithm to calculate the curve fitness value and find the optimal position x of the individual particle pbest (t＝t) and the global optimal position x gbest (t＝t) , get the optimal particle population; The additional variable A is calculated according to the Seagull algorithm, and the optimal particle population is optimized by using the additional variable A to obtain the particle population after the position is reset. Generate updated total flow-total valve position fitting curve and each valve opening-total valve position fitting curve; The particle population after resetting the position Substitute into the valve flow characteristic function, and optimize the data set, calculate the error between the function output value of each particle and the historical data, and then obtain the average error of the particle population. According to the average error of the particle population, the particles are divided into two groups. The particle population of the first group returns the process of calculating the curve adaptation value, and the particle population of the second group uses the nonlinear inertia weight to update the classification position; Determine whether the maximum number of iterations has been reached: if not, return to the process of calculating the curve adaptation value; if yes, output the population optimal value, which is the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

2. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm according to claim 1, characterized in that: The valve flow characteristic historical data includes: the total valve position instruction of the thermal power unit, the valve opening before optimization, the main steam flow, the main steam pressure and the regulating stage pressure signal.

3. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm according to claim 1, characterized in that: According to the particle swarm algorithm, the initial parameters are set and the particle population X is randomly generated. (t＝t) ,include: Set the population size (number of particles) N and the maximum number of iterations T max , population dimension D, location range limit upper limit c1 and lower limit c2, speed limit ω max and ω min , initial population, individual historical optimal fit, step size control factor α, discovery probability p α , search upper bound U b , search for the lower bound L b , where N, T max , D is a positive integer greater than 0; Randomly generate N D-dimensional arrays within the upper and lower limits of the position range, the array is the particle population X (t＝t) , is the particle population after t iterations, t∈[0,T max ] and is an integer with an initial value of 0.

4. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm according to claim 1, characterized in that: At the initial moment, the particle position x is randomly initialized i (t＝0) =(x i1 (t＝0) ,x i2 (t＝0) ,...,x iD (t＝0) ), i = 1, 2, ..., N, calculate the objective function value of each particle and determine the optimal position x of the initial particle pbest (t＝t) And the optimal value of the objective function x gbest (t＝t) ; Further update the particle velocity and position and calculate the objective function value: v i (t＝t+1) =ωv i (t＝t) +c1r1[p i (t＝t) -x i (t＝t) ]+c2r2[g (t＝t) -x i (t＝t) ](1) x i (t＝t+1) =x i (t＝t) +v i (t＝t+1) ; Where: i∈[1,N], t∈[1,T max ];v i represents the velocity of the particle, x i represents the position of the particle; ω represents the inertia weight factor; c1 and c2 are acceleration constants, also known as learning factors; r1 and r2 are random numbers uniformly distributed between [0, 1]; p i (t＝t) represents the best position of the ith particle after t iterations, also known as the individual optimum; g (t＝t) represents the best position searched by all particles after t iterations; v max Indicates the boundary value set by the velocity vector; Compare the calculated optimal value of the objective function of the tth generation with that of the tth generation. If the optimal value of the objective function of the t+1th generation is better than that of the tth generation, then the optimal position of the current particle is recorded as x. pbest (t＝t+1) , otherwise it is still x pbest (t＝t) ; The current particle's optimal position x pbest (t＝t / t+1) With the probability of discovery p α For comparison, if x pbest (t＝t / t+1) <p α , it means that the particle has not been eliminated. If x pbest (t＝t / t+1) >p α , it means that the particle is eliminated, the particle position is updated, the new objective function value is calculated, and the optimal position of the t+1 / t+2 generation particle is determined by comparison as x pbest (t＝t+1 / t+2) , update the global optimal position to x gbest (t ＝t+1 / t+2) .

5. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm as claimed in claim 4, characterized in that: The particle position is updated using the position update method in the cuckoo algorithm, including: in, x i (t＝t) is the position of the i-th bird's nest at the t-th iteration; a is the step size scaling factor; L(s,λ) obeys the Levy distribution, indicating the random path of Levy flight; s is the random flight step size; λ is the power coefficient; Γ(λ) is the standard Gamma function with unbounded mean and variance.

6. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm according to claim 1, characterized in that: Calculate the additional variable A: A = f c -[t×(f c / T max )], where: f c is the frequency of the additional variable A; According to the obtained additional variable A, combined with the generated particle population X (t＝t) Get the particle population after resetting the position The formula is: Where, X (t＝t) is the t-th generation particle population; is the particle population after the position is reset in the tth generation, T max is the maximum number of iterations.

7. The method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm according to claim 1, characterized in that: Substitute the particle population after resetting the position into the valve flow characteristic function to identify the total valve position command signal data in the data set as input, and obtain the corresponding output O through transfer function calculation. fzzr , calculate the particle error value after the tth generation reset position: In the formula, O zr To identify the valve opening signal value in the data set, is the calculated value of valve opening after the particle at the ith reset position of the tth generation is substituted into the transfer function, for The corresponding error value, i is any integer value between 1 and N; right Calculate the average and get the average error value of the valve opening after the particles after the tth generation N reset positions are substituted into the transfer function Will The average error In comparison, the error value is lower than The first group is higher than The second group is: The particle population of the second group returns to the process of calculating the curve fitness value, and the particle population of the first group combines the nonlinear inertia weight in the cuckoo algorithm to update the position. The formula is as follows: Where, X i (t＝t+1) is the i-th particle of the t+1th generation; is the i-th particle after the position is reset in the t-th generation; is the global optimal particle; x, y, z are the parameters related to the spiral attack behavior of the cuckoo algorithm; are the moving speeds of the i-th particle after the position is reset in the t+1th and tth generations respectively; is the individual optimal particle after resetting the position in the tth generation; r1 and r2 are random numbers between 0 and 1; c1 and c2 are constants between 0 and 1, and ω is the nonlinear inertia weight. Get the individual and global optimal particles of the particle population after resetting the position; The calculation formula of nonlinear inertia weight factor is: In the formula, ω (t＝t) represents the nonlinear inertia weight at iteration t, ω max ,ω min Represent the maximum and minimum inertia weights respectively.

8. A valve flow characteristic optimization system for thermal power units based on particle swarm algorithm, characterized in that: include: The optimization data set generation unit is configured to: obtain valve flow characteristic historical data of multiple signal points of the thermal power unit, establish an optimization data set, and construct a total flow-total valve position fitting curve before optimization and a valve opening-total valve position fitting curve based on the optimization data set; The particle population random generation unit is configured to: set initial parameters according to the particle swarm algorithm and randomly generate a particle population X (t＝t) ; The optimal particle population generating unit is configured to: (t＝t) , using the optimization algorithm combined with the particle swarm algorithm and the cuckoo algorithm to calculate the curve fitness value and find the optimal position x of the individual particle pbest (t＝t) and the global optimal position x gbest (t＝t) , get the optimal particle population; The optimal particle population resetting unit is configured to: calculate the additional variable A according to the Seagull algorithm, and use the additional variable A to optimize the optimal particle population to obtain the particle population after the reset position Generate updated total flow-total valve position fitting curve and each valve opening-total valve position fitting curve; The classification position updating unit is configured to: reset the particle population after the position Substitute into the valve flow characteristic function, and optimize the data set, calculate the error between the function output value of each particle and the historical data, and then obtain the average error of the particle population. According to the average error of the particle population, the particles are divided into two groups. The particle population of the first group returns the process of calculating the curve adaptation value, and the particle population of the second group uses the nonlinear inertia weight to update the classification position; The population optimal value generating unit is configured to: determine whether the maximum number of iterations has been reached: if not, return to the process of calculating the curve adaptation value; if yes, output the population optimal value, which is the optimized total flow-total valve position and each valve opening-total valve position fitting curve.

9. A computer device, characterized in that: include: a processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for optimizing the flow characteristics of a valve of a thermal power unit based on a particle swarm algorithm as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the method for optimizing valve flow characteristics of a thermal power unit based on a particle swarm algorithm as described in any one of claims 1 to 7.

Images