Hydroelectric generating set maintenance layout method based on improved genetic algorithm

Abstract

The invention relates to a hydroelectric generating set maintenance layout optimization method based on an improved genetic algorithm, and aims to solve the problems that an existing maintenance space layout method based on a two-dimensional drawing depends on experience of designers, is long in planning period, high in cost consumption, poor in planning effect accuracy and waste in resources, and cannot meet actual production requirements. The invention provides a hydroelectric generating set maintenance layout optimization method based on an improved genetic algorithm, and the method comprises the steps: carrying out the numbering and classification of disassembled maintenance parts, determining the maintenance space of a hydroelectric generating set through a free plane search method, carrying out the modeling of a hydroelectric maintenance layout plan based on the maintenance carrying cost and the maintenance space utilization rate, and carrying out the optimization of the maintenance layout. The model is solved by using an improved genetic algorithm, and an obtained result is prevented from falling into local optimum and can be quickly converged, so that optimal layout planning of the maintenance parts of the hydroelectric generating set is realized.

Description

Technical Field

[0001] The invention relates to the technical field of digital maintenance of hydropower units, and in particular to a method for optimizing the layout of maintenance components of hydropower units based on an improved genetic algorithm. Background Art

[0002] Hydropower generation is a process that uses the kinetic energy or potential energy of water to drive a turbine and then convert it into electrical energy. It is a renewable energy source with clean and stable characteristics. However, the structure of the turbine unit is complex, the types and quantity of parts are numerous, and the maintenance cycle is long and the maintenance space is small. These problems not only affect the maintenance work of the hydropower unit, but also further affect the normal operation and power generation efficiency of the hydropower generator, posing a serious threat to the safety and economy of hydropower generation. At present, the existing maintenance space layout method based on two-dimensional drawings mainly relies on the experience of designers, which can no longer meet the actual needs of production. In addition, this planning method is prone to problems such as long planning cycle, high cost, poor planning effect accuracy and waste of resources. Therefore, layout planning of maintenance components of hydropower units is an important task of unit maintenance, the purpose of which is to improve maintenance efficiency, make full use of maintenance space, reduce maintenance costs, ensure the safe and stable operation of hydropower units, and improve the operating efficiency and economic benefits of hydropower generation. Summary of the invention

[0003] The technical problem of the present invention is to improve the genetic algorithm to optimize the design of the maintenance layout of the hydropower unit, improve the efficiency of the maintenance work, make full use of the maintenance space, avoid the waste of resources, and improve the safety and efficiency of the operation of the hydropower unit.

[0004] The purpose of the present invention is to solve the above-mentioned problems. The present invention provides a method for optimizing the maintenance layout of a hydropower unit based on an improved genetic algorithm. The method realizes the digitization of maintenance information by numbering and classifying disassembled maintenance parts. The maintenance space of the hydropower unit is determined by an idle plane search method. Then, a mathematical model is built for the hydropower maintenance layout planning based on the maintenance transportation cost and the maintenance space utilization rate. The mathematical model is solved by using an improved genetic algorithm so that the obtained result avoids falling into the local optimum and can converge quickly, thereby realizing the optimal layout planning of the maintenance components of the hydropower unit.

[0005] The technical solution of the present invention is a method for optimizing the maintenance layout of a hydropower unit based on an improved genetic algorithm, which is characterized by comprising the following steps: S1: According to the actual structure of the hydropower unit, the various parts of the hydropower unit for maintenance and disassembly are classified and numbered, and the maintenance parts information is digitized; S2: Use the idle plane search method to search for the maintenance space of the hydropower unit; S3: Based on the principle of minimum maintenance cost and maximum area utilization, the optimal objective function model of maintenance layout planning is constructed; S4: Calculate the optimal solution of the model based on the improved genetic algorithm and obtain the optimal location of the hydropower unit component layout; S5: Perform simulation evaluation based on the solution of step S4 to form an overall layout optimization plan for the maintenance parts of the hydropower unit.

[0006] Furthermore, in step S1, the maintenance component information is digitized, including the equipment being decomposed into a tree structure composed of parts, and the maintenance information of the parts being decomposed into maintenance tools, instruments, precautions, and dimensions and weights, which are encoded to form a relational data table.

[0007] Furthermore, in step S2, an idle plane search method is used to search for the maintenance space of the hydropower unit, including taking the idle plane as the available space for placing the machine, searching the entire plane from the upper left corner to the bottom and then to the right with a fixed step size, obtaining all idle planes, and determining that the idle plane is the maintenance space of the hydropower unit.

[0008] Preferably, step S3 includes the following sub-steps: 1) Establish the optimal objective function of comprehensive maintenance: ; In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, represents the optimal maintenance planning function, which is the weighted sum of the minimum maintenance and handling cost and the minimum area utilization. , is the weight factor, and , find the minimum value; 2) The length constraints of the repair parts are: ; In the formula, represents the width of the maintenance area k, represents the length of the n+1th maintenance component, Represents the sum of the lengths of n maintenance components in maintenance area k.

[0009] 3) The width constraints of the repaired parts are: ; In the formula, represents the width of the maintenance area k, represents the width of the n+1th maintenance component, represents the sum of the widths of n maintenance components arranged in maintenance area k; 4) Calculation formula for the horizontal coordinate of the repaired parts: ; In the formula, represents the ordinate of the i-th maintenance component in maintenance area k, represents the length of the i-th maintenance component in maintenance area k, 5) Calculation formula for the ordinate of the repaired component: ; In the formula, Represents the ordinate of the i-th maintenance component in maintenance area k.

[0010] Furthermore, in step S4, the optimal handling cost and area utilization of the repaired parts are taken as the combined optimization target, including the following sub-steps: S41. Coding principle: Use digital coding rules to directly encode the numbered disassembled and repaired parts in digital format.

[0011] S42. Initialize the first generation population using the 2-opt and 3-opt methods to generate the first generation population.

[0012] S43. Simulated annealing process. The new individuals generated in this algorithm are determined by the Metropolis acceptance criterion. All individuals in the population are annealed and then a new population is generated.

[0013] S44. Selection, crossover, and mutation principles. The selection principle adopts the roulette method, and the individual fitness function value is used as the basis for individual selection; the crossover principle uses the coincidence point crossover or random crossover operation between the selected parents to generate new offspring; the mutation operation uses double-point exchange mutation; S45. Fitness function design, taking the optimal handling cost and area utilization of maintenance parts as the combined optimization objectives, the fitness calculation formula for each individual in the population is: ; In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, Represents the fitness of each individual in the population.

[0014] Preferably, in step S4, the optimal solution of the model is calculated based on the improved genetic algorithm, and the genetic algorithm is used to perform an annealing operation on each new individual to obtain a new generation of population until the genetic algorithm converges and the iteration value tends to be stable or no longer changes significantly.

[0015] Compared with the prior art, the beneficial effects of the present invention include: 1) Based on the total maintenance parts transportation cost and maintenance space utilization rate as principles, a maintenance layout planning model was established. Compared with the traditional layout evaluation method based on personnel experience, it provides a fixed hydropower unit maintenance layout evaluation standard.

[0016] 2) The improved genetic algorithm is used to solve the maintenance layout problem of hydropower units, which overcomes the problem of traditional genetic algorithms falling into local optimality, improves the efficiency of calculation and the accuracy of calculation results, effectively shortens the maintenance cost of hydropower units, and improves the utilization rate of maintenance space.

[0017] 3) By simulating and verifying the optimal solution and outputting it as an overall layout optimization plan for the maintenance parts of the hydropower unit, a series of information related to the production process is provided, which can guide production operations more effectively. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0019] Figure 1 A schematic diagram of a flow chart of a method for optimizing the maintenance layout of a hydropower unit according to an embodiment of the present invention; Figure 2 A schematic diagram of a dynamic search using an idle search method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the maintenance space of a hydropower unit according to an embodiment of the present invention; Figure 4 This is a flow chart of an improved genetic algorithm according to an embodiment of the present invention; Figure 5 A comparison chart of the improved genetic algorithm according to an embodiment of the present invention and the traditional genetic algorithm. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. However, it should be understood that the protection scope of the present invention is not limited to the specific implementation methods.

[0021] Reference Figure 1As shown, the present invention provides a method for optimizing the overall layout of hydropower unit maintenance based on an improved genetic algorithm, comprising the following steps: S1: According to the actual structure of the hydropower unit, the various parts of the hydropower unit for maintenance and disassembly are classified and numbered, and the maintenance parts information is digitized; As shown in Table 1, according to the actual structure of the hydropower unit, each maintenance and disassembly component of the hydropower unit is classified and numbered, and the maintenance component information is digitized. The equipment is decomposed into a tree structure composed of components, and the maintenance information of the components is decomposed into maintenance tools, instruments, precautions, dimensions and weights, which are encoded to form a relational data table.

[0022] Table 1 Dimensions of components of each unit

[0023] S2: Use the idle plane search method to search for the maintenance space of the hydropower unit.

[0024] The free plane is the available space in the layout space where the machine can be placed. With a fixed step length t, where t does not exceed the length of the shortest side of the placed items, the entire plane is searched from the upper left corner downward to the right to find all the free planes, and the machines to be placed are continuously moved within the free planes to determine the maintenance space of the hydropower unit. The result of the free plane search algorithm is a list of available free planes of the currently searched plane.

[0025] The area of ​​the hydroelectric unit in the present invention is 1440m 2 , the maintenance space is divided into 6 parts using the free plane search method. Figure 3 shown.

[0026] S3: Based on the principle of minimum maintenance cost and maximum area utilization, the optimal objective function model of maintenance layout planning is constructed; 1) Establish the optimal objective function of comprehensive maintenance: ; In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, represents the optimal maintenance planning function, which is the weighted sum of the minimum maintenance and handling cost and the minimum area utilization. , is the weight factor, and , find the minimum value; 2) The length constraints of the repair parts are: ; In the formula, represents the width of the maintenance area k, represents the length of the n+1th maintenance component, Represents the sum of the lengths of n maintenance components in maintenance area k.

[0027] 3) The width constraints of the repaired parts are: ; In the formula, represents the width of the maintenance area k, represents the width of the n+1th maintenance component, represents the sum of the widths of n maintenance components arranged in maintenance area k; 4) Calculation formula for the horizontal coordinate of the repaired parts: ; In the formula, represents the ordinate of the i-th maintenance component in maintenance area k, represents the length of the i-th maintenance component in maintenance area k, 5) Calculation formula for the ordinate of the repaired component: ; In the formula, Represents the ordinate of the i-th maintenance component in maintenance area k.

[0028] S4: Based on the improved genetic algorithm, the optimal solution of the model is calculated to obtain the optimal location of the hydropower unit components, such as Figure 4 As shown: The S41 coding principle adopts digital coding rules to directly encode the numbered disassembled and repaired parts in digital format.

[0029] S42 The first generation population is initialized using the 2-opt and 3-opt methods to generate the first generation population.

[0030] S43 simulated annealing process. The new individuals generated in this algorithm are determined by the Metropolis acceptance criterion. All individuals in the population are annealed and then a new population is generated.

[0031] S44 selection, crossover, and mutation principles. The selection principle adopts the roulette method, that is, the individual fitness function value is used as the basis for individual selection; the crossover principle uses coincident point crossover or random crossover operations between the selected parents to generate new offspring; the mutation operation uses double-point exchange mutation; The S45 fitness function is designed with the optimal handling cost and area utilization of maintenance parts as the combined optimization objectives. The fitness calculation formula for each individual in the population is: ; In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, Represents the fitness of each individual in the population.

[0032] As shown in Table 2, based on the improved genetic algorithm solution model, individuals with high fitness are selected for crossover and mutation operations to obtain the optimal convergence solution and determine whether the new individuals meet the predetermined termination conditions. This process can be iterated continuously until the preset termination conditions are met. If they are met, the optimal solution is obtained. If not, jump to step S3 to update the population and enter the next round of iteration.

[0033] Table 2 Optimization results of maintenance layout of hydropower units

[0034] like Figure 5 As shown, the improved genetic algorithm obtains the optimal convergence value in about 55 generations, while the traditional genetic algorithm converges faster initially but slower overall. The improved genetic algorithm is superior to the traditional genetic algorithm in both convergence speed and results.

[0035] The present invention establishes a comprehensive maintenance planning optimization model based on the principles of minimizing the total logistics cost and the utilization rate of the maintenance space. Compared with the traditional layout evaluation method based on personnel experience, it provides a quantitative evaluation standard for the maintenance layout of hydropower units. It uses an improved genetic algorithm to solve the layout problem of hydropower maintenance unit components, which improves the efficiency of the calculation and the accuracy of the calculation results, and effectively shortens the cycle of the maintenance layout planning of the hydropower unit. By simulating and verifying the optimal solution and outputting it as an overall layout optimization plan for the hydropower unit components, it provides a series of information related to the production process, which can more effectively guide production operations.

Claims

1. A method for optimizing the maintenance layout of hydropower units based on an improved genetic algorithm, characterized in that: The following steps are involved: S1: According to the actual structure of the hydropower unit, the various parts of the hydropower unit for maintenance and disassembly are classified and numbered, and the maintenance parts information is digitized; S2: Use the idle plane search method to search for the maintenance space of the hydropower unit; S3: Based on the principle of minimum maintenance cost and maximum area utilization, the optimal objective function model of maintenance layout planning is constructed; S4: Calculate the optimal solution of the model based on the improved genetic algorithm and obtain the optimal location of the hydropower unit component layout; S5: Perform simulation evaluation based on the solution of step S4 to form an overall layout optimization plan for the maintenance parts of the hydropower unit.

2. A hydropower unit maintenance layout method based on improved genetic algorithm according to claim 1, characterized in that: In step S1, the maintenance component information is digitized, including the equipment being decomposed into a tree structure composed of parts, and the maintenance information of the parts is decomposed into maintenance tools, instruments, precautions and dimensions and weights, which are encoded to form a relational data table.

3. The hydropower unit maintenance layout method based on improved genetic algorithm according to claim 1 is characterized in that: In step S2, the idle plane search method is used to search for the maintenance space of the hydropower unit, including taking the idle plane as the available space for placing the machine, searching the entire plane from the upper left corner to the bottom and then to the right with a fixed step length, obtaining all the idle planes, and determining that the idle plane is the maintenance space of the hydropower unit.

4. The hydropower unit maintenance layout method based on improved genetic algorithm according to claim 1 is characterized in that: In step S3, the following sub-steps are included: 1) Establish the optimal objective function of comprehensive maintenance: ； In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, represents the optimal maintenance planning function, which is the weighted sum of the minimum maintenance and handling cost and the minimum area utilization. , is the weight factor, and , find the minimum value; 2) The length constraints of the repair parts are: ； In the formula, represents the width of the maintenance area k, represents the length of the n+1th maintenance component, represents the sum of the lengths of n maintenance components in maintenance area k; 3) The width constraints of the repaired parts are: ； In the formula, represents the width of the maintenance area k, represents the width of the n+1th maintenance component, represents the sum of the widths of n maintenance components arranged in maintenance area k; 4) Calculation formula for the horizontal coordinate of the repaired parts: ； In the formula, represents the ordinate of the i-th maintenance component in maintenance area k, represents the length of the i-th maintenance component in maintenance area k, 5) Calculation formula for the ordinate of the repaired parts: ； In the formula, Represents the ordinate of the i-th maintenance component in maintenance area k.

5. The hydropower unit maintenance layout method based on improved genetic algorithm according to claim 1 is characterized in that: In step S4, the optimal handling cost and area utilization of the repair parts are taken as the combined optimization target, including the following sub-steps: S41. Coding principle: adopt digital coding rules and directly encode the numbered disassembled and repaired parts in digital format; S42. Initialization of the first generation population, using the 2-opt and 3-opt methods to generate the first generation population; S43. Simulated annealing process, in which the new individuals generated by the algorithm are determined by the Metropolis acceptance criterion, and all individuals in the population are annealed to generate a new population; S44. Selection, crossover and mutation principles. The selection principle adopts the roulette method, and the individual fitness function value is used as the basis for individual selection; the crossover principle adopts the coincidence point crossover or random crossover operation between the selected parents to generate new offspring; the mutation operation adopts double point exchange mutation; S45. Fitness function design, taking the optimal handling cost and area utilization of maintenance parts as the combined optimization objectives, the fitness calculation formula for each individual in the population is: ； In the formula, Indicates the maintenance parts of different hydropower units. Indicates different maintenance spaces, Indicates the cost of transporting repair parts. Indicates the parts handling distance, Indicates the number of parts moved, represents the minimum area utilization, Represents the fitness of each individual in the population.

6. The hydropower unit maintenance layout method based on improved genetic algorithm according to claim 1 is characterized in that: In step S4, the optimal solution of the model based on the improved genetic algorithm calculation also includes using the genetic algorithm to perform an annealing operation on each new individual to obtain a new generation of population until the genetic algorithm converges and the iteration value tends to be stable or no longer changes significantly.

Images