Hydroelectric generating set maintenance part layout optimization method and system based on subtraction average optimization algorithm

Abstract

The invention belongs to the technical field of hydroelectric generating set digital maintenance, discloses a hydroelectric generating set maintenance component layout optimization method based on a subtraction average optimization algorithm, and establishes a comprehensive maintenance planning optimization model based on the principle of total logistics cost minimization and maintenance space utilization rate maximization. Different from a traditional layout evaluation method depending on personnel experience, the invention provides a quantitative hydroelectric generating set maintenance layout evaluation standard. The layout problem of the hydroelectric generating set components is solved through the improved subtraction optimization algorithm, the calculation efficiency and the result accuracy are improved, and the maintenance layout planning period is effectively shortened. Through simulation verification of the optimal solution and output of the overall layout optimization scheme of the hydroelectric generating set components, the detailed information related to the production process is provided, so that the production operation can be guided more effectively.

Description

Technical Field

[0001] This invention belongs to the field of digital maintenance technology for hydropower units, and particularly relates to a method and system for optimizing the layout of maintenance components for hydropower units based on a subtractive average optimization algorithm. Background Technology

[0002] Hydropower generation utilizes the kinetic or potential energy of water to drive turbines, converting it into electricity. It is a clean and stable renewable energy source. However, hydropower turbine units have complex structures, numerous and varied components, long maintenance cycles, and limited maintenance space. These issues not only affect the maintenance of the units but may also further impact the normal operation and power generation efficiency of the hydropower generators, threatening the safety and economic viability of power generation. Currently, maintenance space layout methods based on two-dimensional drawings rely heavily on the experience of designers, which cannot meet actual production needs and easily leads to problems such as long planning cycles, high costs, poor accuracy, and resource waste. Therefore, the layout planning of maintenance components in hydropower units has become a key task for improving maintenance efficiency, optimizing space utilization, reducing costs, ensuring the safe and stable operation of the units, and improving power generation efficiency and economic benefits.

[0003] Existing technology patents:

[0004] CN109656998A (“Method for Calculating the Efficiency of Hydropower Units Based on Operation Monitoring Data”) discloses a technical solution that calculates and obtains the efficiency values ​​of hydropower units under different operating conditions in real time by constructing a database and using techniques such as spatial interpolation.

[0005] Existing technical problems:

[0006] While this patented method effectively achieves efficiency calculation and data digitization, it focuses on efficiency monitoring and evaluation, without addressing maintenance layout planning or space optimization. In actual maintenance processes, this method cannot quantify the rationality of the placement of each maintenance component, nor can it provide optimized layout schemes or maintenance path planning. Therefore, the lack of quantitative evaluation standards to guide maintenance space layout, improve space utilization, and reduce logistics and handling costs means it cannot significantly improve maintenance planning efficiency and layout quality; this is its significant technical limitation. Summary of the Invention

[0007] To address the problems existing in the prior art, this invention provides a method for optimizing the layout of maintenance components in hydropower units based on a subtractive averaging optimization algorithm.

[0008] This invention is implemented as follows: A method for optimizing the layout of maintenance components in hydropower units based on a subtractive averaging optimization algorithm includes:

[0009] S1: Based on the actual mechanical structure of the hydropower unit, classify and number its various maintenance and disassembly components, digitize the relevant maintenance component information, and obtain hydropower unit component structure sample data.

[0010] S2: The single-step planar search method is used to search for the unused space in the power plant for maintenance of hydropower units;

[0011] S3: Based on the principles of minimizing overall maintenance costs and maximizing maintenance space utilization, construct an optimal objective function model for maintenance layout planning;

[0012] S4: Introducing Singer chaotic mapping and golden sine strategy to improve the subtractive average optimization algorithm, so as to enhance the diversity and global convergence of the population and overcome the problem that the traditional subtractive average optimization algorithm is prone to getting trapped in local optima.

[0013] S5: Based on the improved subtractive average optimization algorithm, the maintenance layout planning model is optimized and solved. Through multiple iterations of training, the optimal location of the maintenance components of the hydropower unit and the overall layout optimization scheme are obtained.

[0014] Furthermore, in step S1, the digital processing of the maintenance component information involves decomposing the equipment into tree-like components and breaking down the maintenance information of each component into maintenance tools, instruments, precautions, dimensions, and weight, etc.; after encoding, a corresponding relational data table is formed.

[0015] Furthermore, in step S2, the single-step planar space search specifically involves: the maintenance plane refers to the area in the layout space where unit components can be maintained; using the shortest side of the maintenance part as the step size v, the entire plane is scanned step by step downwards and to the right, starting from the upper left corner, to find all suitable spaces for maintenance; within the free area, the hydropower unit components can move continuously to determine the available maintenance areas; the result of the single-step search algorithm is a list of available maintenance areas in the current search plane.

[0016] Furthermore, step S3 includes the following sub-steps:

[0017] 1) The optimal objective function for comprehensive maintenance is established as follows:

[0018]

[0019] In the formula, i represents different maintenance parts in different hydropower unit areas, j represents different maintenance spaces, and c ij This indicates the cost of transporting the repaired parts, d ij f represents the distance the parts are transported. ij S represents the number of parts to be moved. tLet F represent the minimum area utilization rate, which is the maintenance optimal planning function, i.e., the weighted sum of the minimum maintenance and handling cost and the minimum area utilization rate. l1 and l2 are weighting factors, and l1+l2=1, in order to obtain the minimum value.

[0020] 2) The length constraints of the parts to be inspected are as follows:

[0021]

[0022] In the formula, z k z represents the width of the maintenance area k. k(n+1) This represents the length of the (n+1)th component under maintenance. This represents the sum of the lengths of the n components to be inspected in the inspection area k;

[0023] 3) The width constraint conditions for the parts under inspection are:

[0024]

[0025] In the formula, w k w represents the width of the maintenance area k. k(n+1) This represents the width of the (n+1)th maintenance component. This represents the sum of the widths of the n maintenance components arranged in maintenance area k;

[0026] 4) Formula for calculating the x-axis of the component under maintenance:

[0027]

[0028] In the formula, x ki Z represents the ordinate of the i-th component under maintenance in maintenance area k. ki This represents the length of the i-th component in the maintenance area k.

[0029] 5) Formula for calculating the ordinate of the component under maintenance:

[0030] y ki =max[y k3 ,y k2 ,y k1 ...y kn (5)

[0031] In the formula, y ki This represents the ordinate of the i-th component under maintenance in maintenance area k.

[0032] Furthermore, the specific steps of the subtraction averaging optimization algorithm in step S4 are as follows:

[0033] 1) Randomly initialize population locations

[0034] x i,d =lb d+r i,d ·(ub d -lb d (6)

[0035] x i,d Represents the current optimal position, ub d lb d r represents the upper and lower bounds of the optimization of decision variable d. i,d A random number within the interval [1,2];

[0036] 2) Update the agent position using the arithmetic mean position of the population members at the t-th iteration of the search agent. Based on the v-subtraction between search agent B and search agent A, it is defined as:

[0037]

[0038] In the formula, Let F(A) and F(B) represent random data vectors of dimension m, and let F(A) and F(B) represent the fitness values ​​of individuals A and B in the population.

[0039] 3) The position update formula is:

[0040]

[0041] In the formula, N is the total number of populations, and r i A random number in the interval [0,1]. For the new position after displacement update, F i This represents the objective function value.

[0042] Furthermore, the specific method for introducing the Singer chaotic mapping optimization subtraction flat optimization algorithm in step S4 is as follows:

[0043] The mathematical formula for the Singer chaotic map is as follows:

[0044]

[0045] In the formula: mod is the modulo operation, which calculates the remainder when two numbers are divided; t is the dimension of the solution, representing the current iteration number. This represents the position of the i-th individual in the t-th iteration; This represents the new population position after the chaotic mapping;

[0046] Initializing the dung beetle population location using chaotic values ​​generated by the Singer mapping generates a uniform and random initial population, which can increase population diversity and thus help the SABO algorithm to accelerate convergence in subsequent optimization processes.

[0047] In step S4, the golden sine algorithm is introduced to optimize the subtractive averaging algorithm. The specific method is as follows:

[0048] The mathematical formula for the golden sine algorithm is as follows:

[0049]

[0050] In the formula: X represents the position of the i-th individual in the t-th iteration. b Let e1 be a random number in the range [0, 2π], e2 be a random number in the range [0, π], a be an initial value of -π, b be an initial value of π, g1 be the golden ratio, and k1 and k2 be coefficients containing the golden ratio.

[0051] The Golden Sine Algorithm (Gold-SA) is an iterative optimization method based on the sine function, often used to search for the extreme points of a function in two-dimensional space. The Gold-SA algorithm has a strong global search capability by sequentially accessing all values ​​of the sine function. At the same time, the introduction of the golden ratio makes it also have a strong search capability in the vicinity of the optimal solution sought in each iteration.

[0052] In step S4, the fitness pair function is designed based on the improved subtractive averaging optimization algorithm: the optimal handling cost and area utilization rate of the repaired parts are used as the combined optimization objectives, and the fitness calculation formula for each individual in the population is as follows:

[0053]

[0054] In the formula, i represents different maintenance parts in different hydropower unit areas, j represents different maintenance spaces, and c ij This indicates the cost of transporting the repaired parts, d ij f represents the distance the parts are transported. ij S represents the number of parts to be moved. t f represents the minimum area utilization rate. i This represents the fitness of each individual in the population;

[0055] Step S5 includes a combined optimization objective of optimal handling cost and area utilization rate for the repaired parts, and includes the following sub-steps:

[0056] 1) Coding principle: Adopt the numerical coding rule, and directly encode the disassembled and repaired parts with numbers in numerical format;

[0057] 2) Set the ISABO population size N, the total number of iterations to T, and set i = 1 and t = 1;

[0058] 3) Introduce Singer chaotic mapping to randomly generate the initial search population position;

[0059] 4) Evaluate the objective function based on the initial search population: Update the population position using the golden sine algorithm according to equation (11) during the iteration process;

[0060] 5) Calculate the fitness value of the new population according to equation (12);

[0061] 6) Replace the old population location with a new population that has better fitness, and generate a new population location;

[0062] 7) Repeat steps 4)-6) until the termination condition is met, and determine the optimal layout plan.

[0063] In step S5, the optimal solution of the model is calculated based on the improved subtraction optimization algorithm to obtain a new generation of population until the algorithm converges and the iteration value tends to stabilize or no longer changes significantly.

[0064] Another objective of this invention is to provide a hydropower unit maintenance component layout optimization system based on a subtraction average optimization algorithm, comprising:

[0065] The digital processing module is used to classify and number various maintenance and disassembly components according to the actual mechanical structure of the hydropower unit, and to digitize the relevant maintenance component information to obtain sample data of hydropower unit component structure.

[0066] The search module is used to search for the unused space in the power plant for maintenance of hydropower units using a single-step planar search method.

[0067] A module is constructed to build an optimal objective function model for maintenance layout planning, based on the principles of minimizing overall maintenance costs and maximizing maintenance space utilization.

[0068] The module introduces Singer chaotic mapping and the golden sine strategy to improve the subtractive average optimization algorithm, so as to enhance the diversity and global convergence of the population and overcome the problem that the traditional subtractive average optimization algorithm is prone to getting trapped in local optima.

[0069] The iterative training module is used to optimize the maintenance layout planning model based on the improved subtractive average optimization algorithm. Through multiple iterative training, the optimal location of the maintenance components of the hydropower unit and the overall layout optimization scheme are obtained.

[0070] Another object of the present invention is to provide a computer device, the computer device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the hydropower unit maintenance component layout optimization method based on the subtraction average optimization algorithm.

[0071] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the hydropower unit maintenance component layout optimization method based on the subtraction average optimization algorithm.

[0072] Another objective of this invention is to provide an information data processing terminal for implementing the hydropower unit maintenance component layout optimization system based on the subtraction average optimization algorithm.

[0073] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0074] This invention provides a method for optimizing the maintenance layout of hydropower units based on an improved subtractive averaging optimization algorithm. It digitizes maintenance information by numbering and classifying disassembled maintenance components, determines the maintenance space of the hydropower unit using a planar search method, and establishes a mathematical model for hydropower maintenance layout planning based on maintenance transportation costs and maintenance space utilization. The subtractive averaging optimization algorithm is improved by introducing Singer chaotic mapping and the golden sine algorithm, effectively avoiding the problem of the algorithm getting trapped in local optima. The improved algorithm is then used to find the optimal solution for the mathematical model, enabling the results to converge quickly and achieving the optimal layout planning of the hydropower unit's maintenance components. Attached Figure Description

[0075] Figure 1 This is a flowchart of the hydropower unit maintenance component layout optimization method based on the subtraction average optimization algorithm provided in the embodiments of the present invention;

[0076] Figure 2 This is a structural block diagram of the hydropower unit maintenance component layout optimization system based on the subtraction average optimization algorithm provided in this embodiment of the invention;

[0077] Figure 3 This is a schematic diagram of dynamic search using a single-step planar spatial search method provided in an embodiment of the present invention;

[0078] Figure 4 This is a schematic diagram of the maintenance space of the hydropower plant provided in an embodiment of the present invention;

[0079] Figure 5 This is a flowchart of the improved subtractive averaging optimization algorithm provided in an embodiment of the present invention;

[0080] Figure 6 This is a comparison chart of the ISABO algorithm provided in this embodiment of the invention and the traditional SABO algorithm.

[0081] Figure 7 This is a two-dimensional layout effect diagram of the maintenance components after optimization according to an embodiment of the present invention.

[0082] Figure 8 This is a three-dimensional layout rendering of the maintenance components after optimization according to an embodiment of the present invention.

[0083] Figure 9 This is a three-dimensional unfolded layout effect diagram of the maintenance components after the optimization of the present invention. Detailed Implementation

[0084] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0085] During the long-term maintenance of hydropower units, existing layout methods generally suffer from insufficient space utilization and lengthy component handling paths. Due to the large number, size, and significant weight variations of hydropower unit components, traditional experience-based layout methods often lead to increased handling distances and higher frequency of auxiliary equipment use during maintenance, ultimately resulting in longer maintenance times and higher costs. In actual plant maintenance areas, unreasonable space division can also cause congestion in localized areas, restricting the lifting and handling of large equipment, reducing maintenance efficiency, and even affecting the safety of unit operation. Therefore, how to achieve a rational layout of maintenance components within limited plant space has become a key issue restricting the maintenance efficiency of hydropower units.

[0086] In this context, the layout optimization problem is transformed into a multi-objective programming model. This model not only focuses on minimizing the handling cost of maintenance components but also considers the area utilization rate of the maintenance area. Specifically, each component involves variables such as weight, size, and handling path length during layout, which are linked to constraints through an objective function. The weighting coefficients in the objective function reflect the balance between cost and space, while the constraints ensure that maintenance components do not experience size conflicts or exceed boundaries in the layout space. In this way, the essence of the problem is abstracted into a combinatorial optimization problem, requiring the search for a globally optimal solution in a complex search space.

[0087] While traditional subtractive averaging optimization algorithms can solve combinatorial optimization problems to some extent, they are prone to getting trapped in local optima when dealing with nonlinear, multi-peak maintenance layout problems. This algorithm, based on a difference update strategy between the surrogate position and the population average position, suffers from insufficient search diversity when the population size is small, resulting in fast convergence but weak global applicability of the solution. Therefore, relying solely on this algorithm cannot meet the industrial application requirements of hydropower unit maintenance layout; improvements are necessary to enhance the global exploration capability and local convergence accuracy.

[0088] To overcome this deficiency, Singer's chaotic mapping and the golden sine strategy are introduced as algorithm improvement mechanisms. Singer's mapping generates a chaotic sequence with uniformity and ergodicity through nonlinear iteration, which is used to initialize the population positions, resulting in a wider distribution of initial solutions and increasing the diversity of the early search phase. The golden sine strategy utilizes the periodicity of the sine function and the search characteristics of the golden ratio to strengthen the search of the neighborhood of the current optimal solution during iteration, avoiding premature convergence while maintaining global optimization capability. The combination of these two mechanisms significantly improves the stability and convergence efficiency of the improved subtractive average optimization algorithm in high-dimensional maintenance layout problems.

[0089] During algorithm execution, the system first establishes structural samples based on the digital information of the components under maintenance and inputs them into the layout optimization model. Then, it determines candidate regions in the maintenance plane using a single-step planar search method and calculates the available layout space by combining the component's geometric parameters. The objective function iteratively calculates the cost of the transport path and the space utilization rate, and the improved algorithm updates the position and fitness value of each candidate solution during the search process. Through multiple iterations, the new generation of the population gradually approaches the global optimum. When the objective function value stabilizes, the optimal layout scheme that satisfies the constraints is obtained.

[0090] Ultimately, this method significantly reduces the overall transportation costs of maintenance components in industrial applications, while effectively improving the utilization efficiency of plant maintenance areas. Because the component layout scheme is optimal based on numerical calculations, its application in actual hydropower station maintenance sites can reduce the frequency of auxiliary equipment use, shorten disassembly and assembly time, and improve personnel safety and the controllability of maintenance plans. This method not only adapts to the daily maintenance of conventional hydropower units but also has the potential to be extended to the maintenance of large hydropower hubs and complex unit structures, providing a reliable layout optimization solution for the full life-cycle maintenance of hydropower units.

[0091] like Figure 1 As shown in the figure, the method for optimizing the layout of maintenance components of a hydropower unit based on the subtraction average optimization algorithm provided by this embodiment of the invention includes the following steps:

[0092] S1: Based on the actual mechanical structure of the hydropower unit, classify and number its various maintenance and disassembly components, digitize the relevant maintenance component information, and obtain hydropower unit component structure sample data.

[0093] S2: The single-step planar search method is used to search for the unused space in the power plant for maintenance of hydropower units;

[0094] S3: Based on the principles of minimizing overall maintenance costs and maximizing maintenance space utilization, construct an optimal objective function model for maintenance layout planning;

[0095] S4: Introducing Singer chaotic mapping and golden sine strategy to improve the subtractive average optimization algorithm, so as to enhance the diversity and global convergence of the population and overcome the problem that the traditional subtractive average optimization algorithm is prone to getting trapped in local optima.

[0096] S5: Based on the improved subtractive average optimization algorithm, the maintenance layout planning model is optimized and solved. Through multiple iterations of training, the optimal location of the maintenance components of the hydropower unit and the overall layout optimization scheme are obtained.

[0097] In step S1 provided in this embodiment of the invention, the digital processing of the maintenance component information involves decomposing the equipment into tree-like components and breaking down the maintenance information of each component into maintenance tools, instruments, precautions, dimensions, and weight, etc.; after encoding, a corresponding relational data table is formed.

[0098] In step S2 of this embodiment of the invention, the single-step planar space search specifically refers to the following: the maintenance plane refers to the area in the layout space where unit components can be maintained; taking the shortest side of the maintenance part as the step size v, the entire plane is scanned step by step downwards and to the right, starting from the upper left corner, to find all suitable spaces for maintenance; in the free area, the hydropower unit components can move continuously to determine the available maintenance area; the result of the single-step search algorithm is a list of available maintenance areas in the current search plane.

[0099] Step S3 provided in this embodiment of the invention includes the following sub-steps:

[0100] 1) The optimal objective function for comprehensive maintenance is established as follows:

[0101]

[0102] In the formula, i represents different maintenance parts in different hydropower unit areas, j represents different maintenance spaces, and c ij This indicates the cost of transporting the repaired parts, d ij f represents the distance the parts are transported. ij S represents the number of parts to be moved. t Let F represent the minimum area utilization rate, which is the maintenance optimal planning function, i.e., the weighted sum of the minimum maintenance and handling cost and the minimum area utilization rate. l1 and l2 are weighting factors, and l1+l2=1, in order to obtain the minimum value.

[0103] 2) The length constraints of the parts to be inspected are as follows:

[0104]

[0105] In the formula, z k z represents the width of the maintenance area k. k(n+1) This represents the length of the (n+1)th component under maintenance. This represents the sum of the lengths of the n components to be inspected in the inspection area k;

[0106] 3) The width constraint conditions for the parts under inspection are:

[0107]

[0108] In the formula, w k w represents the width of the maintenance area k. k(n+1) This represents the width of the (n+1)th maintenance component. This represents the sum of the widths of the n maintenance components arranged in maintenance area k;

[0109] 4) Formula for calculating the x-axis of the component under maintenance:

[0110]

[0111] In the formula, x ki Z represents the ordinate of the i-th component under maintenance in maintenance area k. ki This represents the length of the i-th component in the maintenance area k.

[0112] 5) Formula for calculating the ordinate of the component under maintenance:

[0113] y ki =max[y k3 ,y k2 ,y k1 ...y kn (5)

[0114] In the formula, y ki This represents the ordinate of the i-th component under maintenance in maintenance area k.

[0115] The specific steps of the subtraction average optimization algorithm in step S4 provided in this embodiment of the invention are as follows:

[0116] 1) Randomly initialize population locations

[0117] x i,d =lb d +r i,d ·(ub d -lb d (6)

[0118] x i,d Represents the current optimal position, ub d lb d r represents the upper and lower bounds of the optimization of decision variable d. i,d A random number within the interval [1,2];

[0119] 2) Update the agent position using the arithmetic mean position of the population members at the t-th iteration of the search agent. Based on the v-subtraction between search agent B and search agent A, it is defined as:

[0120]

[0121] In the formula, Let F(A) and F(B) represent random data vectors of dimension m, and let F(A) and F(B) represent the fitness values ​​of individuals A and B in the population.

[0122] 3) The position update formula is:

[0123]

[0124] In the formula, N is the total number of populations, and r i A random number in the interval [0,1]. For the new position after displacement update, F i This represents the objective function value.

[0125] The specific method for introducing the Singer chaotic mapping optimization subtraction flat optimization algorithm in step S4 of the present invention is as follows:

[0126] The mathematical formula for the Singer chaotic map is as follows:

[0127]

[0128] In the formula: mod is the modulo operation, which calculates the remainder when two numbers are divided; t is the dimension of the solution, representing the current iteration number. This represents the position of the i-th individual in the t-th iteration; This represents the new population position after the chaotic mapping;

[0129] Initializing the dung beetle population location using chaotic values ​​generated by the Singer mapping generates a uniform and random initial population, which can increase population diversity and thus help the SABO algorithm to accelerate convergence in subsequent optimization processes.

[0130] In step S4, the golden sine algorithm is introduced to optimize the subtractive averaging algorithm. The specific method is as follows:

[0131] The mathematical formula for the golden sine algorithm is as follows:

[0132]

[0133] In the formula: X represents the position of the i-th individual in the t-th iteration. bLet e1 be a random number in the range [0, 2π], e2 be a random number in the range [0, π], a be an initial value of -π, b be an initial value of π, g1 be the golden ratio, and k1 and k2 be coefficients containing the golden ratio.

[0134] The Golden Sine Algorithm (Gold-SA) is an iterative optimization method based on the sine function, often used to search for the extreme points of a function in two-dimensional space. The Gold-SA algorithm has a strong global search capability by sequentially accessing all values ​​of the sine function. At the same time, the introduction of the golden ratio makes it also have a strong search capability in the vicinity of the optimal solution sought in each iteration.

[0135] In step S4, the fitness pair function is designed based on the improved subtractive averaging optimization algorithm: the optimal handling cost and area utilization rate of the repaired parts are used as the combined optimization objectives, and the fitness calculation formula for each individual in the population is as follows:

[0136]

[0137] In the formula, i represents different maintenance parts in different hydropower unit areas, j represents different maintenance spaces, and c ij This indicates the cost of transporting the repaired parts, d ij f represents the distance the parts are transported. ij S represents the number of parts to be moved. t f represents the minimum area utilization rate. i This represents the fitness of each individual in the population;

[0138] Step S5 includes a combined optimization objective of optimal handling cost and area utilization rate for the repaired parts, and includes the following sub-steps:

[0139] 1) Coding principle: Adopt the numerical coding rule, and directly encode the disassembled and repaired parts with numbers in numerical format;

[0140] 2) Set the ISABO population size N, the total number of iterations to T, and set i = 1 and t = 1;

[0141] 3) Introduce Singer chaotic mapping to randomly generate the initial search population position;

[0142] 4) Evaluate the objective function based on the initial search population: Update the population position using the golden sine algorithm according to equation (11) during the iteration process;

[0143] 5) Calculate the fitness value of the new population according to equation (12);

[0144] 6) Replace the old population location with a new population that has better fitness, and generate a new population location;

[0145] 7) Repeat steps 4)-6) until the termination condition is met, and determine the optimal layout plan.

[0146] In step S5, the optimal solution of the model is calculated based on the improved subtraction optimization algorithm to obtain a new generation of population until the algorithm converges and the iteration value tends to stabilize or no longer changes significantly.

[0147] like Figure 2 As shown in the figure, an embodiment of the present invention provides a hydropower unit maintenance component layout optimization system based on a subtraction average optimization algorithm, comprising:

[0148] The digital processing module is used to classify and number various maintenance and disassembly components according to the actual mechanical structure of the hydropower unit, and to digitize the relevant maintenance component information to obtain sample data of hydropower unit component structure.

[0149] The search module is used to search for the unused space in the power plant for maintenance of hydropower units using a single-step planar search method.

[0150] A module is constructed to build an optimal objective function model for maintenance layout planning, based on the principles of minimizing overall maintenance costs and maximizing maintenance space utilization.

[0151] The module introduces Singer chaotic mapping and the golden sine strategy to improve the subtractive average optimization algorithm, so as to enhance the diversity and global convergence of the population and overcome the problem that the traditional subtractive average optimization algorithm is prone to getting trapped in local optima.

[0152] The iterative training module is used to optimize the maintenance layout planning model based on the improved subtractive average optimization algorithm. Through multiple iterative training, the optimal location of the maintenance components of the hydropower unit and the overall layout optimization scheme are obtained.

[0153] Another object of the present invention is to provide a computer device, the computer device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the hydropower unit maintenance component layout optimization method based on the subtraction average optimization algorithm.

[0154] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the steps of the hydropower unit maintenance component layout optimization method based on the subtraction average optimization algorithm.

[0155] Another objective of this invention is to provide an information data processing terminal for implementing the hydropower unit maintenance component layout optimization system based on the subtraction average optimization algorithm.

[0156] A system for optimizing the layout of maintenance components in hydropower units based on the subtraction averaging optimization algorithm includes:

[0157] Specific implementation of the present invention:

[0158] This invention provides a method for optimizing the overall layout of hydropower unit maintenance based on an improved genetic algorithm, comprising the following steps:

[0159] S1: Based on the actual mechanical structure of the hydropower unit, classify and number its various maintenance and disassembly components, digitize the relevant maintenance component information, and obtain sample data of hydropower unit component structure.

[0160] As shown in Table 1, based on the actual structure of the hydropower unit, each maintenance and disassembly component is classified and numbered, and the maintenance information is digitized. The equipment is disassembled into a tree structure composed of parts, and the maintenance information of the parts is further broken down into maintenance tools, instruments, precautions, and dimensions and weights, and a relational data table is generated through coding.

[0161] Table 1 Dimensions of each unit component

[0162] serial number name long Width serial number name long Width 1 Top cover 4.2 4.2 8 sleeve 2.3 1.8 2 Auxiliary rotor 1.6 1.6 9 Claw arm 1.8 1.9 3 auxiliary stator 1.4 1.4 10 Guide vanes 2.6 3.9 4 rack 5 5 11 Bottom ring 3.6 3.6 5 rack 4.1 4.1 12 Water-conducting tiles 2.4 2.5 6 Rotor 4.5 4.5 13 Twin Arm 1.5 1.7 7 cover plate 2.1 1.2 14 Rotary wheel 4.5 4.5

[0163] S2: The maintenance space of the hydropower unit is searched using a single-step planar search method;

[0164] like Figure 3 The maintenance plane refers to the area in the layout space where unit components can be maintained. Using the shortest side of the component to be maintained as the step size v, the entire plane is scanned step-by-step downwards and to the right, starting from the top left corner, to find all suitable spaces for maintenance. Within the free area, the hydropower unit components can be moved continuously to determine available maintenance areas. The result of the single-step search algorithm is a list of available maintenance areas in the currently searched plane.

[0165] In this embodiment of the invention, the hydroelectric power plant area is 1550m². 2 The maintenance space was divided into six areas using the free space plane search method. Each maintenance area is as follows: Figure 4 As shown.

[0166] S3: Based on the principle of minimizing overall maintenance costs and maximizing area utilization, construct an optimal objective function model for maintenance layout planning;

[0167] 1) The optimal objective function for comprehensive maintenance is established as follows:

[0168]

[0169] In the formula, i represents different maintenance parts in different hydropower unit areas, j represents different maintenance spaces, and c ij This indicates the cost of transporting the repaired parts, d ij f represents the distance the parts are transported. ij S represents the number of parts to be moved. t Let F represent the minimum area utilization rate, which is the maintenance optimal planning function, i.e., the weighted sum of the minimum maintenance and handling cost and the minimum area utilization rate. l1 and l2 are weighting factors, and l1+l2=1. The minimum value is obtained.

[0170] 2) The length constraints of the parts to be inspected are as follows:

[0171]

[0172] In the formula, z k z represents the width of the maintenance area k. k(n+1) This represents the length of the (n+1)th component under maintenance. This represents the sum of the lengths of the n components to be inspected in the inspection area k.

[0173] 3) The width constraint conditions for the parts under inspection are:

[0174]

[0175] In the formula, w k w represents the width of the maintenance area k. k(n+1) This represents the width of the (n+1)th maintenance component. This represents the sum of the widths of the n maintenance components arranged in maintenance area k;

[0176] 4) Formula for calculating the x-axis of the component under maintenance:

[0177]

[0178] In the formula, x ki Z represents the ordinate of the i-th component under maintenance in maintenance area k. ki This represents the length of the i-th component in the maintenance area k.

[0179] 5) Formula for calculating the ordinate of the component under maintenance:

[0180] y ki =max[y k3 y k2 y k1 ...y ka ]

[0181] In the formula, y ki This represents the ordinate of the i-th component under maintenance in maintenance area k.

[0182] S4: The Singer chaotic mapping and the golden sine strategy are introduced to improve the subtractive averaging optimization algorithm, so as to enhance the diversity and global convergence of the population and overcome the problem that the traditional subtractive averaging optimization algorithm is prone to getting trapped in local optima.

[0183] S5: Based on the improved subtractive average optimization algorithm, the maintenance layout planning model is optimized and solved. Through multiple iterations of training, the optimal location of the maintenance components of the hydropower unit and the overall layout optimization scheme are obtained.

[0184] As shown in Table 2, the improved subtractive average optimization algorithm is used to solve the model by selecting individuals with high fitness to calculate the spatial layout position, thereby obtaining the optimal convergent solution. It is then determined whether the new individual meets the predetermined termination condition. This process can be iterated continuously until the preset termination condition is reached. If the condition is met, the optimal solution is obtained; otherwise, step 5) is skipped to update the population and enter the next round of iteration.

[0185] Table 2 Results of Optimization of Maintenance Layout for Hydropower Units

[0186]

[0187] like Figure 6 As shown, the improved subtractive averaging optimization algorithm achieves the optimal convergence value in about 4 generations, while the traditional algorithm has a faster initial convergence but a slower overall convergence. The improved subtractive averaging optimization algorithm is superior to the traditional algorithm in both convergence speed and results.

[0188] Figure 6 The diagram shows a comparison of the convergence curves of the improved Subtractive Average Optimization (ISABO) algorithm and the traditional algorithm (SABO). Looking at the iteration count on the x-axis and the fitness value on the y-axis, ISABO converges to a stable value around the 4th iteration, while SABO only reaches the same convergence accuracy around the 10th iteration. This demonstrates that the improved algorithm significantly outperforms the traditional method in both convergence speed and result stability. This figure visually illustrates the improvement in optimization efficiency and accuracy achieved by this invention, providing reliable algorithmic support for subsequent optimization applications in maintenance layouts.

[0189] Figure 7 This is a two-dimensional layout diagram of the maintenance components optimized using the algorithm of this invention. The diagram clearly marks the placement areas for various equipment and disassembled parts, such as the generator stator, rotor, and auxiliary equipment. The two-dimensional layout allows for a direct observation of the rationality of the maintenance space division, ensuring that the spacing between equipment meets safety standards, while optimizing transportation and hoisting paths to avoid overlapping operations and reduced efficiency due to improper layout. This diagram provides a planar and quantitative intuitive basis for maintenance planning.

[0190] Figure 8 The demonstration showcases the optimized 3D layout of the maintenance components, highlighting the actual spatial placement of critical large components (such as rotors). Compared to a 2D plane, the 3D effect more intuitively displays the component volume, space occupation, and relative positional relationships, facilitating visual inspection and solution verification by technicians. 3D modeling allows for more accurate assessment of lifting paths, transportation routes, and operational safety margins, further ensuring the feasibility of the layout scheme.

[0191] Figure 9 This is the optimized 3D panoramic layout rendering, compared to... Figure 8 This partial view, covering the entire factory area, clearly shows the overall layout of Unit 1, Unit 2, and related disassembled components. The panoramic view allows for a comprehensive assessment of the coordination between various maintenance areas, ensuring that the disassembly, handling, and assembly of components do not interfere with each other. This image not only verifies the correctness of the algorithm optimization results but also provides an intuitive reference for on-site construction management and maintenance scheduling.

[0192] pass Figures 6 to 9 The comparison and demonstration can systematically reflect the advantages of the present invention: First, Figure 6 The improved algorithm demonstrates its superior convergence speed and computational accuracy; secondly, Figure 7 The two-dimensional layout effect clearly demonstrates the rationality of the optimized component placement; Figure 8 and Figure 9 The three-dimensional layout effect was then demonstrated from both local and panoramic perspectives, further verifying the feasibility of the layout scheme. It is evident that the maintenance component layout optimization method proposed in this invention not only improves planning efficiency and accuracy but also significantly shortens the maintenance preparation cycle, providing a quantifiable, visualized, and operable overall solution for hydropower unit maintenance.

[0193] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be included within the scope of protection of the present invention.

Claims

1. A method for optimizing the layout of maintenance components in hydropower units based on a subtractive averaging optimization algorithm, characterized in that, Includes the following steps: S1: Based on the actual mechanical structure of the hydropower unit, classify and number its various maintenance and disassembly components, digitize the relevant maintenance component information, and obtain hydropower unit component structure sample data. S2: The single-step planar search method is used to search for the unused space in the power plant for maintenance of hydropower units; S3: Based on the principles of minimizing maintenance costs and maximizing maintenance space utilization, construct an optimal objective function model for maintenance layout planning; S4: Introduce Singer chaotic mapping and golden sine strategy into the subtraction average optimization algorithm to enhance population diversity and global convergence ability. S5: Based on the improved subtractive average optimization algorithm, the maintenance layout planning model is optimized and solved. Through multiple iterations of training, the optimal location of the fixed layout of the maintenance components of the hydropower unit and the overall optimization scheme are obtained.

2. The method as described in claim 1, characterized in that, The digital processing in S1 includes: breaking down the equipment into tree-like components, and breaking down the maintenance information of each component into maintenance tools, instruments, precautions, dimensions and weight, etc., and then encoding them to form a relational data table.

3. A method for determining the maintenance space of a hydropower unit based on single-step planar search, characterized in that: Using the shortest side of the part to be inspected as the step size, scan downwards and to the right from the upper left corner of the inspection plane to find all suitable spaces for inspection and form a list of available inspection areas.

4. The method as described in claim 3, characterized in that, During the search process, when a component is in an empty area, it is allowed to move continuously and determine the available space for maintenance to improve search accuracy.

5. A method for constructing an objective function for the overhaul of hydropower units, characterized in that: An objective function is established with the comprehensive optimization index of the handling cost and area utilization rate of the maintenance parts. The length constraint, width constraint and the formula for calculating the horizontal and vertical coordinates of the maintenance parts are set to calculate the reasonable position of each part.

6. The method as described in claim 5, characterized in that, The objective function uses weighting factors to weight maintenance and handling costs and area utilization rate, and the sum of the weighting factors equals 1.

7. An improved subtractive averaging optimization algorithm, characterized in that: The population position is initialized using Singer chaotic mapping to improve the uniformity and randomness of the population; and the search position is updated using the golden sine strategy during the iteration process to improve the global search capability and local search accuracy.

8. The algorithm as described in claim 7, characterized in that, Singer's chaotic mapping generates chaotic values ​​through modular arithmetic, while the golden sine strategy refines the search around the optimal solution using a sine function and the golden ratio.

9. A system for optimizing the layout of maintenance components for hydropower units, characterized in that, include: The digital processing module is used to generate component structure sample data; The search module is used to determine available maintenance space using a single-step planar search method. The building module is used to establish the maintenance layout objective function; The optimization module is used to iteratively optimize the layout scheme by introducing the Singer chaotic mapping and the subtractive average optimization algorithm of the golden sine strategy. The output module is used to output the optimal fixed layout scheme.

10. The system as described in claim 9, characterized in that, During the iteration process, the optimization module evaluates the maintenance and handling costs and area utilization of individuals based on the fitness function, and replaces the old population with a new population with better fitness until convergence.

Images