Hybrid encoding and genetic operation method and system for pipeline support hanger arrangement optimization

Abstract

This invention provides a hybrid coding and genetic operation method and system for optimizing the layout of pipe supports and hangers. The method includes: S1, determining the pipe segments to be optimized and combining the optimized pipe segments to form an optimization range; S2, selecting an appropriate optimization mode according to engineering requirements and design stage; S3, performing coding operations for each optimized pipe segment, and the combination of codes for all pipe segments forms a complete chromosome coding structure for the optimization range; S4, generating an initial parent population based on the chromosome coding structure, and performing genetic operations through crossover and mutation to generate offspring individuals; S5, decoding the offspring individuals, performing simulation analysis, screening and constructing a new generation population; S6, repeating the evolutionary process until a preset termination condition is met. This invention uses real number coding combined with integer coding, and introduces natural number index coding to establish a mapping relationship with the coding, and designs matching chromosome crossover and mutation operation rules to achieve efficient genetic operations on the coded chromosomes.

Description

Technical Field

[0001] This invention relates to the field of pipeline system support and hanger arrangement in nuclear power plants, and particularly to a hybrid coding and genetic operation method and system for optimizing pipeline support and hanger arrangement. Background Technology

[0002] In existing technologies, although the arrangement of supports and hangers in nuclear power plant piping systems is determined by the initial design, it is usually necessary to conduct piping mechanical analysis to ensure safety, and adjust the arrangement of pipe supports based on the analysis results. This process involves repeated iterations until the mechanical calculation results for all operating conditions meet the limits and specifications. The number of supports and hangers in a piping system is enormous, and their arrangement is a key factor affecting the pipe's stress level, vibration characteristics, thermal expansion displacement, and seismic performance.

[0003] Traditional mechanical analysis relies on engineers manually adjusting the arrangement of supports and hangers based on experience, which is inefficient and makes it difficult to obtain a globally optimized arrangement. In recent years, intelligent optimization algorithms, such as genetic algorithms and particle swarm optimization, have been increasingly used for support and hanger arrangement optimization. When solving pipeline support and hanger optimization problems, optimization variables are usually represented by chromosomes in the form of genetic codes. Genetic operations such as crossover and mutation drive population evolution. Combined with a decoding mechanism, the chromosome codes are mapped to a physical model for simulation evaluation, thereby generating a support and hanger arrangement scheme that satisfies multiple optimization objectives.

[0004] Therefore, adopting an efficient genetic coding scheme that matches the characteristics of the engineering problem and implementing corresponding chromosome crossover and mutation genetic operations is of great significance for improving optimization efficiency and solution quality. Since the pipeline support optimization problem consists of the position, quantity, type, and adjustment strategy of the supports, most of the optimization algorithms in related studies use simple binary or real number encoding, without fully considering the complex operations such as "type, position" and "deletion, addition, and movement" of the supports.

[0005] In view of this, the inventors of this application have designed a hybrid coding and genetic operation method and system for optimizing the layout of pipe supports and hangers, in order to overcome the above-mentioned technical problems. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art, which is that the arrangement of pipe supports and hangers is manually adjusted based on experience, resulting in low efficiency and difficulty in obtaining a globally optimized arrangement scheme. The present invention provides a hybrid coding and genetic operation method and system for optimizing the arrangement of pipe supports and hangers.

[0007] The present invention solves the above-mentioned technical problems through the following technical solution:

[0008] A hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers, characterized in that the hybrid coding and genetic operation method includes the following steps:

[0009] S1. Identify the pipe segments that need to be optimized, combine the optimized pipe segments, and form the optimization range;

[0010] S2. Based on the engineering requirements and design stage, select the appropriate optimization mode, including the reconfiguration of support and hanger optimization mode and the fine-tuning of support and hanger optimization mode;

[0011] S3. Perform coding operations for each optimized pipe segment, and the coding combination of all pipe segments forms the complete chromosome coding structure of the optimization range;

[0012] Step S3 in the reconfiguration support optimization mode includes:

[0013] S 31 Remove existing supports and hangers between the starting nodes of the pipe segment to be optimized, and generate multiple candidate installation positions on the pipe segment based on the minimum support and hanger spacing constraint;

[0014] S 32 1. Configure an optional support type at each of the candidate installation locations;

[0015] S 33 The location of the support and hanger is represented by a real number code, and the code value is the ratio of the axial distance of the support and hanger installation position from the starting node of the pipe section to the total length of the pipe section;

[0016] S 34 Integer codes are used to identify the type of support and hanger;

[0017] S 35 The real number code and integer code of each pipe segment to be optimized constitute the hybrid coding data structure of the pipe segment to be optimized, and the hybrid coding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range;

[0018] Step S3 in the fine-tuning support optimization mode includes:

[0019] S 31’ The original design supports and hangers are retained as the basis, and their positions are encoded with real numbers, while the operations of the supports and hangers at their positions are encoded with integers.

[0020] S 32’ The real number code and integer code of each pipe segment to be optimized constitute the hybrid coding data structure of the pipe segment to be optimized, and the hybrid coding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range;

[0021] S4. Generate an initial parent population based on the chromosome coding structure, and perform genetic operations on the parent population through crossover and mutation to generate offspring individuals.

[0022] S5. Decode and map offspring individuals to update the finite element model of pipe supports and hangers, call finite element software for simulation analysis, calculate objective function values ​​and evaluate constraints, and screen and construct a new generation of population.

[0023] S6. Repeat the evolution process until the preset termination condition is met, and output the optimal support and hanger arrangement scheme that satisfies the constraints.

[0024] According to an embodiment of the present invention, step S1 includes:

[0025] S 11 Obtain the original finite element analysis model and calculation results of the target pipeline system;

[0026] S 12 Select at least one pipe segment that needs to be optimized as the optimization target, and all selected pipe segments together constitute the optimization scope.

[0027] According to an embodiment of the present invention, step S3 further includes: establishing a support / hanger position index and a support / hanger type or support / hanger operation index, both of which are numbered using natural numbers starting from 0, and the position index and the type or operation index maintain a one-to-one correspondence in the encoding sequence.

[0028] According to an embodiment of the present invention, the crossover operation in step S4 includes: randomly selecting two parent individuals and copying them to obtain two copies of the parent individuals;

[0029] Perform a crossover operation between the first parent individual and the copy of the second parent individual, and between the second parent individual and the copy of the first parent individual.

[0030] According to one embodiment of the present invention, the crossover operation includes:

[0031] Determine the number of intersection points: Select the minimum number of candidate support / hanger positions among the two parent individuals participating in the intersection operation;

[0032] Determine the intersection point location: Randomly select a set of exchange point location indices in the first parent individual. The location indexes are a non-repeating index sequence randomly selected from the candidate locations of the support and hanger, and serve as the source indexes; Randomly select a set of location indices in the clones of the second parent individual. The number of location indices is the same as the source indexes. The location indexes are a non-repeating index sequence randomly selected from the candidate locations of the support and hanger, and serve as the target indexes;

[0033] Perform crossover operation: Replace the real and integer codes of the support brackets at each source index position of the first parent individual with the code data at the corresponding target index position of the copy of the second parent individual, forming a new child individual;

[0034] In the same manner, a crossover operation is performed between the second parent individual and a copy of the first parent individual to generate another new child individual.

[0035] According to one embodiment of the present invention, a mutation operation is added to the offspring individuals generated by the crossover operation; in the reconstructed support and hanger optimization mode, the mutation operation includes the mutation types of adding supports and hangers, deleting supports and hangers, and moving supports and hangers; in the fine-tuning support and hanger optimization mode, the mutation operation includes the mutation types of deleting supports and hangers and moving supports and hangers.

[0036] According to one embodiment of the present invention, adding a support includes: randomly generating a new candidate position for the support and its corresponding support type; determining its insertion position in the chromosome sequence based on the real number encoding value of the support; and inserting the position code and type code of the support into the corresponding position to generate a new individual, that is, inserting it into the appropriate position of the chromosome according to the normalized value.

[0037] According to one embodiment of the present invention, deleting a support or hanger includes: randomly selecting an existing support or hanger from the current individual, and removing the position real number code and the corresponding type integer code of the support or hanger.

[0038] According to one embodiment of the present invention, the movable support includes: applying a preset or random position offset to the real number code of the selected support position, and synchronously updating the type integer code of the support to generate a new individual.

[0039] According to an embodiment of the present invention, step S5 includes:

[0040] S 51 Multiply the real number encoding representing the position of the support by the total length of the corresponding pipe segment to convert it into the actual axial coordinate;

[0041] S 52 Convert integer codes into specific support and hanger structural forms or support and hanger operations;

[0042] S 53 Generate structured modeling data, update the support and hanger layout, and update the finite element analysis model;

[0043] S 54 The pipeline mechanics analysis software is called to perform multi-condition simulation calculations. The objective function value is calculated based on the simulation results, and the engineering constraints are verified to select qualified individuals.

[0044] According to an embodiment of the present invention, step S6 includes:

[0045] S 61 The selected qualified individuals are used to form a new generation population, and the crossover, mutation, updating of the finite element analysis model, and simulation evaluation process are repeated.

[0046] S 62 Set the maximum number of generations;

[0047] S 63 The final output is the optimal support and hanger layout scheme that satisfies all engineering constraints.

[0048] The present invention also provides a hybrid coding and genetic operating system for optimizing the layout of pipe supports and hangers, characterized in that the hybrid coding and genetic operating system adopts the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers as described above.

[0049] The hybrid coding and genetic operating system includes: an initial data acquisition module, an optimization variable encoding module, a genetic operation module, an optimization variable decoding module, a finite element simulation calling module, and an output module;

[0050] The initial data acquisition module is responsible for providing the original finite element model and mechanical analysis data; the optimization variable encoding module constructs an initial population and a hybrid encoding structure based on the data; the genetic operation module performs crossover and mutation operations to generate a new generation of encoding sequences; the optimization variable decoding module reverse-engineers the new encoding and updates the finite element model; the finite element simulation calling module automatically drives the pipeline mechanics analysis software to perform simulation calculations and obtain the objective function value and constraint condition verification results; the genetic operation module selects and constructs a new generation of population based on the latest simulation results;

[0051] The various modules work together to form an automatic closed loop, and the process iterates until the convergence condition is met. Finally, the output module outputs the optimal support and hanger arrangement scheme.

[0052] The present invention also provides an electronic device, characterized in that the electronic device includes: a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the hybrid coding and genetic operation method for optimizing the arrangement of pipe supports and hangers as described above.

[0053] The present invention also provides a readable storage medium, characterized in that a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, it implements the hybrid coding and genetic operation method for optimizing the arrangement of pipe supports and hangers as described above.

[0054] The positive and progressive effects of this invention are as follows:

[0055] The present invention relates to a hybrid coding and genetic operation method and system for optimizing the layout of pipe supports and hangers. It uses real number coding to accurately represent the position coordinates of the supports and hangers, combines integer coding to characterize the support and hanger types, and introduces natural number index coding to establish a mapping relationship with the coding. Based on this, matching chromosome crossover and mutation operation rules are designed to achieve efficient genetic operation of the coded chromosomes.

[0056] The hybrid encoding and genetic operation method, by constructing a complete encoding, genetic, and decoding process, effectively supports the application of genetic optimization algorithms in the design of pipeline system support and hanger layout. It can significantly improve the rationality and economy of support and hanger layout and promote the in-depth application of intelligent optimization technology in nuclear power plant pipeline engineering. Attached Figure Description

[0057] The above and other features, properties and advantages of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings and embodiments, in which the same reference numerals always denote the same features, wherein:

[0058] Figure 1 This is a flowchart illustrating the pipe support and hanger layout optimization process in the hybrid coding and genetic operation method of the present invention.

[0059] Figure 2 This is a schematic diagram of the chromosome structure for reconstructing the optimized support and hanger pattern in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0060] Figure 3 This is a schematic diagram of the chromosome structure of the fine-tuning support optimization mode in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0061] Figure 4 This is a schematic diagram illustrating the generation of offspring during the crossover operation in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0062] Figure 5 This is a schematic diagram illustrating the addition of a support / hanger mutation operation in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers according to the present invention.

[0063] Figure 6 This is a schematic diagram of the deletion of support and hanger mutation operation in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0064] Figure 7 This is an operation diagram of the variation of moving supports in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0065] Figure 8This is a flowchart of the pipe support and hanger layout optimization based on the genetic optimization algorithm in the hybrid coding and genetic operation method for optimizing pipe support and hanger layout of the present invention.

[0066] Figure 9 This is a schematic diagram of the pipeline model before optimization in the hybrid coding and genetic operation method for optimizing the layout of pipeline supports and hangers of the present invention.

[0067] Figure 10 This is a schematic diagram of the optimized pipe model in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers of the present invention.

[0068] Figure 11 This is a schematic diagram showing the stress ratio before and after optimization in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers in this invention.

[0069] Figure 12 This is a schematic diagram of the model before the optimization of the number of pipe supports and hangers in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers of the present invention.

[0070] Figure 13 This is a schematic diagram of the optimized model for the number of pipe supports and hangers in the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers of the present invention. Detailed Implementation

[0071] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0072] Embodiments of the invention will now be described in detail with reference to the accompanying drawings. Preferred embodiments of the invention will now be described in detail, examples of which are shown in the drawings. Wherever possible, the same reference numerals will be used in all the drawings to denote the same or similar parts.

[0073] Furthermore, although the terminology used in this invention is selected from commonly known and used terms, some terms mentioned in this specification may have been selected by the applicant in his or her judgment, and their detailed meanings are explained in the relevant sections of the description herein.

[0074] Furthermore, the invention should be understood not only through the actual terminology used, but also through the meaning implied by each term.

[0075] like Figure 1 As shown, this invention discloses a hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers, which includes the following steps:

[0076] Step S1: Determine the pipe segments that need to be optimized, combine the optimized pipe segments, and form the optimization range.

[0077] Preferably, step S1 includes:

[0078] Step S 11 Obtain the original finite element analysis model and calculation results of the target pipeline system.

[0079] The finite element model preferably includes pipe geometric parameters, node information, and the current support and hanger layout scheme. The calculation results preferably include mechanical calculation results such as pipe stress, support and hanger load, pipe displacement, equipment connection load, valve acceleration, and through-component load under multiple working conditions.

[0080] Step S 12 Select at least one pipe segment that needs to be optimized as the optimization target, and all selected pipe segments together constitute the optimization scope.

[0081] Based on the results of the original finite element analysis model, one or more pipe segments requiring optimization are identified, and all selected pipe segments together constitute the optimization range. An objective function is constructed based on the mechanical analysis results, and engineering constraints meeting the specifications are set as the optimization direction for the genetic algorithm.

[0082] The objective function preferably includes one or a combination of minimizing stress, maximizing stress, minimizing the number of supports and hangers, minimizing load, and minimizing acceleration. The engineering constraints preferably include allowable stress limits, nozzle load limits, and acceleration limits under ASME or RCC-M standards.

[0083] Step S2: Based on the engineering requirements and design stage, select the appropriate optimization mode, including the reconfiguration support optimization mode and the fine-tuning support optimization mode.

[0084] Select the appropriate optimization mode based on project requirements and design phase:

[0085] If it is in the preliminary design or renovation stage and structural adjustments are allowed, then the reconfiguration support optimization mode can be selected to support the adjustment of the position, quantity, and type of supports, as well as the addition, deletion, movement, type change, and total number of supports.

[0086] If the project is in the construction solidification or commissioning phase and only minor adjustments are permitted, then the aforementioned fine-tuning support optimization mode should be selected. This mode allows for localized optimization based on the original design, including the movement and deletion of supports. In other words, while retaining most of the original supports, minor positional adjustments or localized reductions are made.

[0087] Step S3: Perform coding operations for each optimized tube segment to construct the chromosome coding structure.

[0088] Preferably, step S3 in the reconfiguration support and hanger optimization mode includes:

[0089] Step S31 Remove all existing supports and hangers between the starting nodes of the pipe segment to be optimized, set the minimum support and hanger spacing constraint according to the specification requirements (e.g., not less than 0.1 meters), and randomly generate multiple (e.g., N) candidate installation positions on the pipe segment.

[0090] Step S 32 Each of the candidate installation locations is configured with an optional support type.

[0091] The types mentioned include unidirectional constraint, bidirectional constraint, tridirectional constraint, or fixed constraint. The support and hanger types mentioned here primarily refer to the three types of rigid supports and hangers, and are only examples, not limitations. The support and hanger types can also include spring supports, damper supports, etc., with added support and hanger type numbers and associated design parameters. All types of support and hangers are within the scope of protection of this application.

[0092] Step S 33 The position of the support / hanger is represented by a real number encoding, where the encoded value is the ratio of the axial distance of the support / hanger installation position from the starting node of the pipe segment to the total length of the pipe segment. For example, the ratio ranges from [0,1]. Alternatively, the real number encoding of the support / hanger position can also be achieved by encoding the position offset relative to the previous support / hanger.

[0093] Step S 34 Integer codes are used to identify the type of support and hanger.

[0094] Step S 35 The real-number encoding and integer encoding of each pipe segment to be optimized constitute the hybrid encoding data structure of the pipe segment to be optimized, and the hybrid encoding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range.

[0095] Specifically, such as Figure 2 As shown, the preferred encoding rule is:

[0096] Location coding: Real number coding is used, which is the ratio of the axial distance of the support installation position from the starting node of the pipe segment to the total length of the pipe segment. The value of the ratio is preferably a real number in the interval [0,1]. For example, if a support is located at 60% of the total length of the pipe segment, its location code is 0.6.

[0097] Type encoding: Integer encoding is used, and the mapping relationship is as follows:

[0098] 0 → One-way constraint type;

[0099] 1 → Two-way constraint type;

[0100] 2 → Three-way constraint type;

[0101] 3 → Fixed constraint type;

[0102] Each support is represented by a pair of data: (real number encoding for position, integer encoding for type). Multiple supports are arranged in axial order to form the encoding sequence of the pipe segment. The encoding sequences of all optimized pipe segments are combined to form a complete chromosome structure.

[0103] Preferably, step S3 in the fine-tuning support optimization mode includes:

[0104] Step S 31’ The original design's supports and hangers are retained as a foundation. Their positions are encoded using real numbers, while operations on these supports and hangers are encoded using integers. The support and hanger positions are also encoded using a [0,1] normalized code. The specific encoding format is as follows: Figure 3 As shown.

[0105] In the fine-tuning support optimization mode, the pipe segment code consists of the original support position and operation type. The support position is a real number code, and the operation type is an integer code. The operation type includes moving the support and deleting the support.

[0106] Step S 32’ The real-number encoding and integer encoding of each pipe segment to be optimized constitute the hybrid encoding data structure of the pipe segment to be optimized, and the hybrid encoding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range.

[0107] Furthermore, step S3 also includes: establishing a support / hanger location index and a support / hanger type index or a support / hanger operation index. These indices are all numbered using natural numbers starting from 0 (i.e., encoded using natural numbers starting from 0), used for precise location of the support / hanger type and operation element in subsequent crossover and mutation operations. The location index and the type or operation index maintain a one-to-one correspondence in the encoding sequence.

[0108] The position index is used to identify the logical position of the support in the chromosome, supporting the location of the exchange point in the crossover operation and the addition, deletion and modification processing in the mutation operation.

[0109] Step S4: Generate an initial parent population based on the chromosome coding structure, and perform genetic operations on the parent population through crossover and mutation to generate offspring individuals.

[0110] For example, if the population size is set to P, then P independent individuals are randomly generated, and each individual represents a complete support and hanger arrangement scheme.

[0111] The number of individuals meets the preset population size, and the initial population is used as the parent population for the genetic algorithm. Individuals in the parent population are replicated, and offspring individuals are generated through crossover and mutation operations. Each offspring individual corresponds to a support / hanger arrangement scheme. Taking the reconstruction of the support / hanger pattern as an example, the following operations are performed on the parent individuals to generate offspring, such as... Figure 4 The diagram shows the generation of offspring during the crossover operation.

[0112] Preferably, the crossover operation in step S4 includes: randomly selecting two parent individuals (i.e., the first parent individual and the second parent individual), and recording them as parent 1 and parent 2. Then, replicating each of the two parent individuals (i.e., replicas of the first parent individual and the second parent individual), and recording them as parent 1 replica and parent 2 replica.

[0113] Perform a crossover operation between the first parent individual (i.e., parent 1) and the copy of the second parent individual (i.e., copy of parent 2), and perform a crossover operation between the second parent individual (i.e., parent 2) and the copy of the first parent individual (i.e., copy of parent 1).

[0114] like Figure 4 As shown, the crossover operation includes:

[0115] Determine the number of intersection points: Select the minimum number of candidate support / hanger positions between the two parent individuals participating in the intersection operation. For example, let the minimum value be k, such as... Figure 4 In this case, k is set to: k=4.

[0116] Determine the intersection point location: Randomly select a set of exchange point location indices in the first parent individual (i.e., parent 1). The location index is a non-repeating index sequence randomly selected from the candidate locations of the support bracket, and is used as the source index. The index order is not required to be continuous or ordered.

[0117] In the copy of the second parent individual (i.e., the copy of parent 2), a set of position indices is randomly selected. The number of position indices is the same as the source index. The position indices are a non-repeating index sequence randomly selected from the candidate positions of the support and hanger, and the index order is not required to be continuous or ordered. These indices are used as the target indexes.

[0118] For example, k position indices are randomly selected in parent 1 as source indices, and k target indices of different orders are randomly selected in the parent 2 copy.

[0119] Perform a crossover operation: Take the real and integer codes of the supports at each source index position of the first parent individual (i.e., parent 1) and replace them with the codes of the second parent's copy (i.e., parent 2 copy) at the corresponding target index positions. This essentially changes the candidate positions and types of the supports in parent 2 copy, forming a new child individual, recorded as child 1. Positions not replaced retain their original values.

[0120] In the same manner, a crossover operation is performed between the second parent individual (i.e., parent 2) and the copy of the first parent individual (i.e., the copy of parent 1) to generate another new child individual, which is recorded as child 2.

[0121] In addition, the crossover operation can also be performed as follows: the encoding sequences of the two parent individuals are divided into multiple blocks of the same length, and the blocks are rotated and crossed.

[0122] In the crossover operation, the hybrid coding and genetic operation method achieves multi-point heterogeneous gene fragment exchange by selecting disordered and discontinuous source and target indices between the parent and its replicas.

[0123] Subsequently, mutation operations are added to the offspring individuals generated by the crossover operation. In the reconstructed support / hanger optimization mode, the preferred mutation types include: adding supports / hangers, deleting supports / hangers, and moving supports / hangers. In the fine-tuning support / hanger optimization mode, the preferred mutation types include: deleting supports / hangers and moving supports / hangers.

[0124] like Figure 5 As shown, the preferred method for adding support and hanger mutation operation is to randomly generate a new support and hanger candidate position (satisfying the minimum spacing) and its corresponding support and hanger type, determine its insertion position in the chromosome sequence according to its real number encoding value, and insert the position code and type code of the support and hanger into the corresponding position to generate a new individual, that is, insert it into the appropriate position of the chromosome according to the normalized value.

[0125] like Figure 6 As shown, the preferred method for deleting a support / hanger mutation is to randomly select an existing support / hanger from the current individuals and remove its position real number code and corresponding type integer code.

[0126] like Figure 7 As shown, the preferred method for the mobile support mutation operation is to apply a preset or random position offset, such as a random offset within the range of [0,1], to the real number code of the selected support position, and simultaneously update its type integer code to generate a new individual.

[0127] The newly generated individuals constitute the offspring population, and each offspring individual corresponds to a candidate support and hanger arrangement scheme.

[0128] The above Figures 5 to 7 The variation operation shown applies only to the location and type of a single support / hanger, and is merely an example and not intended to be limiting. The variation operation can be applied to one or more supports / hangers; multiple supports / hangers selected randomly or sequentially by location are all within the scope of protection of this application.

[0129] In the mutation operation, newly added supports are inserted into the chromosome sequence in axial order according to their position encoding values, ensuring the physical rationality of the solution. This encoding and operation mechanism achieves coordinated optimization of the position, type, and quantity of supports, supporting multi-mode intelligent optimization from global reconstruction to local fine-tuning.

[0130] Step S5: Decode and map the offspring individuals to update the finite element model of the pipe support, call the finite element software to perform simulation analysis, calculate the objective function value and evaluate the constraints, and screen and construct a new generation of population.

[0131] Preferably, step S5 includes:

[0132] Step S 51 Multiply the real number encoding representing the position of the support by the total length of the corresponding pipe segment to convert it into the actual axial coordinate.

[0133] Step S 52 Convert integer codes into specific support and hanger structural forms or support and hanger operations.

[0134] Step S 53 Generate structured modeling data, update the support and hanger layout, and update the finite element analysis model (e.g., CAESAR II or Pipestress).

[0135] Step S 54 The system calls upon pipeline mechanics analysis software to perform multi-condition simulation calculations, including conditions such as self-weight, thermal expansion, and earthquakes. Based on the simulation results, key indicators are extracted to calculate the objective function value, verify engineering constraints, and screen qualified individuals.

[0136] Step S6: Repeat the evolution process until the preset termination condition is met, and output the optimal support and hanger arrangement scheme that satisfies the constraints.

[0137] Preferably, step S6 includes:

[0138] Step S 61 The selected qualified individuals are used to form a new generation population, and the crossover, mutation, updating of the finite element analysis model, and simulation evaluation process are repeated.

[0139] Step S 62 Set the maximum number of generations;

[0140] Step S 63 The final output is the optimal support and hanger layout scheme that satisfies all engineering constraints.

[0141] like Figure 8 The diagram shows a flowchart of support and hanger layout optimization based on the genetic optimization algorithm (NSGA-II fast non-dominated sorting genetic algorithm). It is assumed that the population size (N) is 20 individuals and the number of generations (E) is 100.

[0142] Population initialization: Generate 20 individuals, each of which calls the pipeline mechanics analysis software once, for a total of 20 initialization calls.

[0143] Assuming we enter the iterative cycle phase (generations 1-100), the iterative process for each generation is as follows:

[0144] Step 1: Generate 20 offspring through crossover mutation;

[0145] The second step is to call the pipeline mechanics analysis software once for each child generation;

[0146] Step 3: Parent generation (e.g., 20) + Child generation (e.g., 20) = 40 individuals;

[0147] Step 4: Select the 20 best ones from the 40 to enter the next generation;

[0148] Step 5: Each generation is called 20 times.

[0149] Based on the above description, the effectiveness of this application will be further described in detail through two specific examples.

[0150] Example 1: Stress ratio optimization

[0151] The pipeline model before optimization is as follows: Figure 9 As shown, the model fails the calculation case where the stress ratio in load condition 330 (self-weight + earthquake) exceeds 1. After adopting the method of this invention, the pipeline model optimized by the genetic algorithm is as follows: Figure 10 As shown. By Figure 10 It can be seen that the position and type of the supports and hangers have been optimized.

[0152] The stress ratio before and after optimization is as follows: Figure 11 As shown, the stress ratios for conditions 10 (self-weight), 15 (hydraulic test), and 330 (self-weight + earthquake) are significantly reduced, while the stress ratio for condition 321 (self-weight + thermal expansion) is slightly increased, but still meets the requirement of being less than 1.

[0153] Example 2: Optimization of the number of supports and hangers

[0154] like Figure 12The model shown has a stress ratio that meets the requirements of mechanical analysis, but the number of supports and hangers is excessive. For example... Figure 13 As shown, after optimization by the present invention, the number of supports and hangers is reduced from 7 to 1, while still meeting the mechanical stress ratio requirement.

[0155] The method proposed in this invention effectively solves the complex operational problems of "type, position" and "deletion, addition, and movement" in pipeline support optimization by introducing a hybrid coding mechanism and chromosome coding and chromosome genetic operation strategy for pipeline supports in nuclear power plants. It has good engineering application prospects and promotion value.

[0156] This invention presents a hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers. It uses real-number coding (e.g., real-number coding within the [0,1] interval) to accurately represent the position coordinates of the supports and hangers, combined with integer coding to represent support / hanger type information and operational information. These two elements constitute a hybrid coding data structure organized by pipe segment. Simultaneously, the hybrid coding and genetic operation method introduces natural number index coding to establish a coding mapping relationship. Based on this, matching chromosome crossover and mutation operation rules are designed, achieving efficient genetic operations on the coded chromosomes.

[0157] The hybrid encoding and genetic operation method effectively supports the application of genetic optimization algorithms in the design of pipeline system support and hanger layout by constructing a complete encoding-genetic-decoding process, significantly improving the rationality and economy of support and hanger layout, and promoting the in-depth application of intelligent optimization technology in nuclear power plant pipeline engineering.

[0158] The present invention also provides a hybrid coding and genetic operating system for optimizing the layout of pipe supports and hangers, which adopts the hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers as described above;

[0159] The hybrid coding and genetic operating system includes:

[0160] The initial data acquisition module is used to acquire the finite element model and results of the pipeline to be optimized.

[0161] A genetic algorithm engine module is used to obtain the optimal layout scheme. The genetic algorithm engine module includes:

[0162] Optimize the variable encoding module to generate a hybrid encoding structure;

[0163] The genetic operations module is used to perform crossover and mutation operations to update the hybrid coding structure;

[0164] The variable decoding module has been optimized to generate the updated finite element model.

[0165] The finite element simulation calling module is used to automatically perform mechanical simulations;

[0166] The output module is used to output the optimal layout scheme.

[0167] The modules work collaboratively to form an automated closed loop: the initial data acquisition module is responsible for providing the original finite element model and mechanical analysis data; the optimization variable encoding module constructs an initial population and a hybrid encoding structure based on the data; the genetic operation module performs crossover and mutation operations to generate a new generation of encoding sequences; the optimization variable decoding module reverse-engineers the new encoding and updates the finite element model; the finite element simulation calling module automatically drives the pipeline mechanics analysis software to perform simulation calculations and obtain the objective function value and constraint condition verification results; the genetic operation module selects and constructs a new generation of population based on the latest simulation results.

[0168] The above process is repeated until the convergence condition is met, and finally the output module outputs the optimal support and hanger arrangement scheme.

[0169] The present invention also provides an electronic device comprising: a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions being executed by the processor to implement the hybrid coding and genetic operation method for optimizing pipe support and hanger arrangement as described above.

[0170] The present invention also provides a readable storage medium on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements the hybrid coding and genetic operation method for optimizing the arrangement of pipe supports and hangers as described above.

[0171] In summary, the hybrid coding and genetic operation method and system for optimizing the layout of pipe supports and hangers of the present invention uses real number coding to accurately represent the position coordinates of the supports and hangers, combines integer coding to characterize the support and hanger types, and introduces natural number index coding to establish a mapping relationship with the coding. On this basis, matching chromosome crossover and mutation operation rules are designed to achieve efficient genetic operation of the coded chromosomes.

[0172] The hybrid encoding and genetic operation method, by constructing a complete encoding, genetic, and decoding process, effectively supports the application of genetic optimization algorithms in the design of pipeline system support and hanger layout. It can significantly improve the rationality and economy of support and hanger layout and promote the in-depth application of intelligent optimization technology in nuclear power plant pipeline engineering.

[0173] For those skilled in the art, the above disclosure is merely illustrative and does not constitute a limitation of this application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application and therefore remain within the spirit and scope of the exemplary embodiments of this application.

[0174] Furthermore, this application uses specific terms to describe embodiments of the application. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic related to at least one embodiment of the application. Therefore, it should be emphasized and noted that "an embodiment," "one embodiment," or "an alternative embodiment" mentioned twice or more in different locations in this specification do not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of the application can be appropriately combined.

[0175] Similarly, it should be noted that, in order to simplify the description of the embodiments disclosed in this application and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of the embodiments of this application sometimes combines multiple features into a single embodiment, drawing, or description thereof. However, this disclosure method does not imply that the subject matter of this application requires more features than those mentioned in the claims. In fact, the embodiments have fewer features than all the features of a single embodiment disclosed above. Some embodiments use numbers describing the number of components or attributes; it should be understood that such numbers used in the description of embodiments are modified in some examples by the terms "approximately," "about," or "generally."

[0176] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. A hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers, characterized in that, The hybrid coding and genetic operation method includes the following steps: S1. Identify the pipe segments that need to be optimized, combine the optimized pipe segments, and form the optimization range; S2. Based on the engineering requirements and design stage, select the appropriate optimization mode, including the reconfiguration of support and hanger optimization mode and the fine-tuning of support and hanger optimization mode; S3. Perform coding operations for each optimized pipe segment, and the coding combination of all pipe segments forms the complete chromosome coding structure of the optimization range; Step S3 in the reconfiguration support optimization mode includes: S 31 Remove existing supports and hangers between the starting nodes of the pipe segment to be optimized, and generate multiple candidate installation positions on the pipe segment based on the minimum support and hanger spacing constraint; S 32 1. Configure an optional support type at each of the candidate installation locations; S 33 The location of the support and hanger is represented by a real number code, and the code value is the ratio of the axial distance of the support and hanger installation position from the starting node of the pipe section to the total length of the pipe section; S 34 Integer codes are used to identify the type of support and hanger; S 35 The real number code and integer code of each pipe segment to be optimized constitute the hybrid coding data structure of the pipe segment to be optimized, and the hybrid coding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range; Step S3 in the fine-tuning support optimization mode includes: S 31’ The original design supports and hangers are retained as the basis, and their positions are encoded with real numbers, while the operations of the supports and hangers at their positions are encoded with integers. S 32’ The real number code and integer code of each pipe segment to be optimized constitute the hybrid coding data structure of the pipe segment to be optimized, and the hybrid coding data structure of all pipe segments to be optimized forms the complete chromosome structure of the optimization range; S4. Generate an initial parent population based on the chromosome coding structure, and perform genetic operations on the parent population through crossover and mutation to generate offspring individuals. S5. Decode and map offspring individuals to update the finite element model of pipe supports and hangers, call finite element software for simulation analysis, calculate objective function values ​​and evaluate constraints, and screen and construct a new generation of population. S6. Repeat the evolution process until the preset termination condition is met, and output the optimal support and hanger arrangement scheme that satisfies the constraints.

2. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 1, characterized in that, Step S1 includes: S 11 Obtain the original finite element analysis model and calculation results of the target pipeline system; S 12 Select at least one pipe segment that needs to be optimized as the optimization target, and all selected pipe segments together constitute the optimization scope.

3. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 1, characterized in that, Step S3 further includes: establishing a support / hanger position index and a support / hanger type or support / hanger operation index, both of which are numbered using natural numbers starting from 0, and the position index and the type or operation index maintain a one-to-one correspondence in the encoding sequence.

4. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 1, characterized in that, The crossover operation in step S4 includes: randomly selecting two parent individuals and copying them to obtain two copies of the parent individuals; Perform a crossover operation between the first parent individual and the copy of the second parent individual, and between the second parent individual and the copy of the first parent individual.

5. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 4, characterized in that, The crossover operation includes: Determine the number of intersection points: Select the minimum number of candidate support / hanger positions among the two parent individuals participating in the intersection operation; Determine the intersection point location: Randomly select a set of exchange point location indices in the first parent individual. The location indexes are a non-repeating index sequence randomly selected from the candidate locations of the support and hanger, and serve as the source indexes; Randomly select a set of location indices in the clones of the second parent individual. The number of location indices is the same as the source indexes. The location indexes are a non-repeating index sequence randomly selected from the candidate locations of the support and hanger, and serve as the target indexes; Perform crossover operation: Replace the real and integer codes of the support brackets at each source index position of the first parent individual with the code data at the corresponding target index position of the copy of the second parent individual, forming a new child individual; In the same manner, a crossover operation is performed between the second parent individual and a copy of the first parent individual to generate another new child individual.

6. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 4, characterized in that, Add mutation operations to the offspring individuals generated by the crossover operation; in the reconstructed support and hanger optimization mode, the mutation operations include the mutation types of adding supports and hangers, deleting supports and hangers, and moving supports and hangers; in the fine-tuning support and hanger optimization mode, the mutation operations include the mutation types of deleting supports and hangers and moving supports and hangers.

7. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 6, characterized in that, Adding supports includes: randomly generating a new candidate position for a support and its corresponding support type; determining its insertion position in the chromosome sequence based on the real number encoding value of the support; and inserting the position code and type code of the support into the corresponding position to generate a new individual, i.e., inserting it into the appropriate position of the chromosome according to the normalized value.

8. The hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers as described in claim 6, characterized in that, Deleting a support or hanger includes: randomly selecting an existing support or hanger from the current individuals, and removing the real number code of the position and the corresponding integer code of the type of the support or hanger.

9. The hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in claim 6, characterized in that, The movable support includes: applying a preset or random position offset to the real number code of the selected support's position, and synchronously updating the type integer code of the support to generate a new individual.

10. The hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers as described in claim 1, characterized in that, Step S5 includes: S 51 Multiply the real number encoding representing the position of the support by the total length of the corresponding pipe segment to convert it into the actual axial coordinate; S 52 Convert integer codes into specific support and hanger structural forms or support and hanger operations; S 53 Generate structured modeling data, update the support and hanger layout, and update the finite element analysis model; S 54 The pipeline mechanics analysis software is called to perform multi-condition simulation calculations. The objective function value is calculated based on the simulation results, and the engineering constraints are verified to select qualified individuals.

11. The hybrid coding and genetic operation method for optimizing the layout of pipe supports and hangers as described in claim 1, characterized in that, Step S6 includes: S 61 The selected qualified individuals are used to form a new generation population, and the crossover, mutation, updating of the finite element analysis model, and simulation evaluation process are repeated. S 62 Set the maximum number of generations; S 63 The final output is the optimal support and hanger layout scheme that satisfies all engineering constraints.

12. A hybrid coding and genetic operating system for optimizing the arrangement of pipe supports and hangers, characterized in that, The hybrid coding and genetic operating system adopts the hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in any one of claims 1-11; The hybrid coding and genetic operating system includes: an initial data acquisition module, an optimization variable encoding module, a genetic operation module, an optimization variable decoding module, a finite element simulation calling module, and an output module; The initial data acquisition module is responsible for providing the original finite element model and mechanical analysis data; the optimization variable encoding module constructs an initial population and a hybrid encoding structure based on the data; the genetic operation module performs crossover and mutation operations to generate a new generation of encoding sequences; the optimization variable decoding module reverse-engineers the new encoding and updates the finite element model; the finite element simulation calling module automatically drives the pipeline mechanics analysis software to perform simulation calculations and obtain the objective function value and constraint condition verification results; the genetic operation module selects and constructs a new generation of population based on the latest simulation results; The various modules work together to form an automatic closed loop, and the process iterates until the convergence condition is met. Finally, the output module outputs the optimal support and hanger arrangement scheme.

13. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the hybrid coding and genetic operation method for optimizing pipe support and hanger layout as described in any one of claims 1-11.

14. A readable storage medium, characterized in that, The program or instructions are stored on the readable storage medium, and when the program or instructions are executed by the processor, they implement the hybrid coding and genetic operation method for optimizing the arrangement of pipe supports and hangers as described in any one of claims 1-11.

Images