A method and system for processing a super-large-area floor joint based on a genetic algorithm

Abstract

This invention relates to the field of ultra-large area flooring construction technology, and discloses a method and system for precise jointing treatment of ultra-large area floors based on a genetic algorithm. The method includes: acquiring multi-source measured data reflecting the construction conditions and state of the flooring; using the multi-source measured data as input, constructing a multi-objective model with jointing parameters as variables and comprehensive performance including crack resistance, smoothness, construction feasibility, and durability as optimization objectives; solving the model using a genetic algorithm to output an optimized jointing scheme containing joint coordinate information; locating and cutting the joints according to the joint coordinate information in the optimized jointing scheme; acquiring new measured data during construction and comparing it with the data or model prediction values ​​from step S1; and triggering adjustments to the optimized jointing scheme or the multi-objective model based on the comparison results. The beneficial effect of this invention is to improve the overall performance and service life of the flooring.

Description

Technical Field

[0001] This invention relates to the field of ultra-large area floor construction technology, specifically to a method and system for treating joints in ultra-large area floors based on a genetic algorithm. Background Technology

[0002] Large-area flooring (single plot area ≥ 1000㎡) is widely used in industrial plants, logistics warehouses, large plazas, and other scenarios. Joint treatment is a crucial step in controlling concrete cracking and ensuring the flatness and durability of the flooring. Traditional joint design typically relies on engineering experience or local finite element simulations, focusing on a single objective (such as crack resistance or ease of construction) while failing to consider multiple requirements such as structural stress, temperature stress, shrinkage deformation, construction costs, and long-term maintenance. This often leads to unintended consequences in actual projects, severely impacting the overall performance and service life of the flooring.

[0003] Current jointing methods have three prominent drawbacks: First, they cannot achieve a systematic balance between crack resistance, flatness, construction feasibility, and durability, often resulting in significant deviations in the economic or technical indicators of the solution; second, jointing solutions are usually static designs and cannot be dynamically adapted to changes in foundation conditions, concrete mix proportions, and construction environment, resulting in a cracking rate as high as 15%–20% in actual complex projects; third, jointing design is disconnected from the construction process, lacking a feedback and adjustment mechanism based on real-time monitoring data, making it difficult to correct the deviation between simulation and actual measurement, leading to frequent defects and high maintenance costs in the later stages. Summary of the Invention

[0004] Existing joint design focuses on a single objective, making it difficult to coordinate multiple requirements such as structural stress, temperature stress, shrinkage deformation, construction costs, and long-term maintenance. This often leads to unintended consequences in actual engineering projects, seriously affecting the overall performance and service life of the floor. The aim is to provide a method and system for treating joints in ultra-large areas of flooring based on genetic algorithms. It adopts a technical structure based on multi-source measured data-driven genetic algorithms for global optimization, enabling joint design to systematically coordinate multiple performance objectives such as crack resistance, flatness, construction feasibility, and durability. This overcomes the shortcomings of traditional experience-based or local simulation methods that focus on one aspect while neglecting another, thereby improving the overall performance and service life of the floor.

[0005] This invention is achieved through the following technical solution:

[0006] A method for precise jointing of ultra-large area floor slabs based on genetic algorithms includes the following steps: S1, acquiring multi-source measured data reflecting the construction conditions and state of the floor slab; S2, using the multi-source measured data as input, constructing a multi-objective model with jointing parameters as variables and comprehensive performance including crack resistance, flatness, construction feasibility, and durability as optimization objectives, and solving the model using a genetic algorithm to output an optimized jointing scheme containing joint coordinate information; S3, performing jointing location and cutting construction based on the joint coordinate information in the optimized jointing scheme; S4, during construction, acquiring new measured data and comparing it with the data or model prediction values ​​from step S1, triggering adjustments to the optimized jointing scheme or the multi-objective model based on the comparison results.

[0007] The beneficial effects of this invention are as follows: By employing a technical structure based on a multi-source measured data-driven genetic algorithm for global optimization, the joint design can systematically consider multiple performance objectives such as crack resistance, smoothness, construction feasibility, and durability, overcoming the shortcomings of traditional experience-based or local simulation methods that often overlook certain aspects. Furthermore, by using an algorithm to generate an optimized scheme including coordinates, and a closed-loop execution structure for precise construction based on these coordinates, the joint design is transformed from a static design into a dynamic instruction that guides on-site construction, achieving deep integration of design and construction and solving the long-standing problem of their disconnect. Additionally, by employing a structure that collects new data in real-time during construction and compares it with the initial model, the system possesses the ability to dynamically adapt to changes in the foundation, materials, and environment, continuously correcting deviations. This reduces the cracking rate from 15%–20% using traditional methods to an even lower level, improving the overall performance and service life of the flooring, and significantly reducing subsequent maintenance costs.

[0008] In some embodiments, the multi-source measured data in step S1 includes at least two of the following: foundation characteristic data, environmental climate data, concrete material performance data, and structural response monitoring data. Because the structure uses multi-source measured data containing at least two of these data as input, the optimization model can comprehensively and realistically reflect the specific mechanical and physicochemical environment of the floor, overcoming the shortcomings of traditional static design in adapting to complex actual conditions. This lays a reliable data foundation for generating jointing schemes that dynamically adapt to different site conditions.

[0009] In some embodiments, in step S2, the genetic algorithm uses chromosome encoding to represent the suture scheme. Each chromosome contains genes representing the suture spacing, suture depth, suture width, and suture plane coordinates. Because this structure encodes the suture spacing, suture depth, suture width, and suture plane coordinates as independent genes on chromosomes, complex engineering suture schemes can be transformed into digital models that the genetic algorithm can directly identify and iteratively optimize. This enables synchronous, globally automated optimization of multiple suture parameters, replacing outdated design methods that rely on human experience and struggle to coordinate multiple parameters.

[0010] In some embodiments, the optimization objective of the genetic algorithm is quantified by a fitness function F, wherein the fitness function F is: ,in: The crack resistance subfunction is calculated based on the design value of concrete tensile strength and the simulated maximum principal tensile stress. The flatness sub-function is calculated based on the height difference between adjacent blocks. This is a construction feasibility subfunction, calculated based on the estimated workload corresponding to the jointing scheme; The durability subfunction is calculated based on the bond strength of the joint filler material. , , , They are respectively , , , The corresponding weighting coefficients, and By employing a structure in which the fitness function F is formed by the weighted summation of four sub-functions—crack resistance, smoothness, construction feasibility, and durability—the optimization objective of the genetic algorithm is fully and quantitatively defined as the pursuit of a systematic balance in the overall performance of the floor. This resolves the core contradiction of traditional methods that focus on a single objective and neglect other aspects, achieving a unified optimization that balances economic efficiency and technical sophistication.

[0011] In some embodiments, the weighting coefficients satisfy: , , , Due to the adoption of crack resistance weighting Flatness weight The structure of specific weight coefficient ranges enables the optimization algorithm to reflect crack resistance priority while taking into account other core engineering logic in the global search, ensuring that the solution output by the algorithm is not only mathematically optimal, but also has the highest reliability and acceptability in engineering practice.

[0012] In some embodiments, the encoding range of the seam spacing gene is: 3m-4m for the main stress path, 4m-5m for the secondary path, and 5m-6m for the non-stressed area; the encoding range of the seam depth gene is: 8cm-10cm for the shallow layer, 10cm-25cm for the middle layer, and 25cm-30cm for the deep layer; and the encoding range of the seam width gene is: 3mm-5mm for the shallow layer, 5mm-8mm for the middle layer, and 8mm-12mm for the deep layer. Because the structure limits the values ​​of genes such as seam spacing, seam depth, and seam width to specific parameter ranges derived from engineering mechanics principles and construction experience, the search space of the genetic algorithm is constrained within an engineeringly feasible and reasonable range, significantly improving optimization efficiency, avoiding unrealistic and invalid solutions, and ensuring that the optimization results are both innovative and feasible on-site.

[0013] In some embodiments, in step S4, the condition for triggering the adjustment of the optimized jointing scheme or the multi-objective model is: the deviation between the newly acquired measured data and the initial input data exceeds 10%, or the deviation from the model prediction value exceeds 15%. Because the structure uses a deviation of measured data from the initial data or model prediction value exceeding a specific threshold (10% or 15%) as the triggering condition for adjustment, the system can intelligently identify key nodes of changes in construction conditions or model distortion, thereby automatically and promptly initiating the re-optimization process. This achieves a leap from static design to dynamic adaptation, effectively addressing the uncertainties of the construction environment and ensuring the real-time optimality of the scheme.

[0014] This invention also provides a system for the aforementioned method of precise jointing treatment of ultra-large area floor slabs based on genetic algorithms, comprising: a data interface module for receiving multi-source measured data; an intelligent optimization module, which incorporates the genetic algorithm and is used to run the multi-objective model based on input data and output an optimized jointing scheme; and a feedback control module for receiving subsequent data and comparing it with historical data or predicted values, and controlling whether the intelligent optimization module initiates iterative optimization. Due to the system structure consisting of the data interface, intelligent optimization, and feedback control modules, the entire process of data acquisition, algorithm optimization, and construction feedback can run automatically on an integrated hardware and software platform, realizing an upgrade at the jointing point from relying on discrete, disconnected manual processes to a continuous, intelligent closed-loop control system.

[0015] In some embodiments, the data source accessed by the data interface module includes at least two of the following: foundation survey equipment, environmental sensors, concrete laboratory systems, and on-site monitoring sensor networks. Because the data interface module can access multiple heterogeneous data sources such as foundation survey equipment and environmental sensors, the system possesses powerful on-site data fusion capabilities. It can directly interface with existing digital equipment on modern construction sites, eliminating information silos and providing real-time and rich input for the intelligent optimization module, thereby enhancing the system's practicality and ease of deployment.

[0016] In some embodiments, a scheme output module is also included, used to output the optimized jointing scheme in a BIM model or construction drawing format containing coordinate information. Because the scheme output module outputs the optimized jointing scheme in a BIM model or construction drawing format, the digital scheme generated by the algorithm can be seamlessly integrated with the next stage of construction drawing delivery and on-site construction work, ensuring that the optimization intent can be accurately and losslessly transmitted and executed, thus solving the problem of design-construction disconnect.

[0017] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0018] By employing a technology structure based on a genetic algorithm driven by multi-source measured data for global optimization, the joint design can systematically coordinate multiple performance objectives such as crack resistance, smoothness, construction feasibility, and durability, overcoming the shortcomings of traditional experience-based or local simulation methods that often overlook certain aspects. Furthermore, the use of an algorithm to generate an optimized scheme including coordinates, coupled with a closed-loop execution structure for precise construction based on these coordinates, transforms the joint design from a static design into a dynamic instruction that guides on-site construction, achieving deep integration of design and construction and resolving the long-standing disconnect between the two. Additionally, the system's ability to dynamically adapt to changes in foundation, materials, and environment during construction, and to continuously correct deviations, reduces the cracking rate from 15%–20% using traditional methods to an even lower level, improving the overall performance and service life of the flooring and significantly reducing subsequent maintenance costs. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0020] Figure 1 This is a flowchart of the present invention.

[0021] The attached diagram shows the markings and corresponding component names: Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of this invention are only for explaining this invention and are not intended to limit this invention.

[0023] Throughout this specification, references to "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "an embodiment," "an example," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0024] In the description of this invention, the terms "front", "rear", "left", "right", "up", "down", "vertical", "horizontal", "high", "low", "inner", and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the scope of protection of this invention.

[0025] The terms "first," "second," etc., used in this invention are merely for clarity of description and are not intended to limit any order or emphasize importance. Furthermore, the term "connection" as used herein, unless otherwise specified, can refer to a direct connection or an indirect connection via other components.

[0026] Example 1

[0027] like Figure 1 As shown, this embodiment provides a method for precise jointing of ultra-large area floor slabs based on genetic algorithms, including the following steps: S1, acquiring multi-source measured data reflecting the construction conditions and state of the floor slab; S2, using the multi-source measured data as input conditions, constructing a multi-objective model with jointing parameters as variables and comprehensive performance including crack resistance, flatness, construction feasibility, and durability as optimization objectives, and solving the model using a genetic algorithm to output an optimized jointing scheme containing joint coordinate information; S3, performing jointing location and cutting construction based on the joint coordinate information in the optimized jointing scheme; S4, during construction, acquiring new measured data and comparing it with the data or model prediction values ​​from step S1, triggering adjustments to the optimized jointing scheme or the multi-objective model based on the comparison results, and when the triggering conditions are met, the system automatically substitutes the new data into the model from step S2 for iterative optimization and outputs an updated jointing scheme for subsequent construction.

[0028] Specifically, the joint positioning and cutting construction in step S3 includes: importing the joint coordinate information in the optimized jointing scheme into the construction surveying and setting out system (such as a total station or BIM setting out robot), and setting out on the work surface; construction personnel operate the cutting equipment to carry out joint cutting operations according to the setting out marks.

[0029] Since the multi-source measured data collected in step S1 originates from different devices and systems, their data formats, dimensions, sampling frequencies, and spatiotemporal references vary. Therefore, preprocessing is required before they can be used as unified input for the genetic algorithm optimization model. The preprocessing process includes three main steps: data cleaning, data fusion, and data formatting. The specific process is as follows:

[0030] Data cleaning: Identifying and processing outliers and missing values ​​in the raw data. Outliers are identified using statistical methods (such as the Laida criterion) or threshold ranges set based on domain knowledge, and then removed or corrected. For missing data, imputation is performed using forward imputation, linear interpolation, or prediction methods based on historical patterns of similar data, depending on the type of missing data.

[0031] Data fusion: Unifying cleaned multi-source data onto the same spatiotemporal reference. Time reference fusion: Unifying the timestamps of all data to absolute time (e.g., UNIX timestamps) and aligning the data through interpolation or aggregation using a preset fixed time interval (e.g., 1 hour) as the reference. Spatial reference fusion: Transforming data with spatial location information (e.g., foundation survey point data, sensor placement data) to the same coordinate system of the construction area (i.e., the BIM model coordinate system). For point data, continuous field data can be generated through spatial interpolation (e.g., Kriging interpolation).

[0032] Data formatting: The fused data is organized into a standardized input matrix that can be directly read by the genetic algorithm model. Each row of this matrix represents the construction scenario corresponding to a jointing scheme to be optimized, and each column represents an input feature variable (e.g., the foundation bearing capacity, average ambient temperature, and 28-day tensile strength of concrete in the construction block corresponding to that row). All numerical features are normalized (e.g., min-max normalization) before matrix construction, transforming them to the [0,1] interval to eliminate dimensional differences and improve the convergence speed and stability of the algorithm. After the above preprocessing, a standardized dataset with a clear structure and reliable quality is obtained, which serves as the direct input for constructing and solving the multi-objective optimization model in step S2.

[0033] In some embodiments, the multi-source measured data in step S1 includes at least two of the following: foundation characteristic data, environmental climate data, concrete material performance data, and structural response monitoring data. Because the structure uses multi-source measured data containing at least two of these data as input, the optimization model can comprehensively and realistically reflect the specific mechanical and physicochemical environment of the floor, overcoming the shortcomings of traditional static design in adapting to complex actual conditions. This lays a reliable data foundation for generating jointing schemes that dynamically adapt to different site conditions.

[0034] Specifically, the foundation characteristic data are collected from engineering geological survey reports and in-situ tests. The specific equipment and methods used include obtaining cone tip resistance and sidewall friction through static cone penetration tests (CPT); obtaining hammer blow counts through standard penetration tests (SPT); and obtaining natural density, water content, compression modulus, internal friction angle, and cohesion of the soil through laboratory geotechnical tests. The characteristic values ​​of the foundation bearing capacity are determined through plate load tests or by calculating the above soil parameters according to national standards (such as the "Code for Design of Building Foundations" GB 50007). The above survey and test results are compiled into structured data and used as input parameters for the soil constitutive relations and boundary conditions in the algorithm model.

[0035] Environmental climate data is collected from microclimate monitoring stations set up at the construction site and historical and real-time data from local meteorological stations. Specific data collection equipment and methods include: continuous monitoring using on-site temperature and humidity sensors to record changes in air temperature, relative humidity, and surface temperature, particularly data during the critical age period after concrete pouring. Anemometers and solar radiation sensors are used to collect data to assess the rate of moisture evaporation from the concrete surface. Sensor data can be wirelessly transmitted to a central database via Internet of Things (IoT) technology, or manually recorded and entered into the system at regular intervals.

[0036] The data on concrete material properties are collected from concrete mix design reports, laboratory standard tests, and on-site testing of specimens cured under the same conditions. Specific data collection equipment and methods include: obtaining accurate water-cement ratio, cement dosage, admixture type and dosage, and aggregate gradation from the commercial concrete plant. Mechanical and deformation properties: compressive / tensile strength: strength development curves are obtained by testing standard cubic specimens or axially tensioned specimens using a laboratory compression testing machine. (Values ​​are thus determined). Elastic modulus and Poisson's ratio: obtained using a universal testing machine equipped with a strain measurement device. Shrinkage and creep: long-term observation of standard specimens using a length ratio meter or a concrete shrinkage and creep tester. Heat of hydration: temperature rise curves obtained using a concrete hydration heat measuring instrument or through a semi-adiabatic temperature rise test.

[0037] The structural response monitoring data is collected from pre-embedded / installed sensing systems in the constructed floor slab areas or test sections. Specific data acquisition equipment and methods include: strain and stress: fiber optic grating (FBG) sensors or vibrating wire strain gauges are pre-embedded in the concrete to monitor internal strain in real time and convert it to stress using constitutive relations. Deformation and displacement: a laser scanner (LiDAR) is used to scan large areas of surface flatness and deformation; high-precision displacement gauges (LVDTs) are installed at critical joint edges to monitor crack opening or misalignment. The measured values ​​can be obtained from this. Temperature field: Thermocouples or distributed fiber optic temperature measurement systems (DTS) are arranged at different depths inside the concrete to monitor the hydration heat temperature rise and internal temperature gradient. Data feedback: All sensors automatically and continuously record data through a data acquisition instrument and transmit it to the central processing system, forming the data source for the dynamic feedback module.

[0038] In some embodiments, in step S2, the genetic algorithm uses chromosome encoding to represent the suture scheme. Each chromosome contains genes representing the suture spacing, suture depth, suture width, and suture plane coordinates. Because this structure encodes the suture spacing, suture depth, suture width, and suture plane coordinates as independent genes on chromosomes, complex engineering suture schemes can be transformed into digital models that the genetic algorithm can directly identify and iteratively optimize. This enables synchronous, globally automated optimization of multiple suture parameters, replacing outdated design methods that rely on human experience and struggle to coordinate multiple parameters.

[0039] In some embodiments, the optimization objective of the genetic algorithm is quantified by a fitness function F, wherein the fitness function F is: ,in: The crack resistance subfunction is calculated based on the design value of concrete tensile strength and the simulated maximum principal tensile stress. The flatness sub-function is calculated based on the height difference between adjacent blocks. This is a construction feasibility subfunction, calculated based on the estimated workload corresponding to the jointing scheme; The durability subfunction is calculated based on the bond strength of the joint filler material. , , , They are respectively , , , The corresponding weighting coefficients, and By employing a structure in which the fitness function F is formed by the weighted summation of four sub-functions—crack resistance, smoothness, construction feasibility, and durability—the optimization objective of the genetic algorithm is fully and quantitatively defined as the pursuit of a systematic balance in the overall performance of the floor. This resolves the core contradiction of traditional methods that focus on a single objective and neglect other aspects, achieving a unified optimization that balances economic efficiency and technical sophistication.

[0040] Specifically, the crack resistance sub-function The calculation formula is: in This is the design value for the tensile strength of concrete (e.g., 2.01 MPa for C30). The maximum principal tensile stress is calculated using a mechanical model based on the multi-source measured data, and when hour, .

[0041] The crack resistance subfunction F1 The maximum principal tensile stress is obtained by inputting the foundation property data (as boundary constraints), concrete material property data (as material constitutive parameters), and environmental climate data (as temperature loads) acquired in step S1 into a three-dimensional finite element model established in general structural mechanics analysis software. Those skilled in the art will know that this type of analysis is a standard technique in civil engineering, allowing for the selection of appropriate models for stress simulation based on the actual engineering conditions.

[0042] The flatness sub-function The calculation formula is: ,in, To estimate the height difference between adjacent blocks based on the jointing scheme, and when At that time, take .

[0043] The construction feasibility subfunction The calculation formula is: ,in, As the benchmark quantity of work, The estimated workload corresponding to the current jointing scheme, and when At that time, take .

[0044] The durability sub-function The calculation formula is: ,in, To design the bond strength, To determine the estimated bond strength based on the filler material selected according to the jointing scheme, and when At that time, take .

[0045] In some embodiments, the weighting coefficients satisfy: , , , Due to the adoption of crack resistance weighting Flatness weight The structure of specific weight coefficient ranges enables the optimization algorithm to reflect crack resistance priority while taking into account other core engineering logic in the global search, ensuring that the solution output by the algorithm is not only mathematically optimal, but also has the highest reliability and acceptability in engineering practice.

[0046] In some embodiments, the encoding range of the seam spacing gene is: 3m-4m for the main stress path, 4m-5m for the secondary path, and 5m-6m for the non-stressed area; the encoding range of the seam depth gene is: 8cm-10cm for the shallow layer, 10cm-25cm for the middle layer, and 25cm-30cm for the deep layer; and the encoding range of the seam width gene is: 3mm-5mm for the shallow layer, 5mm-8mm for the middle layer, and 8mm-12mm for the deep layer. Because the structure limits the values ​​of genes such as seam spacing, seam depth, and seam width to specific parameter ranges derived from engineering mechanics principles and construction experience, the search space of the genetic algorithm is constrained within an engineeringly feasible and reasonable range, significantly improving optimization efficiency, avoiding unrealistic and invalid solutions, and ensuring that the optimization results are both innovative and feasible on-site.

[0047] S2. Detailed Implementation of the Genetic Algorithm Optimization Process: The specific implementation process of the genetic algorithm is as follows:

[0048] (1) Chromosome encoding and population initialization: According to the aforementioned encoding rules and range, N sets (e.g., N=150) of chromosomes that meet the constraints are randomly generated to form the initial population.

[0049] (2) Fitness function calculation: For each chromosome in the population (i.e. a splitting scheme), calculate its fitness value F according to the aforementioned formula.

[0050] (3) Genetic manipulation:

[0051] Selection: A combination of roulette wheel selection and elite retention strategy is employed. First, the top 20% of individuals with the highest fitness in the current population are directly retained to the next generation (elite retention). Then, the remaining 80% of individuals are selected by forming a roulette wheel based on their fitness values ​​as a percentage of the total population fitness. Selection is carried out by randomly rotating the roulette wheel until the population size is reached.

[0052] Crossover: Single-point crossover is performed on the selected individuals. Two parent individuals are randomly selected, and a gene position is randomly chosen (e.g., only the suture spacing gene or the suture depth gene). The parameter values ​​corresponding to this gene position are exchanged to generate two offspring individuals. The crossover probability typically ranges from 0.6 to 0.9. Based on verification from numerous engineering examples, setting it to 0.8 achieves the best balance between exploring new solution spaces and preserving desirable traits, making it the preferred solution of this invention.

[0053] Mutation: The offspring individuals after crossover are mutated with a small probability, typically ranging from 0.05 to 0.10. Preferably, for example, this probability is set to 0.08, which effectively maintains population diversity while avoiding disruption of already established optimal solutions. During mutation, a gene is randomly selected and randomly perturbed within its allowed value range, with the perturbation amplitude not exceeding 10% of the gene's value range.

[0054] (4) Iteration Termination: Repeat the fitness calculation, selection, crossover, and mutation operations described above to form iterative evolution. The algorithm terminates when any of the following conditions are met: the rate of change of the optimal fitness value in the population for G consecutive generations (e.g., G=5) does not exceed δ (e.g., (or the total number of iterations reaches a preset maximum number of generations (e.g., 50 generations). When the algorithm terminates, it outputs the stitching scheme corresponding to the chromosome with the highest fitness value in each generation of the population, as the optimal stitching scheme. This scheme includes complete parameters such as stitch spacing, stitch depth, stitch width, and stitch position plane coordinates, and can automatically generate corresponding BIM visualization drawings.

[0055] In some embodiments, in step S4, the condition for triggering the adjustment of the optimized jointing scheme or the multi-objective model is: the deviation between the newly acquired measured data and the initial input data exceeds 10%, or the deviation from the model prediction value exceeds 15%. Because the structure uses a deviation of measured data from the initial data or model prediction value exceeding a specific threshold (10% or 15%) as the triggering condition for adjustment, the system can intelligently identify key nodes of changes in construction conditions or model distortion, thereby automatically and promptly initiating the re-optimization process. This achieves a leap from static design to dynamic adaptation, effectively addressing the uncertainties of the construction environment and ensuring the real-time optimality of the scheme.

[0056] Example 2

[0057] This embodiment 2 provides a system for the aforementioned method of precise jointing treatment of ultra-large area floor slabs based on genetic algorithms. The system includes: a data interface module for receiving multi-source measured data; an intelligent optimization module with the built-in genetic algorithm for running the multi-objective model based on input data and outputting an optimized jointing scheme; and a feedback control module for receiving subsequent data and comparing it with historical data or predicted values, controlling whether the intelligent optimization module initiates iterative optimization. Due to the system structure consisting of the data interface, intelligent optimization, and feedback control modules, the entire process of data acquisition, algorithm optimization, and construction feedback can run automatically on an integrated hardware and software platform, achieving an upgrade at the jointing point from relying on discrete, disconnected manual processes to a continuous, intelligent closed-loop control system.

[0058] In some embodiments, the data source accessed by the data interface module includes at least two of the following: foundation survey equipment, environmental sensors, concrete laboratory systems, and on-site monitoring sensor networks. Because the data interface module can access multiple heterogeneous data sources such as foundation survey equipment and environmental sensors, the system possesses powerful on-site data fusion capabilities. It can directly interface with existing digital equipment on modern construction sites, eliminating information silos and providing real-time and rich input for the intelligent optimization module, thereby enhancing the system's practicality and ease of deployment.

[0059] Specifically, foundation investigation equipment can include static cone penetration test (CPT), standard penetration test (SPT), and plate load test equipment. Environmental sensors can include temperature and humidity sensors, anemometers, solar radiation sensors, and on-site microclimate monitoring stations. Concrete laboratory systems can utilize compression testing machines, universal testing machines, length ratio meters, hydration heat measuring instruments, and their data management systems (LIMS). On-site monitoring sensor networks can employ IoT monitoring systems composed of fiber optic grating sensor networks, vibrating wire strain gauges, laser scanners, and high-precision displacement gauges. Data interface modules can interface with the aforementioned specific equipment or their data management systems (such as Laboratory Information Management Systems (LIMS) or IoT cloud platforms) via wired (e.g., RS485, Ethernet) or wireless (e.g., LoRa, 4G / 5G) communication protocols to automatically or semi-automatically acquire formatted multi-source measured data.

[0060] In some embodiments, a scheme output module is also included, used to output the optimized jointing scheme in a BIM model or construction drawing format containing coordinate information. Because the scheme output module outputs the optimized jointing scheme in a BIM model or construction drawing format, the digital scheme generated by the algorithm can be seamlessly integrated with the next stage of construction drawing delivery and on-site construction work, ensuring that the optimization intent can be accurately and losslessly transmitted and executed, thus solving the problem of design-construction disconnect.

[0061] It should be noted that the specific equipment and systems used to acquire foundation characteristic data, environmental climate data, concrete material performance data, and structural response monitoring data in this embodiment can be obtained using existing equipment. For example, foundation investigation equipment may include static cone penetrometers, standard penetration test equipment, etc.; environmental sensors may include temperature and humidity sensors, anemometers, etc.; concrete laboratory systems may include information management systems integrating various material testing machines; and on-site monitoring sensor networks may refer to Internet of Things (IoT) monitoring systems composed of fiber optic grating sensors, displacement gauges, etc. Those skilled in the art will understand that any similar equipment or system capable of achieving the corresponding data acquisition functions falls within the scope of this invention.

[0062] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A genetic algorithm-based super-large-area floor precise jointing treatment method, characterized in that, Includes the following steps: S1. Obtain multi-source measured data reflecting the construction conditions and status of the floor; S2. Using the multi-source measured data as input, construct a multi-objective model with joint parameters as variables and comprehensive performance including crack resistance, flatness, construction feasibility and durability as optimization objectives. Then, use a genetic algorithm to solve the model and output an optimized jointing scheme containing joint coordinate information. S3. Based on the joint coordinate information in the optimized jointing scheme, perform joint positioning and cutting construction; S4. During construction, new measured data are acquired and compared with the data or model prediction values ​​in step S1. Based on the comparison results, adjustments are triggered to the optimized jointing scheme or the multi-objective model.

2. The genetic algorithm-based precise jointing method for super large area floor, according to claim 1, characterized in that, The multi-source measured data in step S1 includes at least two of the following: foundation characteristic data, environmental climate data, concrete material performance data, and structural response monitoring data.

3. The genetic algorithm-based method for precise joint treatment of super-large area floor according to claim 1, characterized in that, In step S2, the genetic algorithm uses chromosome encoding to characterize the suture scheme. The chromosome contains genes that respectively characterize the suture spacing, suture depth, suture width, and suture plane coordinates.

4. The method for precise jointing of ultra-large area floor slabs based on genetic algorithm according to claim 1, characterized in that, The optimization objective of the genetic algorithm is quantified by a fitness function F, which is: ,in: The crack resistance subfunction is calculated based on the design value of concrete tensile strength and the simulated maximum principal tensile stress. The flatness sub-function is calculated based on the height difference between adjacent blocks. This is a construction feasibility subfunction, calculated based on the estimated workload corresponding to the jointing scheme; The durability subfunction is calculated based on the bond strength of the joint filler material. , , , They are respectively , , , The corresponding weighting coefficients, and .

5. The method for precise jointing of ultra-large area floor slabs based on genetic algorithm according to claim 4, characterized in that, The weighting coefficients satisfy: , , , .

6. The method for precise jointing of ultra-large area floor slabs based on genetic algorithm according to claim 4, characterized in that, The coding range of the suture spacing gene is: 3m-4m in the main stress path, 4m-5m in the secondary path, and 5m-6m in the non-stressed area; The coding range of the suture depth gene is: shallow layer 8cm-10cm, middle layer 10cm-25cm, and deep layer 25cm-30cm; The coding range of the suture width gene is: 3mm-5mm in the superficial layer, 5mm-8mm in the middle layer, and 8mm-12mm in the deep layer.

7. The method for precise jointing of ultra-large area floor slabs based on genetic algorithm according to claim 1, characterized in that, In step S4, the condition for triggering the adjustment of the optimized seam splitting scheme or the multi-objective model is: the deviation between the newly acquired measured data and the initial input data exceeds 10%, or the deviation from the model prediction value exceeds 15%.

8. A system for the precise jointing treatment method for ultra-large area floor slabs based on genetic algorithms as described in any one of claims 1-7, characterized in that, include: The data interface module is used to access multi-source measured data; The intelligent optimization module, which incorporates the genetic algorithm, is used to run the multi-objective model based on the input data and output an optimized seam splitting scheme. The feedback control module is used to receive subsequent data and compare it with historical data or predicted values, and control whether the intelligent optimization module starts iterative optimization.

9. The system according to claim 8, characterized in that, The data interface module accesses at least two of the following data sources: foundation exploration equipment, environmental sensors, concrete laboratory systems, and on-site monitoring sensor networks.

10. The system according to claim 8, characterized in that, It also includes a scheme output module, which is used to output the optimized jointing scheme in the form of a BIM model or construction drawing containing coordinate information.

Images