Inner floating disc splicing stress parameter optimization method and system

Abstract

The invention belongs to the technical field of welding stress control, and discloses an inner floating disc splicing stress parameter optimization method and system. Real-time working condition information such as the construction stage, the accumulated stress level, the overall structure rigidity and field environment parameters is combined with a dynamic adjustment mechanism of a stress optimization priority set; therefore, the problem that global optimization control is difficult to realize under multi-target conflict, construction stage evolution, cumulative stress change and field environment disturbance is solved, and the effect of realizing continuous balance and global optimization control among the targets in the whole construction period is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of welding stress control, in particular to an inner floating disc splicing stress parameter optimization method and system. BACKGROUND

[0002] The construction of large-scale petrochemical storage tanks is an important link in the industrial field, and the inner floating disc structure inside the tank is a key component to ensure safe operation of the tank and reduce medium evaporation. The inner floating disc is usually spliced by multiple prefabricated metal plates, and welding is a key connection process. However, the local high temperature during welding and subsequent cooling will inevitably introduce residual stress in the weld and its surrounding area. If not properly controlled, these residual stresses will directly affect the flatness and sealing performance of the inner floating disc, and may even cause structural cracking, thereby posing a serious safety hazard.

[0003] In order to effectively control the welding residual stress, a stress self-adaptive optimization system based on multi-sensor data fusion has been introduced in the prior art. The system usually deploys multiple sensors around the welding area, such as strain gauges for measuring local strain, infrared thermography for monitoring welding thermal cycle and cooling speed, and laser displacement sensors for capturing macro deformation of the structure. Based on the real-time data of these sensors, the system can evaluate the current stress state of the inner floating disc, and generate a set of recommended welding process parameters, such as welding current, welding voltage, welding speed and interpass temperature control threshold, etc., aiming to effectively control the residual stress.

[0004] However, in actual engineering practice, the welding stress control of the inner floating disc of the storage tank is not a single objective. When adjusting the welding parameters, the existing optimization system needs to consider multiple performance indicators that are interrelated and may conflict with each other, such as minimizing peak stress, maximizing stress distribution uniformity, maximizing welding efficiency, minimizing energy consumption, and minimizing structural deformation. There is often a trade-off between these objectives, making it difficult to achieve optimal results simultaneously.

[0005] In addition, the splicing of the inner floating disc of the storage tank is a dynamic and long-term process, and the overall structural characteristics and stress state of the inner floating disc continue to evolve during this long construction period. At different construction stages, the importance of each optimization objective changes. For example, during the initial plate connection stage, the overall stiffness of the inner floating disc is relatively small, and the control of local stress allows a certain flexibility, so the importance of optimizing welding efficiency may be higher to ensure overall processing progress; while the residual stress of the completed weld continuously accumulates, the importance of optimizing peak stress and stress distribution uniformity significantly increases during the later stages such as the intermediate structure forming stage and the final sealing and correction stage, to ensure structural integrity. The existing technology is difficult to dynamically adjust the priority of each optimization objective according to the evolution of the construction stage.

[0006] Meanwhile, the dynamic changes of the field environment conditions further aggravate the complexity of the multi-objective optimization strategy. Under different environment conditions, such as the changes of the environment temperature, humidity or wind speed, the same welding parameter adjustment will produce different stress control effects, thereby changing the actual trade-off relationship between the objectives. The prior art lacks a mechanism for evaluating the difficulty of achieving each optimization objective according to the real-time environment parameters and adjusting the optimization strategy accordingly.

[0007] In summary, the existing stress optimization scheme based on multi-sensor fusion data is difficult to achieve the continuous balance and global optimal control among the objectives in the entire construction period when facing the multiple conflict objectives of the welding stress control and the dynamic influences of the construction phase evolution, cumulative stress changes and field environment disturbances in the long-term splicing operation of the inner floating roof of a large oil and chemical storage tank, and lacks a mechanism for autonomously adjusting the optimization strategy according to the real-time working conditions, which has become a technical problem to be solved urgently.

[0008] In view of the above problems, the prior art needs to be improved. SUMMARY

[0009] The purpose of the present application is to provide an inner floating roof splicing stress parameter optimization method and system, which can dynamically adjust the priority of each optimization objective according to the real-time working conditions such as the construction phase, cumulative stress level, overall structural stiffness and field environment parameters, and generate optimized welding process parameters accordingly, thereby effectively solving the problems of multi-objective conflict balance and lack of dynamic adaptability of the optimization strategy in the prior art, and significantly improving the quality and safety of the inner floating roof splicing.

[0010] In a first aspect, the present application provides an inner floating roof splicing stress parameter optimization method for optimizing welding process parameters according to real-time working conditions in the splicing construction operation of a storage tank inner floating roof, the steps of which include: A1. According to the current construction phase, an initial stress optimization priority set corresponding thereto is obtained; the stress optimization priority set contains the priorities corresponding to multiple optimization objectives; A2. Local strain data and temperature field data of the welding area, macroscopic deformation data of the inner floating roof and field environment parameters are obtained; A3. The current cumulative stress level and overall structural stiffness of the inner floating roof are evaluated according to the local strain data, the temperature field data and the macroscopic deformation data; A4. If the cumulative stress level exceeds a preset stress level threshold, the priorities of each optimization objective in the initial stress optimization priority set are adjusted to reduce the risk of structural failure; A5. If the preset interval of the overall structural stiffness changes, the initial stress optimization priority set is switched to a stress optimization priority set matched with the changed preset interval; A6. According to the field environment parameters, evaluate the difficulty of achieving each optimization target; A7. According to the effective stress optimization priority set and the difficulty of achieving, generate welding process parameters for welding operation; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set or the switched stress optimization priority set.

[0011] In a second aspect, the application provides an inner floating plate splicing stress parameter optimization system for optimizing welding process parameters according to real-time working conditions in the splicing construction work of the inner floating plate of the storage tank, which comprises: An initial priority acquisition module is configured to acquire a corresponding initial stress optimization priority set according to the current construction stage; the stress optimization priority set comprises priorities corresponding to multiple optimization targets; A data acquisition module is configured to acquire local strain data and temperature field data of the welding area, macroscopic deformation data of the inner floating plate and field environment parameters; A state evaluation module is configured to evaluate the current cumulative stress level and overall structural rigidity of the inner floating plate according to the local strain data, the temperature field data and the macroscopic deformation data; A priority adjustment module is configured to adjust the priorities of the optimization targets in the initial stress optimization priority set to reduce the risk of structural failure when the cumulative stress level exceeds a preset stress level threshold; A priority switching module is configured to switch the initial stress optimization priority set to a stress optimization priority set matched with the changed preset interval when the preset interval of the overall structural rigidity changes; A difficulty evaluation module is configured to evaluate the difficulty of achieving each optimization target according to the field environment parameters; A parameter generation module is configured to generate welding process parameters for welding operation according to the effective stress optimization priority set and the difficulty of achieving; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set or the switched stress optimization priority set.

[0012] Beneficial effects: The inner floating plate splicing stress parameter optimization method and system provided by the application combine real-time working condition information such as construction stage, cumulative stress level, overall structural rigidity and field environment parameters with the dynamic adjustment mechanism of the stress optimization priority set, thereby solving the problem of difficult global optimization control under multi-target conflict, construction stage evolution, cumulative stress change and field environment disturbance, and achieving the effect of realizing continuous balance and global optimization control among targets in the entire construction cycle. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 The flow chart of the inner floating disc splicing stress parameter optimization method provided by the embodiments of the present application.

[0014] Figure 2 The structural schematic diagram of the inner floating disc splicing stress parameter optimization system provided by the embodiments of the present application.

[0015] Label explanation: 1, initial priority acquisition module; 2, data acquisition module; 3, state evaluation module; 4, priority adjustment module; 5, priority switching module; 6, difficulty evaluation module; 7, parameter generation module. DETAILED DESCRIPTION

[0016] The technical model in the present application will be described clearly and completely in combination with the drawings in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The components of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] It should be noted that: similar labels and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0018] Reference Figure 1 The present application provides an inner floating disc splicing stress parameter optimization method, which is used in the splicing construction work of the inner floating disc of the storage tank, and optimizes the welding process parameters according to the real-time working conditions. The steps of the method include: A1. According to the current construction stage, a corresponding initial stress optimization priority set is obtained; the stress optimization priority set contains the priority of each optimization target; A2. Local strain data and temperature field data of the welding area, macroscopic deformation data of the inner floating disc, and site environment parameters are obtained; A3. According to the local strain data, the temperature field data and the macroscopic deformation data, the current cumulative stress level and the overall structural rigidity of the inner floating disc are evaluated; A4. If the cumulative stress level exceeds the preset stress level threshold, the priority of each optimization target in the initial stress optimization priority set is adjusted to reduce the risk of structural failure; A5. If the preset interval of the overall structural stiffness changes, switch the initial stress optimization priority set to a stress optimization priority set matching the changed preset interval; A6. According to the field environment parameters, evaluate the difficulty of achieving each optimization target; A7. According to the effective stress optimization priority set and the difficulty of achieving, generate a welding process parameter for the welding operation; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set, or the switched stress optimization priority set.

[0019] Wherein, the stress optimization priority set refers to a set of targets for guiding the optimization of welding process parameters and their quantitative representation of relative importance. This set can be implemented by weight vector, priority list or fuzzy logic rule set, for example, assigning numerical weights to each optimization target as priority, mainly to provide dynamic decision basis for multi-objective optimization.

[0020] Wherein, the construction phase refers to a specific period in the inner pontoon splicing construction process with different structural characteristics and engineering emphases. This stage can be divided into predefined stages, mainly to reflect the influence of the evolution of the inner pontoon structure on the importance of optimization targets.

[0021] Wherein, the cumulative stress level refers to the overall quantitative state of internal residual stress of the inner pontoon after the current welding and cooling cycle. This level can be represented by stress concentration factor, average residual stress value or maximum principal stress value, mainly to evaluate the risk of structural failure.

[0022] Wherein, the overall structural stiffness refers to the ability of the inner pontoon to resist deformation under the current construction state. This stiffness can be represented by structural modal analysis results, deformation-to-load ratio or stiffness matrix eigenvalues calculated by finite element model, mainly to reflect the evolution of the inner pontoon structure with the construction process.

[0023] Wherein, the field environment parameters refer to external conditions that affect heat transfer and material properties in the welding site. This parameter can be represented by physical quantities such as ambient temperature, ambient humidity, and ambient wind speed, mainly to evaluate the difficulty of achieving each optimization target under actual working conditions.

[0024] Wherein, the optimization target refers to the performance effect desired in the inner pontoon splicing process. It is mainly to comprehensively measure the overall performance of the welding process.

[0025] The core innovation of the present application is that by combining the real-time working condition information such as the construction stage, the cumulative stress level, the overall structure stiffness and the site environment parameters with the dynamic adjustment mechanism of the stress optimization priority set, the problem of difficult to achieve global optimization control under the multi-objective conflict, construction stage evolution, cumulative stress change and site environment disturbance is solved, and the effect of achieving continuous balance and global optimization control between targets in the entire construction period is achieved.

[0026] Specifically, the method first acquires an initial stress optimization priority set according to the current construction stage, which reflects the importance of each optimization target under the current construction progress. Then, the system real-time acquires the local strain data of the welding area, the temperature field data, the macroscopic deformation data of the inner floating disc and the site environment parameters, which are the basis for evaluating the structure state and environmental influence. Based on these real-time data, the system evaluates the current cumulative stress level and the overall structure stiffness of the inner floating disc. If the cumulative stress level exceeds the preset threshold, the priority of the optimization target is dynamically adjusted to reduce the structure failure risk, for example, the priority of the stress control related target is increased. At the same time, if the preset interval of the overall structure stiffness changes, the system will switch to the stress optimization priority set matched with the new stiffness interval, ensuring that the optimization strategy is adapted to the structure evolution of the inner floating disc. In addition, the system also evaluates the difficulty of achieving each optimization target according to the site environment parameters, so as to more realistically balance the relationship between targets. Finally, considering the effective stress optimization priority set after dynamic adjustment and the difficulty of achieving each target, the system generates welding process parameters suitable for the current working condition to guide the actual welding operation. This mechanism ensures that the generation of welding process parameters can respond to the real-time structure state, potential risks and external environment, so as to achieve continuous balance and global optimization control between multiple conflicting targets.

[0027] Through the above scheme, the present application can effectively solve the problem that in the long-term splicing operation of the inner floating disc of a large petrochemical storage tank, it is difficult to achieve continuous balance and global optimization control between targets in the entire construction period when facing multiple conflicting targets of welding stress control and the dynamic influence of construction stage evolution, cumulative stress change and site environment disturbance. The method ensures that the welding process parameters can adapt to the changing working conditions by real-time monitoring and dynamic adjustment of the optimization strategy, thereby reducing the structure failure risk, improving the welding quality, optimizing the overall construction efficiency, and achieving effective control of the welding stress in a complex dynamic environment.

[0028] As a preferred embodiment, the scheme of the present application is implemented as follows: in the process of inner floating caisson splicing construction, the system first identifies the current construction stage, for example, when in the initial plate connection stage, the system retrieves a set of initial optimization priorities from the preset database, in which the weight of the welding efficiency maximization target is set to a higher value. During the welding operation, the local strain and temperature field data are obtained through the strain sensors and infrared thermography deployed in the welding area, while the overall deformation data of the inner floating caisson are obtained by laser displacement sensors. These data are combined with the material mechanics model and finite element analysis method to calculate the cumulative stress level and overall structural stiffness of the inner floating caisson in real time. For example, when the calculated maximum residual stress exceeds the preset threshold, the priority of the peak stress minimization and stress distribution uniformity maximization targets is automatically increased. At the same time, as more plates are welded, when the overall stiffness of the inner floating caisson transitions from the "flexible" interval to the "semi-rigid" interval, the system automatically switches to another set of preset optimization priorities, which pays more attention to the control of structural deformation; the stress optimization priority set corresponding to different preset intervals can be determined in advance based on expert experience or through historical data analysis, and form a query database, which is queried to determine the matching stress optimization priority set according to the changed preset interval. In addition, environmental sensors continuously monitor the temperature, humidity and wind speed on site, which are used to evaluate the difficulty of achieving each optimization target under the current conditions. Finally, considering the current dynamically adjusted optimization target priorities and the difficulty of achieving each target, and combining the preset welding process parameter constraints (for example, the adjustment range of welding current), a set of optimized welding current, welding voltage, welding speed and inter-pass temperature control threshold values are generated, which are sent to the welding equipment to guide the actual welding operation.

[0029] In some possible embodiments, the construction stage includes an initial plate connection stage, an intermediate structure forming stage, and a final sealing and correction stage; The plurality of optimization targets includes a peak stress minimization target, a stress distribution uniformity maximization target, a welding efficiency maximization target, an energy consumption minimization target, and a structural deformation minimization target; The priorities of the optimization targets in the initial stress optimization priority set corresponding to different construction stages are different, wherein the priority of the welding efficiency maximization target in the initial stress optimization priority set corresponding to the earlier construction stage is higher, and the priorities of the peak stress minimization target and the stress distribution uniformity maximization target in the initial stress optimization priority set corresponding to the later construction stage are higher.

[0030] Here, the construction phase is a time period with specific characteristics during the construction process of the inner floating platform, which is divided according to its structural form, welding progress and engineering requirements. It can be achieved by dividing the milestones in project management, dividing the structural integrity assessment nodes or dividing the cumulative weld length percentage.

[0031] Among them, the initial plate connection stage refers to the early stage of the construction of the inner floating platform, mainly for the preliminary connection between bulk plates and the construction of the basic framework. It can be achieved by positioning and spot welding the first batch of plates, or assembling and preliminary welding the main support structure.

[0032] Among them, the intermediate structure forming stage refers to the middle stage of the construction of the inner floating platform, which is based on the preliminary framework to carry out a large number of continuous welding of plates to form the main structure of the inner floating platform. It can be achieved by continuous welding of large area plates, or installation and welding of secondary support members.

[0033] Among them, the final sealing and correction stage refers to the later stage of the construction of the inner floating platform, mainly to complete the remaining weld connection, structure calibration and final quality inspection. It can be achieved by fine processing of the edge weld, or adjustment and solidification of the overall structure flatness.

[0034] Among them, the peak stress minimization target is to minimize the maximum local stress in the inner floating platform structure by optimizing the welding process parameters.

[0035] Among them, the stress distribution uniformity maximization target is to make the residual stress distribution in the inner floating platform structure as uniform as possible by optimizing the welding process parameters, avoiding local stress concentration.

[0036] Among them, the welding efficiency maximization target is to shorten the welding time as much as possible under the premise of ensuring the welding quality, and improve the welding amount per unit time.

[0037] Among them, the energy consumption minimization target is to minimize the consumption of resources such as electric energy and gas during the welding process.

[0038] Among them, the structure deformation minimization target is to control the overall shape and size deviation of the inner floating platform within the allowable range after welding by optimizing the welding process parameters.

[0039] The method specifies that the priorities of each optimization objective in the initial stress optimization priority set corresponding to different construction stages are different, and specifically indicates that the higher the construction stage, the higher the priority of the welding efficiency maximization objective, and the later the construction stage, the higher the priority of the peak stress minimization objective and the stress distribution uniformity maximization objective. In the initial plate connection stage, since the overall structural stiffness of the inner floating disc is relatively small, the tolerance to local stress is high, at this time, preferentially improving the welding efficiency helps to speed up the overall construction progress and shorten the construction period. As the construction enters the intermediate structure forming stage and the final sealing and correction stage, the overall structure of the inner floating disc gradually forms, and the residual stress of the completed welds accumulates, the requirement for structural integrity and flatness also increases. At this time, the optimization focus is shifted to peak stress minimization and stress distribution uniformity maximization, which can effectively control residual stress, reduce structural failure risk, and ensure the quality and safety of the final product.

[0040] Through the above technical solution, the method can realize accurate optimization of the welding process parameters in the inner floating disc splicing construction process. It solves the problem of lack of specific stage division, target definition and stage priority adjustment mechanism in the prior art, so that the acquisition of the initial stress optimization priority set no longer presents a generalization or static state. The method can accurately reflect the changes in structural characteristics, accumulated stress state and engineering demand of the inner floating disc at different construction periods, so as to realize continuous balance and global optimal control between targets during the entire construction period, especially effective switching between efficiency and structural integrity, thereby improving the quality and efficiency of the inner floating disc construction.

[0041] In some embodiments, in step A1, the initial stress optimization priority set associated with the construction stage identifier of the current construction stage can be directly retrieved from the preset stage information library according to the construction stage identifier.

[0042] In other embodiments, step A1 includes: A101. Obtain the construction stage identifier of the current construction stage; A102. Retrieve the reference initial stress optimization priority set associated with the construction stage identifier from the preset stage information library; A103. Obtain reference information of the current construction stage; the reference information includes at least one of structural integrity requirements, engineering progress requirements, and resource availability information; A104. Adjust the priority of each optimization objective in the reference initial stress optimization priority set according to the reference information to generate the corresponding initial stress optimization priority set.

[0043] The construction stage identifier can be a numerical code, a textual description, or any other symbol that uniquely identifies the current construction stage, and its role is to provide a clear context for the system to retrieve relevant information from the preset data.

[0044] The preset stage information library is a database that stores a set of baseline optimization priority configurations corresponding to different construction stages, which can exist in the form of tables, key-value pairs, or structured documents. Each stage identifier is associated with a set of predefined optimization target priority configurations. The baseline initial stress optimization priority configuration is a pre-set optimization target priority configuration for a specific construction stage without real-time condition modification, which represents the general optimization tendency of the stage and can be determined based on expert experience or historical data statistical analysis.

[0045] The reference information refers to real-time or near real-time data that affects the setting of optimization target priority in the current construction stage, including quality control requirements, safety risk assessment results, or environmental condition changes, in addition to structural integrity requirements, engineering progress requirements, and resource availability information, which provides the basis for dynamic adjustment.

[0046] The adjustment of the priority of each optimization target in the baseline initial stress optimization priority configuration refers to the process of modifying the priority of each optimization target in the baseline priority configuration based on reference information, which can be implemented in various ways such as fuzzy logic reasoning, expert system rules, or machine learning models, to ensure that the final priority configuration can more accurately reflect the current actual requirements.

[0047] In this embodiment, first, the system obtains the current construction stage identifier, which lays the foundation for subsequent information retrieval. Based on this identifier, the system can accurately retrieve the baseline initial stress optimization priority configuration associated with the construction stage from the preset stage information library. This baseline configuration reflects the general optimization tendency of the construction stage. However, the application does not stop here, but further obtains real-time reference information for the current construction stage, which covers multiple dimensions such as structural integrity requirements, engineering progress requirements, and resource availability, directly reflecting the actual situation and urgency of the construction site. Based on these multi-dimensional reference information, the system can adjust the priority of each optimization target in the previously retrieved baseline initial stress optimization priority configuration. For example, when the engineering progress has high urgency, the system can increase the priority of the maximum welding efficiency target; when the structural integrity requirement is high, the system can increase the priority of the minimum peak stress or maximum stress distribution uniformity target. Through this dynamic adjustment, the final initial stress optimization priority configuration can more accurately and flexibly adapt to the actual requirements and constraints of the current construction stage.

[0048] As a preferred implementation, in obtaining the initial stress optimization priority set, the current construction stage identifier can be first automatically obtained through a data interface with the project management system. Subsequently, the system can send a query request to a stage information database built based on a relational database, in which the baseline initial stress optimization priority set corresponding to different construction stages is pre-stored. Further, the system can obtain reference information of the current construction stage from multiple data sources. For example, the structural integrity requirement can be determined according to the identification of key stress areas in the inner floating caisson design drawings or the stress concentration warning information fed back by the structural health monitoring system; the engineering progress requirement can be obtained from the project management software, such as the completion rate of the current task, the comparison between the remaining construction period and the planned construction period; the resource availability information can be obtained from the equipment management system or the inventory management system, such as the number of available welding machines, the amount of welding material in stock, or the welding worker shift arrangement. After obtaining these reference information, the system can adjust the baseline initial stress optimization priority set using a rule-based expert system or a pre-trained machine learning model. For example, if the engineering progress shows that the current task is lagging to a high degree, the system can increase the priority of the welding efficiency maximization target by a preset magnitude based on the baseline value according to the preset rules; if the structural health monitoring system issues a warning that there is a potential stress concentration risk in a certain area, the system can accordingly increase the priority of the peak stress minimization target in that area. In this way, the baseline priority set is dynamically corrected, thereby generating an initial stress optimization priority set that more accurately reflects the current actual working conditions, providing more accurate guidance for subsequent welding process parameter optimization.

[0049] In some embodiments, step A3 comprises: A301. determining real-time mechanical property parameters of the material of the inner floating caisson according to the temperature field data; A302. calculating local stresses of the welding area according to the local strain data and the real-time mechanical property parameters; A303. evaluating the overall structural rigidity of the inner floating caisson according to the macroscopic deformation data, in combination with the geometric configuration of the inner floating caisson and the distribution of completed welds; A304. evaluating the cumulative stress level of the inner floating caisson according to the local stresses of the welding area, in combination with the geometric configuration of the inner floating caisson and the distribution of completed welds.

[0050] Wherein, the real-time mechanical property parameters of the material of the inner floating caisson refer to the mechanical properties of the material used in the inner floating caisson at a specific temperature, such as the elastic modulus, Poisson's ratio, yield strength, and tensile strength, which can be determined according to a pre-established material property-temperature database or through a real-time material testing model.

[0051] Wherein, the local stress of the welding area refers to the force per unit area that the material inside the welding seam and its vicinity bears during the welding process, which can be calculated according to the local strain data and the real-time mechanical property parameters of the material through the constitutive relation.

[0052] Wherein, the geometric configuration of the inner floating disc refers to the actual three-dimensional shape, size and relative position relationship between parts of the inner floating disc at the current construction stage, which can be updated in real time according to the design drawings, BIM model or through three-dimensional scanning data.

[0053] Wherein, the completed weld distribution refers to the position, length, type and quality information of all completed welds on the inner floating disc, which can be obtained according to the welding construction record, weld detection data or through a visual recognition system.

[0054] Wherein, the overall structural stiffness is the ability of the inner floating disc as a whole structure to resist deformation, which can be evaluated according to the macroscopic deformation data, geometric configuration and completed weld distribution through finite element analysis or structural mechanics model.

[0055] Wherein, the cumulative stress level is a comprehensive quantitative index of the residual stress state gradually formed and retained in the structure during the whole welding and construction process due to factors such as welding thermal cycle, cooling shrinkage and external load, which can be evaluated according to the local stress of the welding area, the geometric configuration and the completed weld distribution through the stress superposition principle or the historical path dependence model.

[0056] The scheme refines the evaluation step in the inner floating disc splicing stress parameter optimization method, providing a more accurate and comprehensive method to evaluate the cumulative stress level and overall structural stiffness of the inner floating disc. The evaluation process first determines the real-time mechanical property parameters of the inner floating disc material at the current temperature based on real-time temperature field data. This step is crucial because the mechanical properties of the material, such as elastic modulus and yield strength, change dramatically with temperature, directly affecting the accuracy of stress calculation. Then, using the obtained real-time mechanical property parameters, combined with local strain data, the instantaneous local stress of the welding area is calculated. This stress calculation based on real-time mechanical properties ensures the physical accuracy of the strain-to-stress conversion, providing reliable local basis data for subsequent cumulative stress evaluation. At the same time, in order to comprehensively evaluate the overall structural state of the inner floating disc, the scheme not only considers macro deformation data, but also further combines the changing geometry of the inner floating disc and the distribution of completed welds to evaluate its overall structural stiffness. During the splicing process, the cumulative structure and welds of the inner floating disc will significantly change its stiffness characteristics. By comprehensively considering these dynamic factors, the actual structural stiffness of the inner floating disc at different construction stages can be more accurately reflected, providing a basis for judging whether the structural stiffness has changed within the preset range. Finally, the local stress of the welding area calculated by the scheme is combined with the overall geometry of the inner floating disc and the distribution of completed welds to evaluate the cumulative stress level of the inner floating disc. Local stress is a transient state, while cumulative stress is the result of the entire welding process and structural evolution. Through this comprehensive consideration, the transmission, accumulation, and redistribution of stress in the entire structure can be more comprehensively reflected, avoiding the one-sidedness of relying solely on local transient stress for judgment.

[0057] In some embodiments, step A4 comprises: A401. Calculate the amount of exceeding of the cumulative stress level over the preset stress level threshold; A402. Obtain the spatial distribution characteristics of the cumulative stress; A403. According to the spatial distribution characteristics of the cumulative stress, identify the cumulative stress distribution characteristic type of the inner floating disc; the cumulative stress distribution characteristic type includes single local stress concentration type, multi-point local stress concentration type and overall stress distribution uneven type; A404. According to the identification result of the cumulative stress distribution characteristic type and the exceeding amount, determine the adjustment range and adjustment direction of the priority of each optimization target in the initial stress optimization priority set; A405. According to the adjustment range and adjustment direction of the priority of each optimization target, adjust the priority of each optimization target in the initial stress optimization priority set to reduce the risk of structural failure.

[0058] The spatial distribution characteristic of the accumulated stress refers to the accumulated stress values of each point or each region on the inner floating roof structure and the relative position relationship thereof in a three-dimensional space, which can be expressed in the form of stress field data, stress nephogram, stress gradient diagram, or stress value matrix of key measuring points.

[0059] The accumulated stress distribution characteristic type refers to a typical stress mode induced according to the spatial distribution characteristic of the accumulated stress, which can be classified and recognized based on clustering analysis, pattern recognition algorithm, or a preset rule base. For example, the single local stress concentration type can refer to a case where the stress value in a specific small region of the inner floating roof is obviously higher than that in the surrounding region; the multi-point local stress concentration type can refer to a case where stress concentration occurs in multiple non-continuous small regions of the inner floating roof; and the overall uneven stress distribution type can refer to a case where the stress presents a smooth but continuous fluctuation in a large range of the inner floating roof, rather than being limited to a few points.

[0060] The stress optimization priority adjustment mechanism proposed in the present application works as follows: when the system evaluates that the cumulative stress level of the inner floating platform exceeds the preset threshold, instead of making general adjustments, the system first calculates the amount by which the cumulative stress level exceeds the preset stress level threshold, quantifying the severity of the stress overrun. This overrun amount provides a direct quantitative basis for subsequent priority adjustment, allowing the adjustment range to match the actual stress overrun level. At the same time, the system further obtains the spatial distribution characteristics of the cumulative stress, which enables the system to gain a deep understanding of the specific forms of stress overrun, such as being concentrated at a certain point, multiple points, or uneven overall distribution. Based on the obtained spatial distribution characteristics of the cumulative stress, the system can identify the cumulative stress distribution characteristic type of the inner floating platform, such as single local stress concentration type, multiple local stress concentration type, or overall stress distribution uneven type. By classifying the overrun stress in detail, the present scheme can adopt differentiated processing strategies for different types of stress problems, avoiding the "one-size-fits-all" adjustment method and improving the targeting of the adjustment. Subsequently, the system determines the adjustment range and adjustment direction of the priority of each optimization objective in the initial stress optimization priority set based on the identification result of the cumulative stress distribution characteristic type and the previously calculated overrun amount. This step combines the "degree" and "nature" of stress overrun, making the decision-making process more comprehensive and accurate. For example, for single local stress concentration, the priority of the peak stress minimization objective can be significantly increased; for overall stress distribution unevenness, more emphasis can be placed on the stress distribution uniformity maximization objective. The overrun amount determines the strength of these adjustments. Finally, the system accurately adjusts the priority of each optimization objective in the initial stress optimization priority set based on the determined adjustment range and adjustment direction, thereby more effectively reducing the structural failure risk. The synergistic effect of these steps enables the system to dynamically adjust the optimization strategy based on the severity and spatial distribution characteristics of the stress overrun when stress abnormalities occur during the inner floating platform splicing construction process, ensuring that the structural failure risk is reduced while other optimization objectives are considered as much as possible, avoiding unnecessary performance sacrifices. This refined adjustment mechanism, combined with the scheme in the present application for obtaining the initial priority set based on the construction stage and switching the priority set based on the overall structural stiffness change, collectively builds a multi-faceted, adaptive stress optimization framework, enabling the entire inner floating platform splicing stress parameter optimization method to achieve better global control when faced with complex and variable working conditions.

[0061] To further illustrate the above technical solutions, a specific embodiment is provided below. In a specific embodiment, when the cumulative stress level of the inner floating tank is evaluated to exceed the preset stress level threshold, the system can start the refinement adjustment process. First, the system can calculate the amount of exceeding of the cumulative stress level exceeding the preset stress level threshold, for example, by calculating the difference between the currently evaluated cumulative stress peak value and the preset threshold, or calculating the difference between the stress average value of the threshold exceeding area and the threshold. Then, the system can obtain the spatial distribution characteristics of the cumulative stress, which can be obtained by interpolating the high-density strain sensor array data deployed on the surface of the inner floating tank to generate stress field data, or by the stress cloud map updated in real time by the finite element analysis model. Subsequently, the system can identify the cumulative stress distribution characteristic type according to the obtained stress spatial distribution characteristics. For example, the system can analyze the stress cloud map using an image processing algorithm, and if it is found that the stress peak value is concentrated in a small area and the stress gradient around it is large, it can be identified as a single local stress concentration type; if multiple non-continuous stress peak value areas are found, it can be identified as a multi-point local stress concentration type; if the stress value presents a smooth but continuous fluctuation in a large range, it can be identified as an overall stress distribution uneven type. These identifications can be based on preset pattern matching rules or machine learning models. After identifying the cumulative stress distribution characteristic type, the system can determine the adjustment range and adjustment direction of the priority of each optimization target in the initial stress optimization priority set in combination with the previously calculated exceeding amount. For example, if it is identified as a single local stress concentration type and the exceeding amount is large, the system can significantly increase the priority of the peak stress minimization target and correspondingly reduce the priority of the welding efficiency maximization target; if it is identified as an overall stress distribution uneven type and the exceeding amount is moderate, the system can appropriately increase the priority of the stress distribution uniformity maximization target and slightly reduce the priority of the structure deformation minimization target. These adjustment strategies can be stored in a rule base, and the table look-up or fuzzy logic reasoning can be performed according to different cumulative stress distribution characteristic types and exceeding amount ranges. Finally, the system can adjust the priority of each optimization target in the initial stress optimization priority set according to the determined adjustment range and adjustment direction. For example, if the priority of the peak stress minimization target needs to be increased by 20%, the system can multiply its current priority value by 1.2; if the priority of the welding efficiency maximization target needs to be reduced by 10%, the system can multiply its current priority value by 0.9. These adjusted priority values will serve as the new effective stress optimization priority set for subsequent welding process parameter generation, thereby guiding the welding operation and more accurately reducing the risk of structural failure.

[0062] Preferably, step A404 can include: According to the cumulative stress distribution characteristic type, a corresponding target priority adjustment strategy is obtained from a preset adjustment rule library; the target priority adjustment strategy includes a list of optimization targets that need to be adjusted in priority, and a ratio and a priority adjustment direction between the priority adjustment amplitudes of the optimization targets in the list of optimization targets, wherein the priority adjustment direction of the stress-related optimization target is to increase, and the priority adjustment direction of the other optimization targets is to decrease; According to the excess amount, a basic adjustment coefficient is determined; the basic adjustment coefficient is in a positive correlation with the excess amount; According to the target priority adjustment strategy and the basic adjustment coefficient, the adjustment amplitude and the adjustment direction of the priority of each optimization target in the list of optimization targets are determined.

[0063] The preset adjustment rule library refers to a data set that stores a plurality of predefined rules, which are used to guide how to adjust the priority of the optimization target under different cumulative stress distribution characteristic types. It can be implemented in the form of a database, a lookup table, an expert system rule set or a machine learning model, and contains specific adjustment strategies matched for different stress characteristic types (such as single local stress concentration, multi-point local stress concentration or overall stress distribution unevenness).

[0064] The target priority adjustment strategy refers to a set of specific guidance obtained from the adjustment rule library, which is used to adjust the priority of the optimization target. It includes a list of optimization targets that need to be adjusted in priority, and a ratio and a priority adjustment direction between the priority adjustment amplitudes of the optimization targets in the list of optimization targets. The strategy can be represented in a structured data format, such as a JSON object, an XML file or a data structure inside a program, which clearly defines which optimization targets (such as the peak stress minimization target and the welding efficiency maximization target) need to be adjusted, the relative relationship between the adjustment amplitudes of them (for example, the priority adjustment amplitude of the peak stress minimization target is twice the priority adjustment amplitude of the welding efficiency maximization target), and the adjustment direction of each target (increase or decrease).

[0065] The basic adjustment coefficient refers to a quantitative value that reflects the severity of the cumulative stress level exceeding the preset threshold, and serves as a benchmark for the overall adjustment amplitude. It can be represented by a dimensionless value or a percentage value, calculated by a linear function, an exponential function or a piecewise function, and is in a positive correlation with the excess amount, ensuring that the more the stress exceeds, the greater the adjustment force.

[0066] The adjustment range and adjustment direction of the priority of each optimization target in the optimization target list are determined according to the target priority adjustment strategy and the basic adjustment coefficient. Specifically, the adjustment range of each optimization target in the optimization target list can be obtained by multiplying the proportional value of the proportion between the priority adjustment ranges of each optimization target in the target priority adjustment strategy by the basic adjustment coefficient. For example, if the priority adjustment range of the peak stress minimization target: the priority adjustment range of the stress distribution uniformity maximization target: the priority adjustment range of the welding efficiency maximization target = 3:1:2, and the basic adjustment coefficient is 0.3, then the adjustment range of the priority of the peak stress minimization target is 3*0.3=0.9, the adjustment range of the priority of the stress distribution uniformity maximization target is 1*0.3=0.3, and the adjustment range of the priority of the welding efficiency maximization target is 2*0.3=0.6. The adjustment direction of each optimization target in the optimization target list is the corresponding priority adjustment direction in the target priority adjustment strategy.

[0067] The scheme of the present application solves the challenge of how to accurately respond to different stress problems and severity under multi-objective conflict by introducing a fine adjustment mechanism. Specifically, when the cumulative stress level of the inner floating platform exceeds the preset threshold, the system first acquires a set of targeted target priority adjustment strategies from the preset adjustment rule library according to the identified cumulative stress distribution characteristic type, such as single local stress concentration, multi-point local stress concentration, or overall stress distribution unevenness. This set of strategies is not a simple adjustment direction, but contains a list of optimization targets that need to be adjusted in priority, as well as the relative proportion of the adjustment amplitude between these targets and their respective adjustment directions. For example, for local stress concentration, the strategy may indicate that the priority of stress-related targets (such as the peak stress minimization target) should be significantly increased, while for overall stress distribution unevenness, it may focus more on the priority increase of the stress distribution uniformity maximization target. At the same time, the strategy clearly specifies that the priority adjustment direction of stress-related optimization targets is to increase, while the priority adjustment direction of other optimization targets (such as the welding efficiency maximization target and the energy consumption minimization target) is to decrease, which ensures that when stress risk occurs, the optimization focus can quickly and selectively shift to stress control. On this basis, the system further determines a basic adjustment coefficient according to the amount of excess of the cumulative stress level. This coefficient is positively related to the amount of excess, which means that the more the stress exceeds the threshold, the larger the basic adjustment coefficient, thus quantifying the severity of the stress problem. Finally, the system combines the target priority adjustment strategy (i.e. relative adjustment proportion and direction) obtained from the adjustment rule library with the basic adjustment coefficient (i.e. overall adjustment strength) determined according to the amount of excess to calculate the specific adjustment amplitude and final adjustment direction of each optimization target in the optimization target list. This combination allows the adjustment of priority to be both targeted (according to the stress type) and strong (according to the amount of excess), thus achieving accurate, dynamic and intelligent adjustment of multi-objective priority.

[0068] Through this hierarchical and collaborative adjustment mechanism, the present scheme can overcome the problem of lack of fine and quantitative guidance in the adjustment strategy of traditional methods. It not only can identify the specific stress problem type and match the corresponding adjustment strategy, but also can adaptively adjust the adjustment strength according to the severity of the stress excess. This mechanism is closely combined with the steps of evaluating the cumulative stress level and identifying the stress distribution characteristic type, forming a closed-loop stress risk response and optimization strategy adjustment system. When stress risk occurs, the system can quickly and accurately adjust the optimization target weight, ensuring that while reducing the risk of structural failure, other engineering targets are still considered, thereby improving the robustness and adaptability of the entire optimization method, making the splicing construction process of the inner floating platform safer and more efficient.

[0069] In some embodiments, step A6 comprises: A601. determining heat input characteristics and heat dissipation characteristics of the welding area according to the field environment parameters; the field environment parameters include at least one of ambient temperature, ambient humidity and ambient wind speed; A602. evaluating the difficulty of achieving each optimization target according to the heat input characteristics and the heat dissipation characteristics, combined with the material thermophysical parameters and geometric configuration of the inner floating basin.

[0070] wherein the heat input characteristics refer to the heat input to the welding area per unit time during the welding process, which can be calculated by comprehensively considering factors such as welding power output, arc efficiency and welding speed.

[0071] wherein the heat dissipation characteristics refer to the rate and mode of heat dissipation from the welding area to the surrounding environment, which can be calculated by comprehensively considering factors such as convective heat transfer coefficient, radiative heat transfer coefficient and material thermal conductivity.

[0072] wherein the material thermophysical parameters refer to the thermal properties of the inner floating basin material at different temperatures, which can be characterized by parameters such as thermal conductivity, specific heat capacity, density and thermal expansion coefficient.

[0073] wherein the geometric configuration refers to the structure shape, size of the inner floating basin, and the type and position distribution of the weld, which can be described by data such as three-dimensional model data, CAD drawing information and weld cross-sectional shape.

[0074] wherein the difficulty of achieving the optimization target refers to the resource input, technical challenge or parameter adjustment range required to achieve the preset welding optimization target, such as minimizing peak stress, maximizing welding efficiency, etc., under the current field environment and the conditions of the inner floating basin itself.

[0075] The method for evaluating the difficulty of achieving each optimization target is refined, thereby solving the problem of difficulty in accurately evaluating the difficulty of achieving the optimization target under dynamic environmental conditions. Specifically, the method first determines the heat input characteristics and heat dissipation characteristics of the welding area according to the field environmental parameters through the A601 step. The welding process is essentially a thermodynamic process, and its results are closely related to the input and dissipation of heat. Field environmental parameters, such as environmental temperature, environmental humidity, and environmental wind speed, directly affect the heat balance of the welding area. For example, lower environmental temperature or higher wind speed can accelerate the heat dissipation of the weld, affecting the cooling speed and stress formation; while humidity can affect the arc stability. By quantifying the influence of these environmental factors on the heat balance of the welding area, a physical basis can be provided for subsequent evaluation of the difficulty of achieving the optimization target, enabling the understanding of environmental impact to move from qualitative to quantitative. On this basis, the A602 step further evaluates the difficulty of achieving each optimization target according to the determined heat input characteristics and heat dissipation characteristics, combined with the material thermal physical parameters and geometric configuration of the inner floating disc. The thermal conductivity, specific heat capacity, and other thermal physical parameters of the inner floating disc material determine the heat conduction and storage capacity in the material, while the geometric configuration of the inner floating disc, such as plate thickness, weld type, and structure size, affects the heat distribution and dissipation path. By comprehensively considering the environmental-induced heat input and heat dissipation characteristics and the material and structural characteristics of the inner floating disc itself, the actual difficulty of achieving each optimization target, such as minimizing peak stress and maximizing welding efficiency, can be comprehensively and accurately evaluated under specific working conditions. For example, in an environment with faster heat dissipation and higher material thermal conductivity, more precise welding parameter control may be required to achieve lower peak stress, thereby increasing the difficulty of achieving this goal. This comprehensive evaluation mechanism ensures that the judgment of the difficulty of achieving the optimization target is based on a physical model, rather than simple experience.

[0076] Through the combination of the above two steps, the present solution converts abstract field environmental parameters into specific quantification of welding thermodynamic behavior, and further combines the physical properties of the inner floating disc, thereby providing a more accurate and comprehensive evaluation of the difficulty of achieving the optimization target. This accurate difficulty evaluation, as a refinement of the step of evaluating the difficulty of achieving each optimization target, can provide a more reliable basis for the subsequent generation of welding process parameters, enabling the generated welding process parameters to more accurately adapt to dynamically changing field working conditions, thereby continuously and effectively balancing and optimizing various performance indicators throughout the construction cycle, achieving global optimal control.

[0077] In one specific embodiment, in order to determine the heat input characteristics and heat dissipation characteristics of the welding zone according to the field environmental parameters, multiple sensors can be deployed. For example, the ambient temperature can be collected in real time by a thermocouple or an infrared temperature sensor; the ambient humidity can be acquired by a humidity sensor; the ambient wind speed can be measured by an anemometer. These sensor data can be input to an environmental parameter processing module. This module can have a built-in thermodynamic model, for example based on finite element analysis or computational fluid dynamics (CFD) model, which can calculate the convective heat transfer coefficient, the radiative heat transfer coefficient and the potential influence of latent heat of water evaporation of the welding zone according to the input temperature, humidity and wind speed data, so as to quantify the heat dissipation characteristics of the welding zone. At the same time, combined with the rated power of the welding equipment, the arc efficiency and the welding speed and other parameters, the actual heat input characteristics can be calculated. On this basis, in order to evaluate the difficulty of achieving each optimization target, a comprehensive evaluation unit can be used. This unit can pre-store a material thermophysical parameter database of the inner floating caisson, such as the thermal conductivity, specific heat capacity and density data of Q345R steel at different temperatures, as well as the geometric configuration data of the inner floating caisson, such as the plate thickness, weld groove shape and overall structure size imported through the CAD model. The evaluation unit can run a multi-physical field coupling simulation software, such as ANSYS or ABAQUS, to simulate the temperature field evolution and stress and strain distribution during the welding process by taking the determined heat input characteristics and heat dissipation characteristics as boundary conditions, combining the material thermophysical parameters and geometric configuration. Through analysis of the simulation results, the required welding parameter adjustment range or additional control measures to achieve a specific optimization target, such as controlling the peak residual stress below a certain threshold or controlling the welding deformation within the allowable range, can be quantified. For example, if the simulation shows that under the current environmental and structural conditions, extremely low welding speed or additional cooling measures are required to achieve lower peak stress, it can be judged that the difficulty of achieving this optimization target is high.

[0078] In some embodiments, step A7 comprises: A701. obtaining welding process parameter constraint conditions of the current construction stage; the welding process parameter constraint conditions comprise adjustment ranges of each welding process parameter determined based on material characteristics of the inner floating caisson, weld geometry and performance of the welding equipment; the welding process parameters comprise welding current, welding voltage, welding speed and inter-pass temperature control threshold of the weld; A702. determining adjustment directions and adjustment amplitudes of each welding process parameter according to the effective stress optimization priority set and the difficulty of achievement, and the welding process parameter constraint conditions and the current welding process parameters; A703. generating a set of candidate welding process parameters based on the adjustment directions and adjustment amplitudes of each welding process parameter and the current welding process parameters; A704. evaluate the influence of the candidate welding process parameters on each optimization target, and determine whether the candidate welding process parameters meet the welding process parameter constraint conditions; A705. if the candidate welding process parameters do not meet the welding process parameter constraint conditions, or the influence of the candidate welding process parameters on each optimization target does not achieve the preset improvement effect, then according to the influence evaluation result, adjust the adjustment direction and adjustment amplitude of each welding process parameter, and return to step A703; A706. if the candidate welding process parameters meet the welding process parameter constraint conditions, and the influence of the candidate welding process parameters on each optimization target achieves the preset improvement effect, then output the candidate welding process parameters as the final welding process parameters for welding operation.

[0079] The welding process parameter constraint condition refers to the limitation range set for welding current, welding voltage, welding speed, and inter-pass temperature control threshold value, etc. in actual welding operation, in order to ensure the material integrity of the inner floating disc, the forming quality of the weld, and the stable operation of the welding equipment. It can be determined by using a preset database, real-time sensor monitoring, or engineering specification calculation.

[0080] The adjustment direction and adjustment amplitude of each welding process parameter refer to the trend of increasing or decreasing the parameter value and the specific change value when modifying the current welding process parameter. It can be determined by using gradient calculation based on optimization algorithm, rule-based reasoning, or expert experience system. This multi-dimensional consideration ensures that the adjustment of the parameter can effectively respond to the current optimization demand, and can also take into account the limitations of actual operation, avoiding blind adjustment. For example, an optimization algorithm based on model predictive control (MPC) can be used; the algorithm takes an effective stress optimization priority set as the target function weight, takes the difficulty as the penalty term, and takes the welding process parameter constraint condition as the hard constraint; the algorithm can calculate the stress response and target achievement under different adjustment directions and adjustment amplitudes according to the current welding process parameters, so as to determine an adjustment strategy; for example, if the current peak stress is too high and the stress distribution uniformity priority is high, the system can calculate the adjustment direction and amplitude of reducing the welding speed and slightly reducing the welding current.

[0081] When generating a set of candidate welding process parameters based on the adjustment direction and adjustment amplitude of each welding process parameter and the current welding process parameters, the adjustment amplitude can be added or subtracted from the current welding process parameters according to the adjustment direction.

[0082] The candidate welding process parameters refer to a set of potential feasible welding parameter combinations generated based on the existing parameters according to the current adjustment direction and adjustment amplitude in the iterative optimization process. This step converts the abstract adjustment instructions into specific parameter values, providing a test scheme for subsequent evaluation and verification.

[0083] The preset improvement effect refers to the minimum standard of performance improvement or problem alleviation expected to be achieved when evaluating the influence of the candidate welding process parameters on each optimization target. The comprehensive performance score of the influence of the candidate welding process parameters on each optimization target can be obtained, and the comprehensive performance score corresponding to the current welding process parameters can also be obtained. The increase in the comprehensive performance score of the candidate welding process parameters relative to the current welding process parameters is calculated, and the increase is compared with the preset increase threshold. If the increase in the comprehensive performance score is higher than the increase threshold, it is determined that the preset improvement effect is achieved, otherwise, it is determined that the preset improvement effect is not achieved.

[0084] This double evaluation mechanism ensures that the final output parameters not only achieve the optimization effect, but also meet the actual operation requirements. If the candidate welding process parameters do not meet the constraint conditions or the influence on each optimization target does not achieve the preset improvement effect, the system will not directly give up, but will adaptively adjust the adjustment direction and adjustment amplitude of each welding process parameter according to the influence evaluation result and return to generate new candidate parameters. This closed-loop feedback and iterative adjustment mechanism enables the system to continuously approach the optimal and feasible welding process parameters, improving the robustness of parameter generation and enhancing the adaptability to complex working conditions. Finally, when the system finds a set of candidate parameters that meet all the welding process parameter constraint conditions and achieve the preset improvement effect on each optimization target, it confirms the candidate parameters as the final welding process parameters and outputs them for actual welding operation.

[0085] The scheme effectively solves the problem of lack of practical operation feasibility constraints and effect verification in the generation of welding process parameters in the prior art by introducing the acquisition of constraints on welding process parameters, parameter adjustment based on multi-dimensional consideration, generation and double evaluation of candidate parameters, and key iterative feedback and adjustment mechanism. By continuously considering the actual limitations such as the material properties of the inner floating plate, the weld geometry, and the welding equipment performance during the parameter generation process, the output welding parameters are ensured to have practical application feasibility while achieving theoretical optimization effect and improving safety. In addition, by evaluating the influence of the candidate parameters and iteratively adjusting them, the system can continuously approach the optimal and feasible parameter combination, improving the robustness of the parameter generation and enhancing the adaptability to complex working conditions. This enables the system to continuously output verified and reliable welding guidance throughout the construction cycle, thereby achieving a continuous balance between optimization objectives and global optimal control, avoiding structural failure or low efficiency caused by unreasonable parameters.

[0086] Preferably, in step A704, the step of evaluating the influence of the candidate welding process parameters on each optimization objective can include: determining the current importance weight of each optimization objective according to the effective stress optimization priority set; evaluating the expected value of the optimization index of each optimization objective of the inner floating plate after applying the candidate welding process parameters; quantifying the actual influence degree of the candidate welding process parameters on each optimization objective according to the expected value; calculating the comprehensive performance score of the candidate welding process parameters according to the current importance weight and the actual influence degree; taking the actual influence degree and the comprehensive performance score as the influence evaluation result of the candidate welding process parameters on each optimization objective.

[0087] The current importance weight refers to the numerical value assigned to each optimization objective according to the effective stress optimization priority set, indicating its relative importance in the current optimization stage. The priority in the effective stress optimization priority set can be normalized, and the normalized result can be used as the current importance weight, or the priority can be directly used as the current importance weight.

[0088] The expected value of the optimization index refers to the quantitative value of each optimization objective obtained by simulation or prediction after applying the candidate welding process parameters. For example, the expected peak stress, the expected stress distribution uniformity, the expected welding efficiency, the expected energy consumption, and the expected structural deformation.

[0089] The actual influence degree refers to the improvement ratio of the expected value of the optimization index corresponding to the candidate welding process parameter relative to the expected value of the optimization index corresponding to the current welding process parameter; for example, the expected value corresponding to the candidate welding process parameter is referred to as a first expected value, and the expected value corresponding to the current welding process parameter is referred to as a second expected value, and the actual influence degree includes the reduction ratio of the first expected peak stress relative to the second expected peak stress, the improvement ratio of the first expected stress distribution uniformity relative to the second expected stress distribution uniformity, the improvement ratio of the first expected welding efficiency relative to the second expected welding efficiency, the reduction ratio of the first expected energy consumption relative to the second expected energy consumption, and the reduction ratio of the first expected structural deformation relative to the second expected structural deformation.

[0090] The comprehensive performance score refers to a single numerical value that can reflect the overall advantages and disadvantages of the candidate welding process parameter, which is obtained by weighted calculation in combination with the current importance weight of each optimization target and the actual influence degree. The influence evaluation result refers to a data set containing the actual influence degree and the comprehensive performance score output after evaluating the performance of the candidate welding process parameter.

[0091] In the scheme, when evaluating the influence of the candidate welding process parameter on each optimization target, first, the importance weight of each optimization target under the current working condition is determined according to the adjusted effective stress optimization priority set. This ensures that the evaluation process can respond to changes in the construction phase, cumulative stress level and field environment parameters, so that the optimization strategy always focuses on the current performance index. Secondly, the system predicts the expected value of the optimization index (such as peak stress, welding efficiency, etc.) of each optimization target after applying the candidate welding process parameter to the inner floating tank. This prediction is based on the simulation of future states and provides a data basis for subsequent quantitative analysis. Then, the predicted optimization index expected values are converted into comparable actual influence degrees. This quantitative treatment enables different optimization targets of different natures to be compared and analyzed in a unified framework. Further, the quantitative actual influence degree is combined with the determined importance weight to calculate the comprehensive performance score of the candidate welding process parameter. This score considers the influence of the parameter on each target and weights these influences according to the current needs, thereby finding a balance point between multiple conflicting targets. Finally, the actual influence degree and the comprehensive performance score are output as the influence evaluation result. The actual influence degree provides the details of the influence of the parameter on each specific target, and the comprehensive performance score provides the overall judgment.

[0092] It is this dynamic, multi-dimensional evaluation mechanism that enables the scheme to provide feedback for subsequent parameter adjustment (such as step A705). When the candidate parameters do not meet the constraint conditions or do not achieve the preset improvement effect, the system can adjust the adjustment direction and amplitude of the welding process parameters according to the evaluation results, forming an iterative optimization closed loop. This combination enables the entire optimization method to adapt to the construction environment and changing needs, thereby achieving a balance and control between the optimization objectives throughout the construction cycle, achieving the structural integrity and construction efficiency of the inner floating deck.

[0093] With reference Figure 2 The present application provides an inner floating deck splicing stress parameter optimization system for optimizing welding process parameters according to real-time working conditions in the splicing construction operation of a storage tank inner floating deck, which comprises: An initial priority acquisition module 1 is configured to acquire a corresponding initial stress optimization priority set according to the current construction stage; the stress optimization priority set contains the priorities of multiple optimization objectives (for specific processes, refer to step A1 in the foregoing description); A data acquisition module 2 is configured to acquire local strain data and temperature field data of the welding area, macroscopic deformation data of the inner floating deck, and field environment parameters (for specific processes, refer to step A2 in the foregoing description); A state evaluation module 3 is configured to evaluate the current cumulative stress level and overall structural stiffness of the inner floating deck according to the local strain data, the temperature field data, and the macroscopic deformation data (for specific processes, refer to step A3 in the foregoing description); A priority adjustment module 4 is configured to adjust the priorities of the optimization objectives in the initial stress optimization priority set to reduce the risk of structural failure when the cumulative stress level exceeds a preset stress level threshold (for specific processes, refer to step A4 in the foregoing description); A priority switching module 5 is configured to switch the initial stress optimization priority set to a stress optimization priority set that matches the changed preset interval when the overall structural stiffness is in a preset interval (for specific processes, refer to step A5 in the foregoing description); A difficulty evaluation module 6 is configured to evaluate the difficulty of achieving each optimization objective according to the field environment parameters (for specific processes, refer to step A6 in the foregoing description); A parameter generation module 7 is configured to generate welding process parameters for welding operations according to the effective stress optimization priority set and the difficulty of achieving each optimization objective; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set, or the switched stress optimization priority set (for specific processes, refer to step A7 in the foregoing description).

[0094] The above merely provides an example of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing stress parameters of inner floating plate splicing, used for optimizing welding process parameters according to real-time working conditions during the splicing construction of inner floating plate of storage tank, characterized in that: The steps of the method include: A1. Obtain an initial stress optimization priority set based on the current construction phase. The stress optimization priority set includes priorities corresponding to multiple optimization objectives. A2. Obtain local strain data and temperature field data of the welding area, macroscopic deformation data of the inner floating plate, and on-site environmental parameters; A3. Evaluate the current cumulative stress level and overall structural stiffness of the inner floating disc based on the local strain data, the temperature field data, and the macro deformation data; A4. If the cumulative stress level exceeds a preset stress level threshold, adjusting the priority of each optimization objective in the initial stress optimization priority set to reduce the risk of structural failure; A5. If the preset interval of the overall structural stiffness changes, switching the initial stress optimization priority set to a stress optimization priority set that matches the changed preset interval; A6. Evaluate the difficulty of achieving each optimization goal based on the site environment parameters; A7. Generate welding process parameters for the welding operation based on the effective stress optimization priority set and the difficulty of achieving the desired result; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set, or the switched stress optimization priority set.

2. The inner floating plate splicing stress parameter optimization method according to claim 1 is characterized in that: The construction phase includes the initial plate connection phase, the intermediate structure forming phase and the final sealing and correction phase; The multiple optimization objectives include a peak stress minimization objective, a stress distribution uniformity maximization objective, a welding efficiency maximization objective, an energy consumption minimization objective, and a structural deformation minimization objective; The priorities of the optimization objectives in the initial stress optimization priority set corresponding to different construction stages are different. The priority of the welding efficiency maximization objective in the initial stress optimization priority set corresponding to the earlier construction stage is higher, and the priority of the peak stress minimization objective and the stress distribution uniformity maximization objective in the initial stress optimization priority set corresponding to the later construction stage is higher.

3. The inner floating plate splicing stress parameter optimization method according to claim 1 is characterized in that: Step A1 includes: A101. Get the construction phase identifier of the current construction phase; A102. Retrieve a baseline initial stress optimization priority set associated with the construction stage identifier from a preset stage information library; A103. Obtain reference information of the current construction phase; the reference information includes at least one of structural integrity requirements, project schedule requirements, and resource availability information; A104. Adjust the priority of each optimization target in the benchmark initial stress optimization priority set according to the reference information to generate the corresponding initial stress optimization priority set.

4. The method for optimizing the inner floating plate splicing stress parameters according to claim 1, characterized in that: Step A3 includes: A301. According to the temperature field data, determine the real-time mechanical properties of the inner floating material parameters; A302. Calculate the local stress of the welding area based on the local strain data and the real-time mechanical property parameters; A303. Based on the macro deformation data, combined with the geometric configuration of the inner floating plate and the distribution of completed welds, evaluate the overall structural stiffness of the inner floating plate; A304. Evaluate the cumulative stress level of the inner floating plate based on the local stress in the welding area, combined with the geometric configuration of the inner floating plate and the distribution of the completed welds.

5. The method for optimizing the inner floating plate splicing stress parameters according to claim 2, characterized in that: Step A4 includes: A401. Calculate the amount by which the cumulative stress level exceeds a preset stress level threshold; A402. Obtain the spatial distribution characteristics of cumulative stress; A403. Identify the cumulative stress distribution characteristic type of the inner floating plate based on the spatial distribution characteristics of the cumulative stress; the cumulative stress distribution characteristic type includes a single local stress concentration type, a multi-point local stress concentration type, and an overall uneven stress distribution type; A404. Determine the adjustment range and direction of the priority of each optimization target in the initial stress optimization priority set based on the identification result of the cumulative stress distribution feature type and the excess amount; A405. Adjust the priority of each optimization objective in the initial stress optimization priority set according to the adjustment range and adjustment direction of the priority of each optimization objective to reduce the risk of structural failure.

6. The method for optimizing the inner floating plate splicing stress parameters according to claim 5, characterized in that: Step A404 includes: According to the cumulative stress distribution feature type, a corresponding target priority adjustment strategy is obtained from a preset adjustment rule library; the target priority adjustment strategy includes a list of optimization targets that need to have their priorities adjusted, as well as the ratios and priority adjustment directions of the priority adjustment ranges of the optimization targets in the optimization target list, wherein the priority adjustment direction of the optimization targets related to stress is increasing, and the priority adjustment direction of other optimization targets is decreasing; Determining a basic adjustment coefficient according to the excess amount; wherein the basic adjustment coefficient is positively correlated with the excess amount; The adjustment range and adjustment direction of the priority of each optimization target in the optimization target list are determined according to the target priority adjustment strategy and the basic adjustment coefficient.

7. The method for optimizing the inner floating plate splicing stress parameters according to claim 1, characterized in that: Step A6 includes: A601. Determine the heat input characteristics and heat dissipation characteristics of the welding area according to the on-site environmental parameters; the on-site environmental parameters include at least one of the ambient temperature, ambient humidity and ambient wind speed; A602. Based on the heat input characteristics and the heat dissipation characteristics, combined with the material thermophysical parameters and geometric configuration of the inner floating disk, evaluate the difficulty of achieving each optimization goal.

8. The method for optimizing the inner floating plate splicing stress parameters according to claim 1, characterized in that: Step A7 includes: A701. Obtain the welding process parameter constraints for the current construction phase; the welding process parameter constraints include the adjustment ranges of the welding process parameters determined based on the inner float material properties, weld geometry, and welding equipment performance; the welding process parameters include welding current, welding voltage, welding speed, and weld interpass temperature control threshold; A702. Determine the adjustment direction and adjustment range of each welding process parameter based on the effective stress optimization priority set and the difficulty of achieving the optimization, as well as the welding process parameter constraints and the current welding process parameters; A703. Based on the adjustment direction and adjustment range of each welding process parameter and the current welding process parameter, generate a set of candidate welding process parameters; A704. Evaluate the impact of the candidate welding process parameters on each optimization objective, and determine whether the candidate welding process parameters meet the welding process parameter constraints; A705. If the candidate welding process parameters do not satisfy the welding process parameter constraints, or their impact on each optimization objective does not achieve the preset improvement effect, adjust the adjustment direction and adjustment range of each welding process parameter based on the impact assessment result, and return to step A703. A706. If the candidate welding process parameters meet the welding process parameter constraints and their impact on each optimization target achieves the preset improvement effect, the candidate welding process parameters are output as the final welding process parameters for use in the welding operation.

9. The inner floating plate splicing stress parameter optimization method according to claim 8, characterized in that: In step A704, the step of evaluating the influence of the candidate welding process parameters on each optimization target includes: Determining the current importance weight of each optimization objective according to the effective stress optimization priority set; evaluating expected values ​​of optimization indicators of various optimization objectives of the inner floating plate after applying the candidate welding process parameters; quantifying the actual influence of the candidate welding process parameters on the optimization objectives according to the expected values; Calculating a comprehensive performance score of the candidate welding process parameters according to the current importance weight and the actual impact degree; The actual impact degree and the comprehensive performance score are used as the impact evaluation results of the candidate welding process parameters on each optimization target.

10. An internal floating plate splicing stress parameter optimization system is used to optimize welding process parameters according to real-time working conditions during the splicing and construction of the internal floating plate of a storage tank, characterized in that: The system includes: The initial priority acquisition module is used to obtain the corresponding initial stress optimization priority set according to the current construction stage; the stress optimization priority set includes the priorities corresponding to multiple optimization objectives; Data acquisition module, used to obtain local strain data and temperature field data of the welding area, macro deformation data of the inner floating plate, and on-site environmental parameters; a state assessment module, configured to assess the current accumulated stress level and overall structural stiffness of the inner floating plate based on the local strain data, the temperature field data, and the macro deformation data; a priority adjustment module, configured to adjust the priority of each optimization objective in the initial stress optimization priority set when the cumulative stress level exceeds a preset stress level threshold, so as to reduce the risk of structural failure; a priority switching module, configured to switch the initial stress optimization priority set to a stress optimization priority set matching the changed preset interval when the preset interval of the overall structural stiffness changes; A difficulty assessment module, used to assess the difficulty of achieving each optimization goal based on the on-site environmental parameters; A parameter generation module is used to generate welding process parameters for welding operations based on an effective stress optimization priority set and the difficulty of achieving the desired effect; the effective stress optimization priority set is the initial stress optimization priority set, the adjusted initial stress optimization priority set, or the switched stress optimization priority set.

Images