Optimized construction method and system for deepwater jacket steel pile SPMT roll-on / roll-off loading

Abstract

The present invention discloses a deepwater jacket steel pile SPMT roll-on / roll-off loading optimization construction method and system, which relates to the field of ship construction technology. The method comprises: extracting key nodes of a target steel pile loading scheme, obtaining K steel pile loading nodes for risk factor identification, determining a set of risk factors of K loading nodes, analyzing and generating a node risk factor mapping cascade tree, quantifying the risk accumulation of the K loading node risk factor sets, obtaining a target loading scheme risk coefficient, analyzing and determining the loading risk generation cause parameters, using loading optimization strategy space to perform strategy optimization analysis on the loading risk generation cause parameters, and outputting a steel pile optimized loading scheme for loading optimization construction control. The method achieves the technical effect of realizing intelligent analytical optimization of the construction scheme through risk identification and evaluation of the steel pile loading scheme, improving the accuracy and applicability of the loading construction scheme, and thus improving the safety and construction efficiency of the loading construction scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of ship construction, and in particular to a deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method and system. Background Art

[0002] As an important supporting structure of the offshore platform, the transportation and installation process of deepwater jacket steel piles is complex and requires high technical requirements. Traditional loading methods such as lifting and sliding methods have problems such as high safety risks, high costs, and long cycles. Self-propelled modular transporters (SPMTs) have gradually become an important tool for the transportation of large structures due to their strong flexibility, large carrying capacity, and smooth transportation. However, when SPMT is applied to the roll-on / roll-off loading of deepwater jacket steel piles, the construction method is less intelligent, and the accuracy and safety of the loading construction plan are not enough. Summary of the invention

[0003] The present application solves the technical problems of low intelligence level of the existing steel pile roll-on / roll-off construction method and insufficient accuracy and safety of the loading construction plan by providing an optimized construction method and system for deepwater jacket steel pile SPMT roll-on / roll-off loading, and achieves the technical effect of achieving intelligent analysis and optimization of the construction plan through risk identification and assessment of the steel pile loading plan, improving the accuracy and applicability of the loading construction plan, and thus improving the safety and construction efficiency of the loading construction plan.

[0004] In view of the above problems, the present invention provides a deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method and system.

[0005] In the first aspect, the present application provides an optimized construction method for roll-on / roll-off loading of deepwater jacket steel piles SPMT, the method comprising: obtaining a target steel pile loading scheme, extracting key nodes of the target steel pile loading scheme, and obtaining K steel pile loading nodes; identifying risk factors for the K steel pile loading nodes respectively, and determining a set of risk factors for the K loading nodes; performing mapping association analysis on the set of risk factors of the K loading nodes based on the target steel pile loading scheme, and generating a node risk factor mapping cascade tree; using the node risk factor mapping cascade tree to perform risk accumulation quantification on the set of risk factors of the K loading nodes, and obtaining a target loading scheme risk coefficient; based on the target loading scheme risk coefficient, identifying risk areas and analyzing generation causes for the target steel pile loading scheme, and determining parameters for generation causes of loading risks; constructing a loading optimization strategy space, using the loading optimization strategy space to perform strategy optimization analysis on the parameters for generation causes of loading risks, outputting an optimized steel pile loading scheme, and performing loading optimization construction control based on the optimized steel pile loading scheme.

[0006] On the other hand, the present application also provides a deepwater jacket steel pile SPMT roll-on / roll-off loading optimization construction system, the system comprising: a key node extraction module, used to obtain a target steel pile loading plan, extract key nodes from the target steel pile loading plan, and obtain K steel pile loading nodes; a risk factor identification module, used to identify risk factors for the K steel pile loading nodes respectively, and determine a set of risk factors for the K loading nodes; a cascade tree generation module, used to map and associate the set of risk factors for the K loading nodes based on the target steel pile loading plan, and generate a node risk factor mapping cascade tree; a risk accumulation quantification module, It is used to use the node risk factor mapping cascade tree to quantify the risk accumulation of the K loading node risk factor sets, and obtain the target loading plan risk coefficient; the risk cause analysis module is used to identify the risk area and generate cause analysis for the target steel pile loading plan based on the target loading plan risk coefficient, and determine the loading risk generation cause parameters; the loading optimization construction control module is used to construct a loading optimization strategy space, use the loading optimization strategy space to perform strategy optimization analysis on the loading risk generation cause parameters, output the steel pile optimization loading plan, and perform loading optimization construction control based on the steel pile optimization loading plan.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By extracting key nodes from the target steel pile loading scheme, K steel pile loading nodes are obtained for risk factor identification, and a set of risk factors of K loading nodes is determined. Based on the target steel pile loading scheme, the set of risk factors of K loading nodes is mapped and associated, and a node risk factor mapping cascade tree is generated, so as to quantify the risk accumulation of the risk factors of the K loading nodes, obtain the target loading scheme risk coefficient, identify the risk area of ​​the target steel pile loading scheme, analyze the generation reasons, determine the generation reason parameters of loading risk, use the loading optimization strategy space to perform strategy optimization analysis on the generation reason parameters of loading risk, and output the steel pile optimized loading scheme for loading optimization construction control. Thus, the technical effect of risk identification and evaluation of the steel pile loading scheme is achieved, intelligent analysis and optimization of the construction scheme is realized, the accuracy and applicability of the loading construction scheme is improved, and the safety and construction efficiency of the loading construction scheme are improved.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A schematic diagram of the process for optimizing the construction method of SPMT roll-on / roll-off loading of deepwater jacket steel piles for this application;

[0011] Figure 2 A schematic diagram of the process of obtaining the target steel pile loading scheme in the deepwater jacket steel pile SPMT roll-on / roll-off loading optimization construction method for this application;

[0012] Figure 3 This is a schematic diagram of the structure of the optimized construction system for the SPMT roll-on / roll-off shipment of deepwater jacket steel piles for this application.

[0013] Explanation of the reference numerals: key node extraction module 11, risk factor identification module 12, cascade tree generation module 13, risk accumulation quantification module 14, risk cause analysis module 15, loading optimization construction control module 16. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] The present application is described below in conjunction with the drawings in the present application.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method, the method comprising:

[0017] Step S1: Obtain a target steel pile loading plan, extract key nodes from the target steel pile loading plan, and obtain K steel pile loading nodes.

[0018] like Figure 2 As shown, further, the steps of obtaining the target steel pile loading plan in this application also include:

[0019] The target information of steel pile loading demand is obtained, wherein the target information of steel pile loading demand includes the attribute information of steel piles to be loaded and the performance parameter information of loading equipment; the SPMT loading record data set of steel piles is collected and acquired through data mining technology, and the SPMT bundle transportation process is adopted to classify and identify the SPMT loading record data set of steel piles, so as to obtain the loading process node record data set; based on the target information of steel pile loading demand, the loading process node record data set is retrieved and matched to obtain the candidate steel pile loading data set; loading effect evaluation and global comparison and optimization are performed on the candidate steel pile loading data set to determine the target steel pile loading plan.

[0020] Furthermore, the steps of determining the target steel pile loading plan also include:

[0021] Obtain a set of steel pile loading effect evaluation indicators, perform loading effect evaluation and global comparison and optimization on the candidate steel pile loading data set based on the steel pile loading effect evaluation indicator set, and determine the available steel pile loading schemes; perform demand deviation calculation and parameter tuning analysis on the available steel pile loading schemes, and obtain multiple steel pile loading optimization schemes; perform effect fitting on the steel pile SPMT loading record data set according to the steel pile loading effect evaluation indicator set, and construct a steel pile loading effect evaluation simulation module; perform simulation evaluation and optimization on the multiple steel pile loading optimization schemes based on the steel pile loading effect evaluation simulation module, and determine the target steel pile loading scheme.

[0022] Specifically, the overall loading structure weight, quantity and size of deepwater jacket steel piles are relatively large. In order to realize the intelligent and applicable analysis of steel pile loading scheme, the target information of steel pile loading demand is first collected through the ship transportation system. The target information of steel pile loading demand demand includes the attribute information of steel piles to be loaded, such as the size (length, diameter or cross-sectional size), weight, material, and anti-corrosion coating of steel piles; and the performance parameter information of loading equipment, such as the load capacity, driving speed, turning radius, climbing ability, power system configuration, etc. of SPMT (self-propelled modular transporter), as well as the performance parameters of auxiliary equipment such as cranes and lifting rigging. Then, the steel pile SPMT loading record data set is collected and obtained through data mining technology. The steel pile SPMT loading record data set is the SPMT loading record data of each historical loading process node.

[0023] The SPMT bundle transportation process is used to quickly and hoist the deepwater jacket steel piles for roll-on / roll-off loading. The steel pile SPMT loading record data set is classified and identified according to the process nodes such as hoisting, packaging, loading, transportation, positioning, and unloading, and the loading process node record data set is obtained after classification and integration according to the process nodes, which is convenient for subsequent retrieval and analysis according to the process nodes. The loading process node record data set is retrieved and matched based on the steel pile loading demand target information, and the steel pile loading demand target information is compared with the loading process node record data set using a similarity algorithm to screen out the record data that meets the current steel pile attributes and equipment performance requirements. For example, the record data with a similarity of 80% is screened and integrated to obtain the corresponding candidate steel pile loading data set.

[0024] In order to ensure the applicability of the loading scheme, the loading effect evaluation and global comparison and optimization of the candidate steel pile loading data set are performed. First, a set of steel pile loading effect evaluation indicators is obtained. The steel pile loading effect evaluation indicator set is used to evaluate the steel pile loading effect, which can be set by yourself, such as time efficiency, cost estimation, safety risk, etc. Then, the loading effect evaluation of the candidate steel pile loading data set is performed based on the steel pile loading effect evaluation indicator set. According to the determined evaluation indicator set, each candidate scheme is quantitatively evaluated, and the specific values ​​of each indicator are weighted to obtain the comprehensive indicator score value. Then, the comprehensive indicator score values ​​of different candidate schemes are globally compared and optimized to determine the available steel pile loading scheme with the best loading effect score. The actual demand deviation of the available steel pile loading scheme is calculated, including deviations in quantity, weight, size, etc., and then the parameter optimization analysis of the available steel pile loading scheme is performed through the expert group or loading experience data according to the deviation parameters, such as loading sequence, stacking method, fixed parameters, etc., and fine-tuning is performed to obtain multiple steel pile loading optimization schemes after parameter fine-tuning.

[0025] According to the steel pile loading effect evaluation index set, the steel pile SPMT loading record data set is fitted, and based on the fitting results, a steel pile loading effect evaluation simulation module is constructed, which can simulate the loading process under different loading schemes and output the corresponding evaluation results. Based on the steel pile loading effect evaluation simulation module, the multiple steel pile loading optimization schemes are simulated and evaluated to obtain the scores of each scheme on various indicators, and according to the simulation evaluation results, the target steel pile loading scheme is preferably determined as the steel pile loading scheme that meets the steel pile loading demand target information. The key nodes of the target steel pile loading scheme are extracted to identify the process nodes that have a significant impact on the loading efficiency, safety and cost. According to the complexity and actual needs of the loading scheme, the number of key nodes K is determined. The value of K depends on the specific situation and importance level of the loading process. K steel pile loading nodes are identified in turn. The K steel pile loading nodes are the key process nodes in the target steel pile loading scheme to ensure the safety of the steel pile loading process. Improve the accuracy and applicability of steel pile loading solutions, thereby ensuring the effectiveness and safety of steel pile loading.

[0026] Step S2: Identify risk factors for the K steel pile loading nodes respectively, and determine a set of risk factors for the K loading nodes.

[0027] Specifically, historical risk case data of steel pile loading projects are collected and obtained, and the risk factor data of each process node are identified and classified, and the risk factor identification model is trained in sequence. Then, the risk factors of the K steel pile loading nodes are identified through the risk factor identification model, and the risk factor information of the K steel pile loading nodes is identified. For example, at the ship positioning node, there are risk factors such as insufficient hull stability, which affects the fixing effect and improper fixing method of steel piles, and steel piles are easy to slide or tip over. The risk factors of each key node are sorted into a set to form a comprehensive and complete set of steel pile loading risk factors, which provides an analytical basis for the risk assessment of subsequent steel pile loading plans.

[0028] Step S3: Based on the target steel pile loading plan, a mapping association analysis is performed on the K loading node risk factor sets to generate a node risk factor mapping cascade tree.

[0029] Furthermore, the step of generating the node risk factor mapping cascade tree in this application also includes:

[0030] Based on the target steel pile loading scheme, a mapping relationship analysis is performed on the risk factor sets of the K loading nodes to obtain K node factor mapping relationship sets; the risk factor sets of the K loading nodes are used as risk node sets, and the risk node sets are identified by association vectors according to the K node factor mapping relationship sets to obtain a node risk factor mapping network; cascade path identification is performed on the node risk factor mapping network according to the K steel pile loading nodes to obtain a node risk cascade path set; based on the node risk cascade path set, mapping cascade conversion is performed on the risk factor sets of the K loading nodes to generate the node risk factor mapping cascade tree.

[0031] Specifically, in order to realize the intelligent risk assessment of the steel pile loading scheme, the K loading node risk factor sets are mapped and associated with each other based on the target steel pile loading scheme, and the mutual influence and association relationship between the risk factors of each loading node is clarified. First, the mapping relationship analysis of the K loading node risk factor sets is performed based on the target steel pile loading scheme. Based on the specific process and requirements of the target steel pile loading scheme, how each risk factor affects other factors, as well as the direct and indirect relationship between them, is analyzed to obtain K node factor mapping relationship sets, which describe the mapping relationship between each risk factor, including the mapping relationship type between the K node risk factors, such as positive impact, negative impact, mutual independence, etc. The K loading node risk factor sets are used as risk node sets, and the risk node sets are identified by association vectors according to the K node factor mapping relationship sets. One or more association factor vectors are assigned to each risk factor, which reflects the strength and direction of association between each node risk factor and other factors. The risk nodes are connected through association vectors to form a node risk factor mapping network, which intuitively shows the mapping relationship between each node risk factor.

[0032] According to the K steel pile loading nodes, the node risk factor mapping network is identified by cascading paths to evaluate the diffusion scope and impact of each node risk. According to the order and logical relationship of the K steel pile loading nodes, a depth-first search is performed in the node risk factor mapping network to identify all possible cascade paths, and all identified cascade paths are organized into a node risk cascade path set. Based on the node risk cascade path set, the K loading node risk factor set is mapped and cascaded, including converting the risk factors in the path and their mapping relationships into nodes and branches in a tree structure. Through the tree structure conversion, a node risk factor mapping cascade tree is generated. The node risk factor mapping cascade tree clearly and intuitively shows how risk factors propagate from one node to another, as well as the risk diffusion path in the entire steel pile loading process. By analyzing and mapping the risk factors in the target steel pile loading scheme, a mapping network and cascade tree of risk factors are constructed, which can intuitively and deeply understand the complex relationship between node risk factors, thereby improving the evaluation accuracy and efficiency of the risk coefficient of the loading scheme.

[0033] Step S4: using the node risk factor mapping cascade tree to perform risk accumulation quantification on the K loading node risk factor sets to obtain a target loading solution risk coefficient.

[0034] Furthermore, the steps of obtaining the risk factor of the target shipping plan also include:

[0035] Perform an impact assessment on each branch node in the node risk factor mapping cascade tree to obtain a branch node risk factor set; perform node risk probability analysis in sequence based on the node risk factor mapping cascade tree to obtain a branch node associated risk probability set; perform risk identification on the node risk factor mapping cascade tree according to the branch node risk factor set and the branch node associated risk probability set, and establish a node risk transfer cascade tree; perform weighted fusion of risk factors based on the node risk transfer cascade tree, and accumulate to obtain the target shipping plan risk coefficient.

[0036] Furthermore, the step of obtaining the risk probability set associated with the branch nodes in this application further includes:

[0037] Perform an occurrence probability assessment on each branch node in the node risk factor mapping cascade tree to obtain a branch node occurrence probability set; perform a next-level impact analysis on each branch node in the node risk factor mapping cascade tree in turn to obtain a branch node level-associated impact probability set and a node level impact coefficient set; hierarchically superimpose the branch node level-associated impact probability set according to the node level impact coefficient set to obtain a branch node level impact additional probability set; perform a gain analysis on the branch node occurrence probability set based on the branch node level impact additional probability set to obtain the branch node associated risk probability set.

[0038] Specifically, the node risk factor mapping cascade tree is used to quantify the risk accumulation of the K loading node risk factor sets. First, the impact degree of each branch node in the node risk factor mapping cascade tree is evaluated. Then, the risk impact degree of each branch node is evaluated through expert scoring or historical data analysis. The evaluation results are converted into specific risk factor values ​​to obtain the corresponding branch node risk factor sets. These values ​​can represent the relative importance or potential destructive power of the nodes in risk transfer.

[0039] Based on the node risk factor mapping cascade tree, node risk probability analysis is performed in sequence. First, the occurrence probability of each branch node in the node risk factor mapping cascade tree is evaluated, and the occurrence probability of each risk factor is predicted according to historical data experience to obtain the corresponding branch node occurrence probability set. Considering the transmission effect of risk factors between levels, the next path level impact analysis is performed on each branch node in the node risk factor mapping cascade tree in sequence, and the associated impact probability of each branch node on the next level node is calculated to obtain the branch node level associated impact probability set, that is, the occurrence probability of each branch node on the next path level. For example, when the risk node occurs, the occurrence probability of the next associated level node will increase by 0.2; at the same time, the node level impact coefficient set is obtained, that is, the transmission attenuation degree of each branch node between levels. For example, as the path level of the risk node increases, the probability impact degree of each additional level will gradually decay by half. When it reaches the third level of the risk node, the occurrence impact probability is reduced from 0.2 to 0.1.

[0040] The branch node hierarchical association impact probability set is hierarchically superimposed according to the node hierarchical influence coefficient set, that is, the hierarchical influence coefficient is used to perform weighted superposition on the branch node hierarchical association impact probability set, quantify the impact strength between levels, and perform hierarchical superposition of probabilities to obtain the corresponding branch node hierarchical impact additional probability set, which is the additional occurrence impact probability of the node when all upper-level associated nodes of each branch node occur. Based on the branch node hierarchical impact additional probability set, the branch node occurrence probability set is subjected to gain analysis, that is, the additional probability is added to the original occurrence probability, or merged according to a certain rule to obtain the branch node associated risk probability set after additional gain.

[0041] According to the branch node risk factor set and the branch node associated risk probability set, the node risk factor mapping cascade tree is risk-marked, that is, according to the branch node risk factor set and the associated risk probability set, each node in the node risk factor mapping cascade tree is risk-marked, such as using color coding, marking risk levels, etc. After completing the risk marking, a node risk transfer cascade tree with more intuitive risks is established. Based on the node risk transfer cascade tree, the risk factors are weighted and fused, and the risk values ​​after weighted calculation are fused and accumulated to obtain the target loading scheme risk coefficient. This coefficient reflects the comprehensive risk level that may be faced during the entire steel pile loading process. A comprehensive and systematic quantitative assessment of the risks in the target steel pile loading scheme is achieved, and the accuracy and efficiency of risk assessment are improved.

[0042] Step S5: Based on the risk coefficient of the target loading scheme, risk area identification and generation cause analysis are performed on the target steel pile loading scheme to determine the generation cause parameters of the loading risk.

[0043] Specifically, after obtaining the risk coefficient of the target loading scheme, the risk area identification and generation cause analysis of the scheme are carried out to determine the main sources and specific causes of risks in the loading process, so as to formulate effective risk mitigation measures. First, the risk coefficient in the node risk transfer cascade tree is mapped back to the original loading process diagram, and the areas or nodes with higher risk coefficients are marked. According to the distribution of risk coefficients, the loading process is divided into different risk areas, which can be specific operation links, equipment areas or time stages. Then, each risk area is evaluated in detail, including risk type, impact range, potential consequences, etc. Starting from the nodes or areas with higher risk coefficients in the node risk factor mapping cascade tree, trace back to the source of risk factors, sort out the causal relationship between risk factors, determine which factors are direct, which are indirect, and the interaction relationship between them. On the basis of causal analysis, the parameters for the generation of loading risks are determined. These parameters can be specific operating errors, equipment failures, environmental factors, management defects, etc. Each parameter should be measurable and traceable, providing an analytical basis for subsequent loading construction risk management and control, so as to improve the applicability of scheme optimization.

[0044] Step S6: construct a loading optimization strategy space, use the loading optimization strategy space to perform strategy optimization analysis on the loading risk generation cause parameters, output a steel pile optimized loading plan, and perform loading optimization construction control based on the steel pile optimized loading plan.

[0045] Furthermore, the optimized loading scheme for exporting steel piles also includes the following steps:

[0046] Based on the loading optimization strategy space, a strategy optimization analysis is performed on the parameters causing the loading risk to obtain a loading strategy parameter solution space; a parameter traversal search is performed in the loading strategy parameter solution space with a preset global step length to obtain a loading strategy search control parameter set; a gradient calculation and comparison is performed on the loading strategy search control parameter set through the steel pile loading effect evaluation simulation module to determine a local strategy parameter optimization direction; a local optimization is performed in the loading strategy parameter solution space according to the local strategy parameter optimization direction until a preset convergence condition is met to determine the steel pile optimized loading scheme.

[0047] Specifically, a loading optimization strategy space is constructed through an expert group or historical loading strategy data. The loading optimization strategy space is historical steel pile loading optimization strategy data, including loading risk generation cause parameters and corresponding parameter optimization strategy data, such as loading sequence, lifting method, ship posture adjustment strategy, cargo fixing method, etc. The loading optimization strategy space is used to perform strategy optimization analysis on the loading risk generation cause parameters. First, based on the loading optimization strategy space, the loading risk generation cause parameters are analyzed for strategy optimization, and the loading risk generation cause parameters are mapped to the strategy space for strategy matching. For example, if the risk cause is the shaking of cargo during the lifting process, then the corresponding strategy parameter may be the selection of lifting equipment, lifting speed or cargo fixing method. In this way, multiple optimal or near-optimal strategy parameter combinations are obtained by matching. These combinations constitute the loading strategy parameter solution space, which is used as the strategy parameter optimization range applicable to the loading risk generation cause parameters to improve the optimization efficiency.

[0048] According to the optimization accuracy requirement, a global step size is preset to control the granularity of the search, and a parameter traversal search is performed in the loading strategy parameter solution space through the global step size to search for a set of loading strategy search control parameters in each direction in the solution space. Each control parameter in the loading strategy search control parameter set is simulated and evaluated by the steel pile loading effect evaluation simulation module to obtain a corresponding loading effect set, and then the loading effect evaluation values ​​in each direction are compared by gradient ascent calculation, and the direction with the fastest gradient ascent rate is determined as the local strategy parameter optimization direction. According to the local strategy parameter optimization direction, local optimization is performed in the loading strategy parameter solution space, and the search step size can be gradually reduced to improve the search accuracy until the preset convergence condition is met, such as the effect improvement of multiple consecutive iterations is less than a certain threshold. When the condition is met, the search is stopped, and after local optimization of the parameters, the steel pile optimized loading scheme with the best loading effect is determined. Based on the steel pile optimized loading scheme, loading optimization construction control is performed, and the optimized loading scheme is deployed in the actual roll-on / roll-off loading construction. Realize intelligent analysis and optimization of construction plans, improve the accuracy and applicability of ship loading construction plans, and thus improve the safety and construction efficiency of ship loading construction plans.

[0049] In summary, the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method provided in this application has the following technical effects:

[0050] By extracting key nodes from the target steel pile loading scheme, K steel pile loading nodes are obtained for risk factor identification, and a set of risk factors of K loading nodes is determined. Based on the target steel pile loading scheme, the set of risk factors of K loading nodes is mapped and associated, and a node risk factor mapping cascade tree is generated, so as to quantify the risk accumulation of the risk factors of the K loading nodes, obtain the target loading scheme risk coefficient, identify the risk area of ​​the target steel pile loading scheme, analyze the generation reasons, determine the generation reason parameters of loading risk, use the loading optimization strategy space to perform strategy optimization analysis on the generation reason parameters of loading risk, and output the steel pile optimized loading scheme for loading optimization construction control. Thus, the technical effect of risk identification and evaluation of the steel pile loading scheme is achieved, intelligent analysis and optimization of the construction scheme is realized, the accuracy and applicability of the loading construction scheme is improved, and the safety and construction efficiency of the loading construction scheme are improved.

[0051] Embodiment 2, based on the same inventive concept as the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method in the aforementioned embodiment, the present invention also provides a deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction system, such as Figure 3 As shown, the system comprises:

[0052] The key node extraction module 11 is used to obtain a target steel pile loading plan, extract key nodes from the target steel pile loading plan, and obtain K steel pile loading nodes.

[0053] The risk factor identification module 12 is used to identify risk factors for the K steel pile loading nodes respectively, and determine the risk factor sets of the K loading nodes.

[0054] The cascade tree generation module 13 is used to perform mapping association analysis on the K loading node risk factor sets based on the target steel pile loading plan to generate a node risk factor mapping cascade tree.

[0055] The risk accumulation and quantification module 14 is used to use the node risk factor mapping cascade tree to perform risk accumulation and quantification on the K loading node risk factor sets to obtain the target loading plan risk coefficient.

[0056] The risk cause analysis module 15 is used to identify the risk area and analyze the generation cause of the target steel pile loading plan based on the risk coefficient of the target loading plan, and determine the generation cause parameters of the loading risk.

[0057] The loading optimization construction control module 16 is used to construct a loading optimization strategy space, use the loading optimization strategy space to perform strategy optimization analysis on the loading risk generation cause parameters, output a steel pile optimization loading plan, and perform loading optimization construction control based on the steel pile optimization loading plan.

[0058] Furthermore, the key node extraction module 11 is also used for:

[0059] The target information of steel pile loading demand is obtained, wherein the target information of steel pile loading demand includes the attribute information of steel piles to be loaded and the performance parameter information of loading equipment; the SPMT loading record data set of steel piles is collected and acquired through data mining technology, and the SPMT bundle transportation process is adopted to classify and identify the SPMT loading record data set of steel piles, so as to obtain the loading process node record data set; based on the target information of steel pile loading demand, the loading process node record data set is retrieved and matched to obtain the candidate steel pile loading data set; loading effect evaluation and global comparison and optimization are performed on the candidate steel pile loading data set to determine the target steel pile loading plan.

[0060] Furthermore, the key node extraction module 11 is also used for:

[0061] Obtain a set of steel pile loading effect evaluation indicators, perform loading effect evaluation and global comparison and optimization on the candidate steel pile loading data set based on the steel pile loading effect evaluation indicator set, and determine the available steel pile loading schemes; perform demand deviation calculation and parameter tuning analysis on the available steel pile loading schemes, and obtain multiple steel pile loading optimization schemes; perform effect fitting on the steel pile SPMT loading record data set according to the steel pile loading effect evaluation indicator set, and construct a steel pile loading effect evaluation simulation module; perform simulation evaluation and optimization on the multiple steel pile loading optimization schemes based on the steel pile loading effect evaluation simulation module, and determine the target steel pile loading scheme.

[0062] Furthermore, the cascade tree generation module 13 is also used for:

[0063] Based on the target steel pile loading scheme, a mapping relationship analysis is performed on the risk factor sets of the K loading nodes to obtain K node factor mapping relationship sets; the risk factor sets of the K loading nodes are used as risk node sets, and the risk node sets are identified by association vectors according to the K node factor mapping relationship sets to obtain a node risk factor mapping network; cascade path identification is performed on the node risk factor mapping network according to the K steel pile loading nodes to obtain a node risk cascade path set; based on the node risk cascade path set, mapping cascade conversion is performed on the risk factor sets of the K loading nodes to generate the node risk factor mapping cascade tree.

[0064] Furthermore, the risk accumulation quantification module 14 is also used for:

[0065] Perform an impact assessment on each branch node in the node risk factor mapping cascade tree to obtain a branch node risk factor set; perform node risk probability analysis in sequence based on the node risk factor mapping cascade tree to obtain a branch node associated risk probability set; perform risk identification on the node risk factor mapping cascade tree according to the branch node risk factor set and the branch node associated risk probability set, and establish a node risk transfer cascade tree; perform weighted fusion of risk factors based on the node risk transfer cascade tree, and accumulate to obtain the target shipping plan risk coefficient.

[0066] Furthermore, the risk accumulation quantification module 14 is also used for:

[0067] Perform an occurrence probability assessment on each branch node in the node risk factor mapping cascade tree to obtain a branch node occurrence probability set; perform a next-level impact analysis on each branch node in the node risk factor mapping cascade tree in turn to obtain a branch node level-associated impact probability set and a node level impact coefficient set; hierarchically superimpose the branch node level-associated impact probability set according to the node level impact coefficient set to obtain a branch node level impact additional probability set; perform a gain analysis on the branch node occurrence probability set based on the branch node level impact additional probability set to obtain the branch node associated risk probability set.

[0068] Furthermore, the loading optimization construction control module 16 is also used for:

[0069] Based on the loading optimization strategy space, a strategy optimization analysis is performed on the parameters causing the loading risk to obtain a loading strategy parameter solution space; a parameter traversal search is performed in the loading strategy parameter solution space with a preset global step length to obtain a loading strategy search control parameter set; a gradient calculation and comparison is performed on the loading strategy search control parameter set through the steel pile loading effect evaluation simulation module to determine a local strategy parameter optimization direction; a local optimization is performed in the loading strategy parameter solution space according to the local strategy parameter optimization direction until a preset convergence condition is met to determine the steel pile optimized loading scheme.

[0070] The foregoing Figure 1 The various variations and specific examples of the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method in Example 1 are also applicable to the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction system in this embodiment. Through the above detailed description of the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method, technical personnel in this field can clearly know the implementation method of the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction system in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0071] This specification and drawings are merely exemplary illustrations of the present application, but the protection scope of the present application is not limited thereto. It should be noted that any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. The optimized construction method of deepwater jacket steel pile SPMT roll-on / roll-off ship loading is characterized by: The method comprises: Obtain a target steel pile loading plan, extract key nodes from the target steel pile loading plan, and obtain K steel pile loading nodes; Identify risk factors for the K steel pile loading nodes respectively to determine a set of risk factors for the K loading nodes; Based on the target steel pile loading scheme, a mapping association analysis is performed on the K loading node risk factor sets to generate a node risk factor mapping cascade tree; The node risk factor mapping cascade tree is used to perform risk accumulation quantification on the K loading node risk factor sets to obtain a target loading solution risk coefficient; Based on the risk coefficient of the target loading scheme, the target steel pile loading scheme is identified for risk areas and analyzed for generation reasons, and loading risk generation reason parameters are determined; Constructing a loading optimization strategy space, using the loading optimization strategy space to perform strategy optimization analysis on the loading risk generation cause parameters, outputting a steel pile loading optimization plan, and performing loading optimization construction control based on the steel pile loading optimization plan; Wherein, generating a node risk factor mapping cascade tree includes: Based on the target steel pile loading plan, a mapping relationship analysis is performed on the K loading node risk factor sets to obtain K node factor mapping relationship sets; Taking the K loading node risk factor sets as risk node sets, and performing association vector identification on the risk node sets according to the K node factor mapping relationship sets, to obtain a node risk factor mapping network; According to the K steel pile loading nodes, cascade path identification is performed on the node risk factor mapping network to obtain a node risk cascade path set; Based on the node risk cascade path set, the K shipping node risk factor sets are mapped and cascaded to generate the node risk factor mapping cascade tree.

2. The deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to claim 1, characterized in that: The method of obtaining the target steel pile loading plan includes: Obtaining target information of steel pile loading demand, wherein the target information of steel pile loading demand demand includes attribute information of steel piles to be loaded and performance parameter information of loading equipment; The steel pile SPMT shipping record data set is collected and acquired by using data mining technology, and the steel pile SPMT shipping record data set is classified and identified by using the SPMT bundle transportation process to obtain the shipping process node record data set; Based on the steel pile loading demand target information, the loading process node record data set is retrieved and matched to obtain a candidate steel pile loading data set; The candidate steel pile loading data set is evaluated for loading effect and globally compared and optimized to determine the target steel pile loading plan.

3. The deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to claim 2, characterized in that: The step of determining the target steel pile loading plan includes: Obtaining a set of steel pile loading effect evaluation indicators, performing loading effect evaluation and global comparison and optimization on the candidate steel pile loading data set based on the steel pile loading effect evaluation indicator set, and determining an available steel pile loading scheme; Performing demand deviation calculation and parameter optimization analysis on the available steel pile loading schemes to obtain multiple steel pile loading optimization schemes; According to the steel pile loading effect evaluation index set, the steel pile SPMT loading record data set is fitted to construct a steel pile loading effect evaluation simulation module; Based on the steel pile loading effect evaluation simulation module, the plurality of steel pile loading optimization schemes are simulated and evaluated to find the optimal solution, and the target steel pile loading scheme is determined.

4. The deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to claim 1, characterized in that: The risk factor of the target shipment plan is obtained, including: Evaluate the impact degree of each branch node in the node risk factor mapping cascade tree to obtain a branch node risk factor set; Perform node risk probability analysis in sequence based on the node risk factor mapping cascade tree to obtain a set of branch node associated risk probabilities; According to the branch node risk factor set and the branch node associated risk probability set, risk identification is performed on the node risk factor mapping cascade tree to establish a node risk transfer cascade tree; Based on the node risk transfer cascade tree, risk factors are weightedly integrated to accumulate and obtain the risk coefficient of the target loading scheme.

5. The deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to claim 4, characterized in that: The step of obtaining a set of risk probabilities associated with branch nodes includes: Performing an occurrence probability evaluation on each branch node in the node risk factor mapping cascade tree to obtain a branch node occurrence probability set; Performing next-level impact analysis on each branch node in the node risk factor mapping cascade tree in turn to obtain a branch node level associated impact probability set and a node level impact coefficient set; The branch node level association influence probability set is hierarchically superimposed according to the node level influence coefficient set to obtain a branch node level influence additional probability set; A gain analysis is performed on the branch node occurrence probability set based on the branch node level impact additional probability set to obtain the branch node associated risk probability set.

6. The deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to claim 3, characterized in that: The optimized shipping plan for exporting steel piles includes: Based on the loading optimization strategy space, a strategy optimization analysis is performed on the loading risk generation cause parameters to obtain a loading strategy parameter solution space; Perform parameter traversal search in the loading strategy parameter solution space with a preset global step size to obtain a loading strategy search control parameter set; The steel pile loading effect evaluation simulation module is used to perform gradient calculation and comparison on the loading strategy search control parameter set to determine the optimization direction of local strategy parameters; According to the optimization direction of the local strategy parameters, local optimization is performed in the loading strategy parameter solution space until the preset convergence condition is met, and the optimized loading plan for the steel piles is determined.

7. Deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction system, characterized by: The system is used to implement the deepwater jacket steel pile SPMT roll-on / roll-off ship optimization construction method according to any one of claims 1 to 6, and comprises: A key node extraction module is used to obtain a target steel pile loading plan, extract key nodes from the target steel pile loading plan, and obtain K steel pile loading nodes; A risk factor identification module is used to identify risk factors for the K steel pile loading nodes respectively and determine a risk factor set for the K loading nodes; A cascade tree generation module, used for performing mapping association analysis on the K loading node risk factor sets based on the target steel pile loading plan, and generating a node risk factor mapping cascade tree; A risk accumulation and quantification module is used to use the node risk factor mapping cascade tree to perform risk accumulation and quantification on the K loading node risk factor sets to obtain a target loading plan risk coefficient; A risk cause analysis module, used to identify risk areas and analyze generation causes of the target steel pile loading scheme based on the risk coefficient of the target loading scheme, and determine loading risk generation cause parameters; The loading optimization construction control module is used to construct a loading optimization strategy space, use the loading optimization strategy space to perform strategy optimization analysis on the parameters causing the loading risk, output a steel pile optimized loading plan, and perform loading optimization construction control based on the steel pile optimized loading plan.

Images