Inflatable rescue boat stability analysis and subdivision optimization method and system

Abstract

The application discloses a kind of inflatable rescue boat stability analysis and compartment optimization method and system, belong to rescue boat technical field, design multiple carrying scheme and carry out corresponding analysis to its stability characteristics, describe the statistical distribution law of rescue boat uncertainty load under complex working condition;Combining stability analysis theory analyzes the stability characteristics of inflatable rescue boat under different damage conditions and generates a large amount of simulation data according to the different damage conditions of air chamber, uses BP neural network to establish three regression models describing the relationship between inflatable boat carrying condition, damage condition and its stability, and uses it to predict the static stability curve under specific conditions;Finally, through compartment optimization and simulation data verification, the comprehensive stability of rescue boat under non-deterministic load condition is quantitatively, comprehensively and comprehensively revealed.The application uses the above-mentioned inflatable rescue boat stability analysis and compartment optimization method and system, which can provide reference for the design of inflatable rescue boat, and also plays a guiding role in practical application.

Description

Technical Field

[0001] This invention relates to the field of rescue boat technology, and in particular to a method and system for stability analysis and compartment optimization of an inflatable rescue boat. Background Technology

[0002] Inflatable rescue boats, with their superior operational capabilities, have become indispensable equipment in water rescue missions. However, the rapids and unpredictable environments encountered during rescue operations pose risks of capsizing and damage to inflatable rescue boats. The stability of a rescue boat directly affects the safety of the crew and those being rescued, and also directly impacts the efficiency and success rate of rescue operations, enabling rescuers to execute their missions more effectively. Stability studies and compartment optimization can help determine the load-bearing capacity and safe operating limits of rescue boats under different conditions, thereby reducing the occurrence of accidents.

[0003] Rescue boats are typically lightweight, so factors such as increases and decreases in load, horizontal and vertical load movement, and air chamber compartment configuration all significantly impact their buoyancy and stability. Traditional stability analysis and compartment optimization methods usually only address single operating conditions and cannot consider the influence of load increases / decreases and distribution, air chamber damage, and other complex conditions on the boat's stability. Therefore, they cannot comprehensively and accurately evaluate the overall stability of the rescue boat. Thus, there is an urgent need to propose a stability analysis and compartment optimization method for inflatable rescue boats to study the impact of different load conditions on the boat's stability, explore the changes in stability under different breach conditions, and establish relevant regression models. This will quantitatively describe the overall stability of the rescue boat under complex conditions, enhance its stability and anti-sinking ability, and provide a theoretical basis for the design, development, and stability verification of rescue boats. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for stability analysis and compartment optimization of inflatable rescue boats, which can provide a certain reference for the design of inflatable rescue boats and also play a certain guiding role in their practical application.

[0005] To achieve the above objectives, this invention provides a method for stability analysis and compartment optimization of an inflatable rescue boat, comprising the following steps:

[0006] S1. Establish a model of the total load capacity and spatial distribution of the inflatable rescue boat based on its operating conditions, and identify the optimal parameters of the model.

[0007] S2. Divide the airbags of the inflatable rescue boat into different numbers of uniformly sized air chambers, and on this basis, study the specific stability changes of the inflatable rescue boat when a certain air chamber is damaged, and solve the stability characteristic regression model.

[0008] S3. Optimize the compartments of the inflatable rescue boat based on the regression model of the relationship between the inflatable rescue boat's loading status, damage status and stability.

[0009] Preferably, step S1 includes the following steps:

[0010] S101. Establish a complete unloaded inflatable rescue boat model and conduct stability analysis;

[0011] S102. Establish complete inflatable rescue boat models under different load conditions and conduct stability analysis;

[0012] S103. Determine the optimal load-bearing parameters in the equivalent complete inflatable rescue boat model based on the stability analysis results.

[0013] S2 includes the following steps:

[0014] S201. Establish a model for different air chamber structures of inflatable rescue boats, and evaluate the probability of damage to each air chamber and the impact of damage on the performance of the rescue boat.

[0015] S202. Simulate the damage to each compartment and use a BP neural network for training and prediction.

[0016] S3 includes the following steps:

[0017] S301. Establish and predict the stability curves of inflatable rescue boats under different compartment configurations, load conditions, and damage scenarios, and conduct simulation verification.

[0018] S302. Select the compartmentalization method with good overall stability from the results and perform further optimization.

[0019] Preferably, in step S101, the existing basic model of the inflatable rescue boat is simplified, additional structures other than the main hull structure are removed, and small-scale gaps and grooves are smoothed; the relevant modules of the simulation software are used to perform stability calculations under no-load conditions.

[0020] In S102, different load conditions are set according to different weights, center of gravity positions, and gravity distributions. A basic model of the corresponding inflatable rescue boat is established, and the stability calculation of different load conditions is performed using relevant modules of simulation software.

[0021] In step S103, the optimal load condition parameters are selected based on the statistical results of the stability of the complete inflatable rescue boat under different load conditions.

[0022] Preferably, in S201, a model for dividing the different air chamber structures of the inflatable rescue boat is established, and the probability of damage to each airbag and the impact of damage on the performance of the rescue boat are evaluated. A compartment optimization model for the inflatable rescue boat with 4, 6, or 8 air chambers is established. Since the probability of airbag rupture is different in different positions, the rupture stability of airbags with high rupture probability in the front and side airbags of the rescue boat is given priority.

[0023] The impact of different air chamber ruptures on the stability of the inflatable rescue boat in S202 was analyzed by simulation software modules to calculate the stability of each air chamber rupture condition. The heel range was 0 to 90° with a step size of 10°, and the pitch angle was set to free pitch depending on the load condition.

[0024] Preferably, the BP neural network consists of a three-layer topology: an input layer, a hidden layer, and an output layer. Each layer consists of several nodes connected by weights and thresholds. The input layer is responsible for receiving and storing external signals and data. The hidden layer connects the input layer and the output layer, and can automatically learn and extract key features and patterns from the input data, providing the nonlinear modeling capability of the BP neural network. The output layer is used to store the network's response to the input signal.

[0025] Preferably, in step S301, under different compartmentation conditions and the condition of each air chamber failure, simulations are performed for various load conditions. After removing missing values ​​from the results, the data is divided into training set data and test set data. The training set data and test set data are fitted using a neural network. The predicted values ​​corresponding to the yaw angle in the range of 0 to 90° with a step size of 10° are obtained by using the established regression model prediction and software simulation respectively. The stability curve is obtained by polynomial fitting.

[0026] The stability curves of each air chamber damage under different compartmentation conditions obtained in S302 are evaluated first. The compartmentation method with good stability is selected first. Then, the economy and manufacturing difficulty are comprehensively considered for further optimization.

[0027] This invention provides a stability analysis and compartment optimization system for an inflatable rescue boat, comprising the following modules:

[0028] Model building module: Based on the operating conditions, a complete model of the inflatable rescue boat and its damage probability model are established, and the model parameters are identified;

[0029] Analysis module: Divide the air chambers of the inflatable rescue boat, use relevant modules of simulation software to perform stability calculations on the damage of each air chamber, and use a BP neural network for training and prediction;

[0030] Optimization module: Based on the stability curves of each air chamber damage under different compartmentation conditions, select the compartmentation method with good stability, and further optimize it while taking into account economy and manufacturing difficulty.

[0031] Preferably, the model building module includes:

[0032] Model building unit: Build equivalent models of complete and damaged inflatable rescue boats respectively, and determine the probability of damage;

[0033] Identify units with undetermined parameters: Determine the optimal load parameters based on load simulation of rescue boat models under different load conditions;

[0034] The analysis module includes:

[0035] Air chamber division unit: The air chambers of the inflatable rescue boat are divided according to the manufacturing process and actual use.

[0036] Stability solution unit: The stability solution of each air chamber damage is performed using relevant modules of the simulation software, and a BP neural network is used for training and prediction.

[0037] Preferably, the optimization module works as follows: by using the established regression model for prediction and software simulation, the predicted values ​​corresponding to the yaw angle in the range of 0 to 90° with a step size of 10° are obtained under the predicted working conditions. The stability curve is obtained by polynomial fitting. The stability curves of each air chamber damage under different compartmentation conditions are evaluated. First, a compartmentation method with good stability is selected. Then, the economy and manufacturing difficulty are comprehensively considered for further optimization.

[0038] Preferably, the construction process of the model building unit is as follows: the existing basic model of the inflatable rescue boat is simplified, the additional structure other than the main structure of the boat is removed, and the small-scale gaps and grooves are smoothed.

[0039] The working process of the unit for identifying undetermined parameters is as follows: using relevant modules of simulation software to perform stability calculations for the unloaded condition, using relevant modules of simulation software to perform stability calculations for different load conditions, obtaining statistical results of the stability of the complete inflatable rescue boat under different load conditions, and selecting the optimal load condition parameters.

[0040] The working process of the air chamber equalization unit is as follows: establish a different air chamber structure division model for the inflatable rescue boat, evaluate the probability of damage to each airbag and the impact of damage on the performance of the rescue boat, establish a 4-air-chamber, 6-air-chamber or 8-air-chamber inflatable rescue boat compartment optimization model, since the probability of airbag rupture is different in different positions, the rupture stability of airbags with high rupture probability in the front part and side airbags of the rescue boat is given priority.

[0041] The solution process of the stability solution unit is as follows: distinguish the impact of different air chamber failures on the stability of the inflatable rescue boat; use relevant modules of simulation software to perform stability calculations for each air chamber failure condition, with a heel range of 0 to 90°, a step size of 10°, and a pitch angle set to free pitch according to the load condition.

[0042] Therefore, the stability analysis and compartment optimization method and system for inflatable rescue boats described above can provide a certain reference for the design of inflatable rescue boats and also play a certain guiding role in their practical application.

[0043] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0044] Figure 1 This is a flowchart of an embodiment of the stability analysis and compartment optimization method and system of an inflatable rescue boat according to the present invention;

[0045] Figure 2 This is a flowchart of S1 of an embodiment of the stability analysis and compartment optimization method and system of an inflatable rescue boat according to the present invention;

[0046] Figure 3 This is a flowchart of S2 of an embodiment of the stability analysis and compartment optimization method and system of an inflatable rescue boat according to the present invention;

[0047] Figure 4 This is a flowchart of S3 of an embodiment of the stability analysis and compartment optimization method and system of an inflatable rescue boat of the present invention;

[0048] Figure 5 This is a flowchart of the BP neural network in S202 of an embodiment of the stability analysis and compartment optimization method and system of an inflatable rescue boat of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0050] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0051] Example 1

[0052] like Figures 1 to 4 As shown, this invention provides a method for stability analysis and compartment optimization of an inflatable rescue boat, comprising the following steps:

[0053] S1. Establish a model of the total load capacity and spatial distribution of the inflatable rescue boat based on its operating conditions, and identify the optimal parameters of the model; specifically including the following steps:

[0054] S101. Establish a complete unloaded inflatable rescue boat model and perform stability analysis. The existing basic model of the inflatable rescue boat was simplified by removing additional structures other than the main hull structure, and small-scale gaps, grooves, and other details were smoothed. The relevant modules of the simulation software were used to perform stability calculations under unloaded conditions.

[0055] S102. Establish complete inflatable rescue boat models under different load conditions and perform stability analysis. Based on different weights, center of gravity positions, and gravity distributions, set different load conditions, establish corresponding basic models of inflatable rescue boats, and use relevant modules of simulation software to perform stability calculations for different load conditions.

[0056] S103. Determine the optimal load-bearing parameters in the equivalent complete inflatable rescue boat model based on the stability analysis results. The optimal load-bearing parameters are selected based on the statistical results of the stability of the complete inflatable rescue boat under different load conditions.

[0057] S2. Divide the airbags of the inflatable rescue boat into different numbers of uniformly sized air chambers, and based on this, study the specific stability changes of the inflatable rescue boat when a certain air chamber ruptures, and solve the stability characteristic regression model. Specifically, this includes the following steps:

[0058] S201. Establish a model for dividing the inflatable rescue boat into different air chamber structures, and evaluate the vulnerability probability of each airbag and the impact on the performance of the rescue boat if damaged. Establish a model for dividing the inflatable rescue boat into different air chamber structures, and evaluate the vulnerability probability of each airbag and the impact on the performance of the rescue boat if damaged. Establish a compartment optimization model for inflatable rescue boats with 4, 6, or 8 air chambers. Since the probability of airbag rupture varies in different locations, priority should be given to the rupture stability of airbags with high rupture probability in the front and side airbags of the rescue boat.

[0059] S202. Simulations were performed on the damage scenarios for each compartment, using a BP neural network for training and prediction. The impact of different compartment ruptures on the stability of the inflatable rescue boat was investigated. Stability calculations were performed on each compartment rupture scenario using relevant modules of the simulation software, with a heel range of 0–90° and a step size of 10°. The trim angle was set to free trim depending on the load condition.

[0060] like Figure 5As shown, a backpropagation (BP) neural network is used for training and prediction. This network consists of three layers: an input layer, a hidden layer, and an output layer. Each layer comprises several nodes connected by weights and thresholds. The input layer receives and stores external signals and data; the hidden layer connects the input and output layers, automatically learning to extract key features and patterns from the input data and providing the nonlinear modeling capability of the BP neural network; the output layer stores the network's response to the input signal.

[0061] The constructed BP neural network has 9, 11, and 13 neurons in the input layer, respectively, and 1 neuron in the output layer. The activation functions are tansig and purelin, the training function is trainlm, the loss function is MSE, the learning rate is 0.01, the maximum number of iterations is set to 1000, and the error precision is set to 10^10. -6 Once the network is built, 80% of the simulation data is randomly divided into a training set and 20% into a prediction set. Model fitting and testing are then performed to evaluate the model's performance and generalization ability.

[0062] S3. Optimize the compartmentalization of the inflatable rescue boat based on a regression model relating the inflatable rescue boat's loading status, damage condition, and stability. This includes the following steps:

[0063] S301. Establish and predict stability curves for inflatable rescue boats under different compartment configurations, load conditions, and damage scenarios, and verify these predictions through simulation. Simulations are performed for various load conditions under different compartment configurations and damage scenarios for each air chamber. After removing missing values, the data is divided into training and test sets. Neural networks are used to fit the training and test sets, obtaining predicted values ​​for heel angles in the range of 0–90° with a step size of 10° through both the established regression model and software simulation. Stability curves are then obtained through polynomial fitting.

[0064] S302. Evaluate the stability curves of each air chamber damage under different compartmentation conditions. First, select the compartmentation method with good stability. Second, take into account the economy and manufacturing difficulty and further optimize it.

[0065] This invention provides a stability analysis and compartment optimization system for an inflatable rescue boat, comprising the following modules:

[0066] Model building module: Based on the operating conditions, establish a complete model of the inflatable rescue boat and its damage probability model, and identify the model parameters; specifically including the model building unit and the unit for identifying parameters to be determined:

[0067] Model building unit: Equivalent models of complete and damaged inflatable rescue boats are built respectively to determine the probability of damage; The model building unit simplifies the existing basic model of inflatable rescue boats, removes additional structures other than the main structure of the hull, and smooths out details such as small-scale gaps and grooves.

[0068] Identifying Units with Undetermined Parameters: Based on the load simulation of the rescue boat model under different load conditions, the optimal load parameters are determined; the units with undetermined parameters are identified by using relevant modules of the simulation software to perform stability calculations under no-load conditions, and by using relevant modules of the simulation software to perform stability calculations under different load conditions, and statistical results of the stability of the complete inflatable rescue boat under different load conditions are obtained, and the optimal load condition parameters are selected.

[0069] Analysis module: This module divides the inflatable rescue boat into air chambers, uses simulation software modules to perform stability calculations on the damage conditions of each air chamber, and employs a BP neural network for training and prediction. Specifically, it includes air chamber partitioning units and stability solution units.

[0070] Air Chamber Division Unit: Based on manufacturing and actual use, the air chambers of the inflatable rescue boat are divided. The air chamber division unit establishes a division model of different air chamber structures for the inflatable rescue boat, evaluates the vulnerability of each airbag and the impact of damage on the performance of the rescue boat, and establishes a compartment optimization model for inflatable rescue boats with 4, 6, or 8 air chambers. Since the probability of airbag rupture is different in different positions, priority is given to the rupture stability of airbags with high rupture probability in the front and side airbags of the rescue boat.

[0071] Stability solution unit: The stability of each air chamber failure is solved using relevant modules of the simulation software, and a BP neural network is used for training and prediction. The impact of different air chamber failures on the stability of the inflatable rescue boat is calculated by the relevant modules of the simulation software for each air chamber failure. The heel range is 0 to 90° with a step size of 10°, and the pitch angle is set to free pitch according to the load condition.

[0072] Optimization Module: Based on the obtained stability curves of each chamber failure under different compartmentation conditions, a compartmentation method with good stability is selected, and further optimization is carried out while comprehensively considering economic factors and manufacturing difficulty. Through the established regression model prediction and software simulation, predicted values ​​corresponding to the heel angle in the predicted operating conditions within the range of 0–90° with a step size of 10° are obtained, and the stability curve is obtained through polynomial fitting. The obtained stability curves of each chamber failure under different compartmentation conditions are evaluated. First, a compartmentation method with good stability is selected; second, further optimization is carried out while comprehensively considering economic factors and manufacturing difficulty.

[0073] The present invention can be applied in the following embodiments, and in the following embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof:

[0074] A computer program for implementing the stability analysis and compartment optimization method for the inflatable rescue boat in the preferred embodiment described above.

[0075] An information data processing terminal for implementing the stability analysis and compartment optimization method for the inflatable rescue boat in the above preferred embodiment.

[0076] A computer-readable storage medium includes instructions that, when executed on a computer, cause the computer to perform the stability analysis and compartment optimization method for an inflatable rescue boat as described in the preferred embodiment above.

[0077] When implemented entirely or partially as a computer program product, the computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, all or part of the flow or function according to embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., a solid-state disk (SSD)).

[0078] Therefore, the stability analysis and compartment optimization method and system for inflatable rescue boats described above can provide a certain reference for the design of inflatable rescue boats and also play a certain guiding role in their practical application.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An air-foiled rescue boat stability analysis and subdivision optimization method, characterized in that: Includes the following steps: S1. Establish a model of the total load capacity and spatial distribution of the inflatable rescue boat based on its operating conditions, and identify the optimal parameters of the model. S2. Divide the airbags of the inflatable rescue boat into different numbers of uniformly sized air chambers, and on this basis, study the specific stability changes of the inflatable rescue boat when a certain air chamber is damaged, and solve the stability characteristic regression model. S3. Optimize the compartment layout of the inflatable rescue boat based on the regression model of the relationship between the inflatable rescue boat's loading status, damage status and stability. S1 includes the following steps: S101. Establish a complete unloaded inflatable rescue boat model and conduct stability analysis; S102. Establish complete inflatable rescue boat models under different load conditions and conduct stability analysis; S103. Determine the optimal load-bearing parameters in the equivalent complete inflatable rescue boat model based on the stability analysis results. In step S101, the existing basic model of the inflatable rescue boat is simplified, additional structures other than the main hull structure are removed, and small-scale gaps and grooves are smoothed; the relevant modules of the simulation software are used to perform stability calculations under no-load conditions. In S102, different load conditions are set according to different weights, center of gravity positions, and gravity distributions. A basic model of the corresponding inflatable rescue boat is established, and the stability calculation of different load conditions is performed using relevant modules of simulation software. In S103, the optimal load condition parameters are selected based on the statistical results of the stability of the complete inflatable rescue boat under different load conditions. S3 includes the following steps: S301. Establish and predict the stability curves of inflatable rescue boats under different compartment configurations, load conditions, and damage scenarios, and conduct simulation verification. S302. Select the compartmentalization method with good overall stability from the results and perform further optimization; In S301, under different compartmentation conditions and the damage of each air chamber, simulations are performed for various load conditions. After removing missing values ​​from the results, the data is divided into training set data and test set data. The training set data and test set data are fitted using a neural network. The predicted values ​​corresponding to the yaw angle in the range of 0~90° with a step size of 10° are obtained by using the established regression model prediction and software simulation respectively. The stability curve is obtained by polynomial fitting. The stability curves of each air chamber damage under different compartmentation conditions obtained in S302 are evaluated first. The compartmentation method with good stability is selected first. Then, the economy and manufacturing difficulty are comprehensively considered for further optimization.

2. The method according to claim 1, wherein: S2 includes the following steps: S201. Establish a model for different air chamber structures of inflatable rescue boats, and evaluate the probability of damage to each air chamber and the impact of damage on the performance of the rescue boat. S202. Simulate the damage to each compartment using a BP neural network for training and prediction.

3. The method according to claim 2, wherein: In S201, a model for dividing the different air chamber structures of the inflatable rescue boat is established to evaluate the vulnerability probability of each airbag and the impact of damage on the performance of the rescue boat. A compartment optimization model for inflatable rescue boats with 4, 6, or 8 air chambers is established. Since the probability of airbag rupture is different in different positions, the rupture stability of airbags with high rupture probability in the front and side airbags of the rescue boat is given priority. The impact of different air chamber ruptures on the stability of the inflatable rescue boat in S202 was analyzed by simulation software modules to calculate the stability of each air chamber rupture condition. The heel range was 0~90° with a step size of 10°, and the pitch angle was set to free pitch depending on the load condition.

4. The method according to claim 2, wherein: The BP neural network consists of a three-layer topology: an input layer, a hidden layer, and an output layer. Each layer comprises several nodes connected by weights and thresholds. The input layer receives and stores external signals and data. The hidden layer connects the input and output layers, automatically learns and extracts key features and patterns from the input data, and provides the nonlinear modeling capability of the BP neural network. The output layer stores the network's response to the input signal.

5. A stability analysis and subdivision optimization system for use in a method of stability analysis and subdivision optimization of an inflatable rescue boat according to any one of claims 1-4, characterized in that, Includes the following modules: Model building module: Based on the operating conditions, a complete model of the inflatable rescue boat and its damage probability model are established, and the model parameters are identified; Analysis module: Divide the air chambers of the inflatable rescue boat, use relevant modules of simulation software to perform stability calculations on the damage of each air chamber, and use a BP neural network for training and prediction; Optimization module: Based on the stability curves of each air chamber damage under different compartmentation conditions, select the compartmentation method with good stability, and further optimize it while taking into account economy and manufacturing difficulty.

6. An inflatable rescue boat stability analysis and subdivision optimization system according to claim 5, characterized in that: The model building module includes: Model building unit: Build equivalent models of complete and damaged inflatable rescue boats respectively, and determine the probability of damage; Identify units with undetermined parameters: Determine the optimal load parameters based on load simulation of rescue boat models under different load conditions; The analysis module includes: Air chamber division unit: The air chambers of the inflatable rescue boat are divided according to the manufacturing process and actual use. Stability solution unit: The stability solution of each air chamber damage is performed using relevant modules of the simulation software, and a BP neural network is used for training and prediction.

7. The system according to claim 5, wherein: The optimization module works as follows: by using the established regression model for prediction and software simulation, the predicted values ​​corresponding to the yaw angle in the range of 0~90° with a step size of 10° are obtained under the predicted working conditions. The stability curve is obtained by polynomial fitting. The stability curves of each air chamber damage under different compartmentation conditions are evaluated. First, the compartmentation method with good stability is selected. Then, the economy and manufacturing difficulty are comprehensively considered for further optimization.

8. The system according to claim 6, wherein: The construction process of the model building unit is as follows: the existing basic model of the inflatable rescue boat is simplified, the additional structure other than the main structure of the boat is removed, and the small-scale gaps and grooves are smoothed. The working process of the unit for identifying undetermined parameters is as follows: using relevant modules of simulation software to perform stability calculations for the unloaded condition, using relevant modules of simulation software to perform stability calculations for different load conditions, obtaining statistical results of the stability of the complete inflatable rescue boat under different load conditions, and selecting the optimal load condition parameters. The working process of the air chamber equalization unit is as follows: establish a different air chamber structure division model for the inflatable rescue boat, evaluate the probability of damage to each airbag and the impact of damage on the performance of the rescue boat, establish a 4-air-chamber, 6-air-chamber or 8-air-chamber inflatable rescue boat compartment optimization model, since the probability of airbag rupture is different in different positions, the rupture stability of airbags with high rupture probability in the front part and side airbags of the rescue boat is given priority. The solution process of the stability solution unit is as follows: distinguish the impact of different air chamber failures on the stability of the inflatable rescue boat; use relevant modules of simulation software to perform stability calculations for each air chamber failure condition, with a heel range of 0~90°, a step size of 10°, and a pitch angle set to free pitch according to the load condition.

Images