船体桁架应力预测代理模型数据

船体桁架应力预测代理模型数据，可在设计阶段快速输出参数对应的应力结果，解决传统验证耗时高的问题，助力高效筛选优方案；航行中结合实时数据预判应力状态，及时预警强台风、货物偏载等引发的应力风险，避免结构故障，保障安全。1.数据收集：根据仿真模拟系统的捕捉功能，我们获得了仿真船体的结构变量；紧接着我们通过仿真测试得到了桁架应力的值2.构建高斯过程：构建代理模型对结构性能评估本质是一个回归问题的模型。将船体结构方案的设计参数作为高斯过程的输入参数，结构性能指标作为高斯过程的输出参数。通过仿真数据的训练，可得到仿真船体的代理模型3.模型预测：通过代理模型数据的估计，我们可以得到预测模型，多项式核函数是高斯过程中常用的核函数之一，可以用来建模输入变量与输出变量之间的非线性关系，当输入新型船体的结构变量时，我们就可以快速得到他的应力的数量预测值。其形式为：K(x,y)=(σ^2*<x,y>+c)^d，其中x和y是输入向量，<x,y>表示它们的内积，d是多项式的次数，σ是一个比例因子，c是一个常数项。模型训练前首先准备数据集，共有100个样本，输入变量为二维，输出变量为一维，使用随机划分的方法将数据集划分为训练集和测试集，其中，80%用于训练，剩余20%数据用于测试。经过模型训练，将测试集应用于高斯过程模型进行测试，使用MAE、MAPE、MSE、RMSE四个参考值对模型的准确性进行评估。

This dataset is designed for the surrogate model of hull truss stress prediction. It can quickly output stress results corresponding to given parameters during the design phase, solving the problem of high time consumption in traditional validation and helping efficiently screen optimal design schemes. During voyages, it can predict stress status in combination with real-time data, timely warn against stress risks caused by extreme typhoons, unbalanced cargo loading and other factors, prevent structural failures, and ensure navigation safety.
1. Data Collection: We collected the structural variables of the simulated hull via the capture function of the simulation system, and then obtained the truss stress values through simulation tests.
2. Gaussian Process Construction: Developing a surrogate model for structural performance evaluation is essentially a regression task. We take the design parameters of the hull structure scheme as the input parameters of the Gaussian process, and the structural performance indicators as the output parameters. After training on the simulation dataset, the surrogate model for the simulated hull can be obtained.
3. Model Prediction: Based on the estimation of the surrogate model data, the prediction model can be derived. The polynomial kernel function, one of the commonly used kernel functions in Gaussian processes, is capable of modeling the nonlinear relationship between input and output variables. When the structural variables of a new hull are input, the predicted stress values can be quickly obtained. Its mathematical form is: $K(x,y)=(sigma^2 cdot langle x,y
angle + c)^d$, where $x$ and $y$ are input vectors, $langle x,y
angle$ represents their inner product, $d$ is the polynomial degree, $sigma$ is a scaling factor, and $c$ is a constant term.
Before model training, the dataset was prepared with a total of 100 samples, featuring 2-dimensional input variables and 1-dimensional output variable. The dataset was randomly split into a training set and a test set, with 80% of the samples used for training and the remaining 20% for testing. After completing the model training, the test set was fed into the Gaussian process model for evaluation. The accuracy of the model was assessed using four reference metrics: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE).

搜集汇总

背景与挑战

背景概述

该数据集为船体桁架应力预测代理模型数据，包含501条CSV格式记录，涵盖桁架结构参数和应力值，用于基于高斯过程回归的代理模型训练。其应用旨在设计阶段快速预测应力以优化船体方案，并在航行中预判风险保障安全，解决传统验证耗时问题。