This research paper presents a comprehensive experimental and statistical approach for the analysis of vibration amplitudes in a high-speed rotating shaft employing a squeeze film damper (SFD). The research combines a comprehensive analysis that connects input parameters and response parameters, with a special emphasis on vibration amplitudes along the X and Z axes. This research utilizes the rigorous procedures of Response Surface Methodology (RSM) together with a Box-Behnken design and harnesses the capabilities of Artificial Neural Network (ANN) optimization techniques. The variables under scrutiny encompass critical factors such as shaft rotational speed, extending up to 8000 rpm, oil pressure, with a range extending up to 100 bar, and various oil mix ratios, spanning from 10 % to 50 %. Various statistical measures are computed to assess the errors and coefficients of determination of the projected models. The artificial neural network (ANN) model has shown somewhat reduced prediction errors and a greater coefficient of determination compared to the Response Surface Methodology (RSM) for both the x and z axes of vibration amplitude. The values of mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R-squared) are found for both x and z axes from RSM (3.50, 3.77), (4.50, 4.72), and (0.81, 0.79), (1.88, 1.70), (2.41, 2.12), and (0.94, 0.95), respectively, using the ANN model. The overall mean absolute percentage error (MAPE) from the ANN model of both the x and z axes (9.73 %, 9.38 %) is found to be lower compared to the RSM model (18.18 %–20.50 %). The conclusive research reveals that the artificial neural network (ANN) prediction model outperforms the regression model based on Response Surface Methodology (RSM), exhibiting superior accuracy in predicting vibration amplitudes. The ANN approach is an excellent option for calculating vibration amplitudes in high-speed rotating shafts. Additionally, it provides significant benefits in terms of effectiveness and time economy. This research provides valuable new insights into the most efficient modeling approaches for vibration management and highlights the benefits of using Artificial Neural Networks (ANN) for predictive assessments in this context. Particle Swarm Optimization is used to minimize the vibration amplitude of the shaft along the x and z axes using experimental data.

中文翻译：

---

优化高速旋转轴振动控制：挤压油膜阻尼器的实验研究以及使用人工神经网络 (ANN) 和响应面方法 (RSM) 的比较分析

本研究论文提出了一种综合实验和统计方法，用于分析采用挤压油膜阻尼器 (SFD) 的高速旋转轴的振动幅度。该研究结合了连接输入参数和响应参数的综合分析，特别强调沿 X 轴和 Z 轴的振动幅度。这项研究利用了严格的响应面方法 (RSM) 程序和 Box-Behnken 设计，并利用了人工神经网络 (ANN) 优化技术的功能。审查的变量包括关键因素，例如轴转速（最高可达 8000 rpm）、油压（范围最高可达 100 bar）以及各种油混合比（范围从 10% 到 50%）。计算各种统计测量来评估预测模型的误差和确定系数。与响应面方法 (RSM) 相比，人工神经网络 (ANN) 模型在 x 轴和 z 轴振动幅度方面显示出一定程度的预测误差减少和更大的确定系数。从 RSM (3.50, 3.77)、(4.50, 4.72) 和 (4.50, 4.72) 中找到 x 轴和 z 轴的平均绝对误差 (MAE)、均方根误差 (RMSE) 和决定系数 (R 平方) 的值使用 ANN 模型分别为 (0.81, 0.79)、(1.88, 1.70)、(2.41, 2.12) 和 (0.94, 0.95)。与 RSM 模型 (18.18%–20.50%) 相比，x 轴和 z 轴的 ANN 模型的总体平均绝对百分比误差 (MAPE) (9.73%、9.38%) 较低。结论性研究表明，人工神经网络（ANN）预测模型优于基于响应面法（RSM）的回归模型，在预测振动幅度方面表现出卓越的准确性。 ANN 方法是计算高速旋转轴振动幅度的绝佳选择。此外，它在有效性和时间经济性方面提供了显着的好处。这项研究为振动管理最有效的建模方法提供了宝贵的新见解，并强调了在这种情况下使用人工神经网络 (ANN) 进行预测评估的好处。粒子群优化用于利用实验数据最小化轴沿 x 和 z 轴的振动幅度。