汽轮机典型支撑轴承流场分布特性与机组状态评估数据集

本数据集聚焦于汽轮机典型支撑轴承流场分布特性与机组状态评估，包含数值模拟计算与机组实测运行两类核心数据。模拟数据源于基于典型结构图纸建立的三维数值模型，涵盖压力场、相场分布及承载力等物理量；实测数据采集自厂级实时监控系统，包含机组负荷、振动、主蒸汽温压等关键时序指标。数据集采用有限体积法进行流场模拟，并结合深度学习技术处理时序数据 。数据与模型紧密关联：数据集提供了配套的预测模型及数据预处理脚本，运行数据作为模型的输入进行特征提取与训练，模型则用于实现状态评估与振动预测。本数据集实现了微观轴承流场机理与宏观机组运行规律的有机结合，不仅揭示了复杂工况下的流体动力学特性，更为汽轮机组的故障诊断、状态评估及振动预测研究提供了高精度、多维度的基础支撑。This dataset focuses on the flow field distribution characteristics of typical support bearings for steam turbines and steam turbine unit condition assessment, including two core types of data: numerical simulation results and field-measured operating data. The simulation data is derived from a 3D numerical model constructed based on typical structural drawings, covering physical quantities such as pressure field, phase field distribution and load capacity. The measured data is collected from the plant-level real-time monitoring system, including key time-series indicators such as unit load, vibration, main steam temperature and pressure. The dataset adopts the Finite Volume Method (FVM) for flow field simulation, and combines deep learning technologies to process time-series data. The data is closely correlated with the models: the dataset provides supporting prediction models and data preprocessing scripts. Operating data serves as the input of the models for feature extraction and training, while the models are utilized to realize condition assessment and vibration prediction. This dataset organically integrates the micro-scale bearing flow field mechanism and the macro-scale operating rules of steam turbine units. It not only reveals the hydrodynamic characteristics under complex working conditions, but also provides high-precision, multi-dimensional fundamental support for research on fault diagnosis, condition assessment and vibration prediction of steam turbine units.

搜集汇总

背景与挑战

背景概述

该数据集整合了汽轮机典型支撑轴承的数值模拟数据与机组实测运行数据，旨在分析其流场分布特性并评估机组状态。它结合了有限体积法模拟和深度学习技术，为故障诊断和振动预测提供了多维度数据与模型支持。