The CSTH Dataset

The CSTH Simulated Benchmark Dataset is designed for time series classification and fault detection and diagnosis (FDD). It is generated using the continuous stirred tank heater (CSTH) simulation model (https://zenodo.org/records/10093059). The model represents a heating system in which hot and cold water are mixed, heated by steam, and regulated through a closed-loop control system.

The dataset consists of 9,000 multivariate time series samples, each with 200 time steps and three process variables (cold water flow, tank level, and temperature). It includes both normal operating conditions (Y=0) and faulty scenarios (Y=1), where faults are introduced through instrumentation errors. The dataset is split into: i) train.pt (70%, 6,300 samples), ii) val.pt (10%, 900 samples), and iii) test.pt (20%, 1,800 samples). This dataset is processed and ready for machine learning applications.

CSTH 仿真基准数据集（CSTH Simulated Benchmark Dataset）专为时间序列分类与故障检测与诊断（Fault Detection and Diagnosis，简称FDD）任务设计。该数据集基于连续搅拌槽加热器（continuous stirred tank heater，CSTH）仿真模型（https://zenodo.org/records/10093059）生成，该模型所表征的加热系统将冷、热水混合后通过蒸汽加热，并由闭环控制系统进行调节。

该数据集共包含9000组多变量时间序列样本，每组样本含200个时间步长与3个过程变量：冷水流量、槽罐液位及温度。数据集涵盖正常运行工况（Y=0）与故障场景（Y=1）两类样本，其中故障通过仪表误差引入。该数据集划分为三部分：i）train.pt（训练集，占比70%，共计6300组样本），ii）val.pt（验证集，占比10%，共计900组样本），以及iii）test.pt（测试集，占比20%，共计1800组样本）。该数据集已完成预处理，可直接应用于机器学习相关任务。

搜集汇总

背景与挑战

背景概述

The CSTH Dataset是一个专为时间序列分类和故障检测与诊断设计的模拟数据集，包含9,000个多变量时间序列样本，涵盖正常和故障操作条件，适用于机器学习应用。数据集已分为训练、验证和测试集，便于直接使用。