xpertsystems/oil019-sample

OIL-019是一个合成炼油厂过程数据集的免费预览版本，由XpertSystems.ai提供，专为炼油厂过程的机器学习研究设计。该数据集模拟了下游炼油操作，包括蒸馏塔、流体催化裂化（FCC）、PID控制循环、热交换器网络、报警事件、混合操作和炼油厂标签。它覆盖了30个炼油厂、360个过程单元，涉及7种单元类型（如CDU、VDU、FCC、加氢裂化器、焦化器、重整器和加氢处理器），并通过8个CSV文件共包含210,820行数据。数据集用于支持蒸馏塔ML、FCC转换建模、PID控制循环分析、热交换器污垢预测、混合优化和报警管理ML等应用。数据生成基于行业标准（如UOP/Mobil FCC手册、API 660、TEMA标准、ASTM D2699、ISA-18.2等），并通过10个指标校准，确保工业真实性。注意，这是一个样本版本，存在一些限制，例如部分单元类型缺少详细表格、标签无特征耦合等，适用于研究而非实际运营决策。

OIL-019 is a free, schema-identical preview of XpertSystems.ais enterprise refinery process dataset for distillation column ML, FCC conversion modeling, PID control loop analytics, heat exchanger fouling prediction, blending optimization, and alarm management ML. The sample covers 30 refineries with 360 process units across 7 unit types, with 210,820 rows linked across 8 tables. It is the first downstream (refining) SKU in the XpertSystems Oil & Gas catalog, complementing upstream and midstream SKUs. The dataset is calibrated using industry standards such as UOP/Mobil FCC handbook, API 660, TEMA Standards, ASTM D2699, and ISA-18.2, with validation achieving a Grade A+ score. Note that this is a sample product with limitations, including missing detail tables for some unit types and feature decoupling in labels, intended for ML research rather than live operational decisions.