2026-10-15T05:37:12Z https://www.scidb.cn/oai

10.57760/sciencedb.43355 2026-07-21T16:14:00Z

2026-07-21 An Industrial Cokemaking Coal-Blending and Coke-Quality Dataset doi:10.57760/sciencedb.43355 en This dataset provides 229 industrial cokemaking coal-blending recipes recorded by a coking plant during routine production from February 2023 to December 2025. Each record aggregates the individual coals in one blending list into 65 blend-level descriptors: mass-weighted coal-quality means (proximate indices Ad, Vdaf, Std, G; vitrinite reflectivity and active-component terms; Gieseler-fluidity characteristic temperatures; dilatometer terms), within-blend coefficients of variation, measured feed-coal properties (Mt, Ad, Vdaf, Std, G, particle-size fractions, coking temperatures), engineered interaction and polynomial terms, per-coal-type mass fractions classified by GB/T 5751, and blend cost — together with 7 measured coke-quality responses (Ad, Vdaf, Std, M10, M40, CRI, CSR). A strict temporal train/validation/test split (160/23/46, random seed 42) is provided in the `split` column. The released table is complete (no missing cells). Advanced coal-quality indicators, missing in 11.1% of individual-coal records, were imputed using training-only category and global means before list-level aggregation; plastic-layer X/Y indices and ash composition were not measured and are therefore absent. The data are desensitized list-level aggregates that cannot be inverted to recover individual coal purchase records. The dataset is intended for coal-blend quality prediction, multi-objective blend-optimization benchmarking, feature-importance analysis, and sensitivity studies under a temporal (out-of-sample) evaluation protocol. cokemaking; coal-blending; coke-quality Tao Wenjian PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank