- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Machine learning analysis on stability of perovskite solar cells
摘要： In this work, a dataset containing long-term stability data for 404 organolead halide perovskite cells was constructed from 181 published papers and analyzed using machine-learning tools of association rule mining and decision trees; the effects of cell manufacturing materials, deposition methods and storage conditions on cell stability were investigated. For regular cells, mixed cation perovskites, multi-spin coating as one-step deposition, DMF t DMSO as precursor solution and chlorobenzene as anti-solvent were found to have positive effects on stability; SnO2 as ETL compact layer, PCBM as second ETL, inorganic HTLs or HTL-free cells, LiTFSI t TBP t FK209 and F4TCNQ as HTL additives and carbon as back contact were also found to improve stability. The cells stored under low humidity were found to be more stable as expected. The degradation was slightly faster in inverted cells under humid condition; the use of some materials (like mixed cation perovskites, PTAA and NiOx as HTL, PCBM t C60 as ETL, and BCP interlayer) were found to result in more stable cells.
关键词： Perovskite solar cells,Knowledge extraction,Machine learning,Association rule mining,Data mining,Stability
更新于2025-09-11 14:15:04
-
[IEEE 2018 37th Chinese Control Conference (CCC) - Wuhan (2018.7.25-2018.7.27)] 2018 37th Chinese Control Conference (CCC) - Association Rule Mining for the Infrared Countermeasure by the PF-Growth Algorithm
摘要： To explore the main influence factors in the infrared countermeasure and reveal the effects of the combinations of the influence factors, this study provides a heuristic idea by adopting the association rule mining theory. First of all, an engagement model including the target model, flare model and missile model is constructed to show different attack situations and countermeasure modes. Meanwhile, a counter-countermeasure algorithm denoted overlap effect is proposed as a recognition approach for distinguishing the true target from the target-flare mixed signal. Then, in view of the miss distance, we separate the association rules into outer and inner levels for mining the relations between the miss distance and the countermeasure factors. Afterwards, FP-growth algorithm is introduced to unearth the association rules by using the off-line data. Finally, we thoroughly investigate the association rules and disclose the main influence factors through simulation examples.
关键词： miss distance,FP-growth algorithm,overlap effect,Infrared countermeasure,association rule mining
更新于2025-09-04 15:30:14