Artificial Intelligence Minor Fault Identification Technology and Its Application in BD1 Area
Chen Kang,
Zhang Sheng,
Zhang Xuan,
Sun Desheng,
Xu Xiang,
Chen Zhigang,
Cai Yintao,
Wang Jie
Issue:
Volume 12, Issue 4, July 2023
Pages:
47-53
Received:
19 July 2023
Accepted:
14 August 2023
Published:
28 August 2023
Abstract: Traditional fault interpretation mainly relies on human-machine interaction, which has low efficiency and high human uncertainty. Coherence attribute is sensitive to the discontinuity characteristics of seismic data and can effectively identify high grade faults. The coherence algorithm has undergone three innovations: cross-correlation (C1), similarity (C2), and eigenstructure (C3). In addition to coherence, attributes such as curvature, dip angle, and ant tracking have been proposed, and the likelihood attribute has developed rapidly in recent years, which can accurately reflect larger fault structures and has certain discrimination ability for small faults. However, due to the small moment and short extension length of low grade faults, they do not necessarily exhibit discontinuous characteristics at the fault location (especially for strike-slip faults), and the traditional attributes have not achieved good results in identifying small-scale faults. With the development of artificial intelligence algorithms in the field of target detection, advanced neural networks have proven to surpass traditional attributes in identifying faults from seismic data. This article takes the BD1 area of the Sichuan Basin as an example and combines fault enhancement interpretive processing such as dip scanning, structure-guided filtering, edge-preserving filtering, and frequeency filtering with artificial intelligence algorithms and transfer learning techniques for low grade fault identification research, forming a precise and reasonable artificial intelligence low grade fault identification technology process. The results show that the artificial intelligence algorithm using a large sample library can identify low grade faults that cannot be detected by traditional methods, and the fault detection results of artificial intelligence are superior to traditional attributes in terms of noise resistance, accuracy, and computational efficiency.
Abstract: Traditional fault interpretation mainly relies on human-machine interaction, which has low efficiency and high human uncertainty. Coherence attribute is sensitive to the discontinuity characteristics of seismic data and can effectively identify high grade faults. The coherence algorithm has undergone three innovations: cross-correlation (C1), simil...
Show More
Experimental Study of a Diesel Engine Incorporating a "KALAMA" Screw and Operating on Vegetable Oils
Gounkaou Yomi Woro,
Diané Ali,
Koala Lucmane,
Daho Tizane,
Sanogo Oumar,
Béré Antoine
Issue:
Volume 12, Issue 4, July 2023
Pages:
54-60
Received:
12 August 2023
Accepted:
11 September 2023
Published:
20 September 2023
Abstract: The vegetable oil is an alternative fuel that complements or substitutes for fossil fuels. However, its use in diesel engines gives rise to a number of difficulties, especially at low engine power levels. To resolve these problems, improving the thermal conditions in the engine's combustion chamber is one of the solutions being considered. This study presents the performance and combustion parameters of a LISTER type indirect injection diesel engine incorporating a KALAMA screw (an adaptation of the engine's pre-chamber screw with a "hot spot") and using vegetable oils. The results obtained were compared with those obtained by operating the engine on diesel and oil, this time without the KALAMA screw. The results show an improvement in engine performance (specific consumption, thermal efficiency and exhaust gas temperature), particularly at low load. The reduction in excess fuel consumption (with the KALAMA screw) is of the order of 12% at loads of 13% and 26% of maximum engine power. The ignition delay and combustion times of Jatropha oil are better than, or even similar to, those obtained with diesel. The combustion phenomenology is modified by the use of the KALAMA screw. On the heat release rate curves, there was no peak in the kinetic combustion phase during the tests with the modified screw. On the other hand, the diffusion phase was comparable for all the tests. Evaluation of cyclic dispersion using the COVIMEP study shows an improvement in the regularity of combustion cycles in this type of engine incorporating the KALAMA screw.
Abstract: The vegetable oil is an alternative fuel that complements or substitutes for fossil fuels. However, its use in diesel engines gives rise to a number of difficulties, especially at low engine power levels. To resolve these problems, improving the thermal conditions in the engine's combustion chamber is one of the solutions being considered. This stu...
Show More
