• Energy Research
• 2021-2025close
• Closed Access close
• Embargo close
• Tsinghua University close

Reservoir classification and evaluation are critical during the oil and gas exploration and production, and traditional production forecasting often require complex methods such as reservoir modeling, which is time-consuming and will delay the E&P process. With the rapid development of artificial intelligence technology, the production forecasting method based on machine learning has become a new hot spot for research. Since the characteristics of various reservoirs are different, it is difficult for conventional machine learning models to meet the required accuracy due to a large number of unknowns. In this paper, we proposed an improved hierarchical XGBoost (h-XGBoost) modeling method, which can effectively extract the features of different reservoirs and build a hierarchical data model. The study is conducted on tight conglomerates reservoir at the Mahu area in Xinjiang, and the results verify the effectiveness of the method.

Abstract In the study, a three-dimensional CFD simulating model coupling with reasonable turbulent model and reduced chemical kinetic mechanism was established and validated. The auto-ignition development and knocking characteristics of a downsized spark-ignition (SI) gasoline rotary engine (RE) under different boosted conditions were numerically investigated. Results showed that as inlet pressure increased from 1.12 bar to 1.16 bar, the knocking intensity (KI) of the RE was enhanced gradually, and the knocking onset was advanced. However, with the further augment of inlet pressure, the KI did not further increase due to the larger heat dissipation loss caused by high turbulent kinetic energy in the long and narrow combustion chamber of the RE. This indicated that the structure of the downsized SI RE had a certain ability of knocking suppression when inlet pressure was sufficiently boosted. The KI of the RE was more serious in the trailing part of the combustion chamber as compared to other positions due to the unidirectional flow field, especially on both sides near the end cover in the trailing part of the combustion chamber. Therefore, it was concluded that strengthening the cooling of both sides near the end cover in the trailing part of the combustion chamber may be an effective way to reduce the KI of a downsized boosted SI RE. In addition, the KI is closely related to auto-ignition development processes, e.g. end-gas auto-ignition modes. Under the mass fraction of unburned mixtures at the moment of end-gas auto-ignition, the local KI caused directly by single hot-spot auto-ignition was higher than that caused by multiple hot-spots auto-ignitions, and the local KI caused by homogeneous auto-ignition was higher than that caused by multiple hot-spots auto-ignitions.

Abstract Thermal runaway and its propagation are bottlenecks for the safe operation of lithium-ion battery systems. This study investigates the influence of characteristic thermophysical parameters during battery thermal runaway, such as the self-heating temperature (T1), triggering temperature (T2), mass loss, and critical heat transfer power (Pc), on the failure propagation behavior in a battery system. A parametric study is conducted based on a failure propagation model. This model not only captures the behavior of thermal failure, but also accounts for the changes in the thermophysical parameters before and after thermal runaway. The results of the modeling analysis demonstrate that increasing T1 and T2 can both delay the thermal runaway propagation. The delay achieved by increasing T2 is greater than that observed by increasing T1. The peak heat transfer power Pc plays a critical role in delaying the thermal runaway propagation. When the peak heat transfer power level is greater than Pc, thermal runaway propagation mainly results from heat transfer, whereas when the peak heat transfer power level is less than Pc, thermal runaway propagation mainly arises from self-heating. This study reveals the dynamic mechanism of thermal runaway propagation within a battery module, thus providing guidance for the safety design of battery systems.