To improve the adaptability of the energy management strategy for mining hybrid loaders to variable cyclic operating conditions, an energy management strategy integrating Deep Q-Network (DQN) and Transfer Learning (TL), named DQN-TL, was proposed. The core idea of this method is that the inherent cyclic characteristic of the loader's V-type operation is utilized, and such repeatable patterns are regarded as extractable and reusable high-value knowledge. First, DQN is utilized by the strategy to learn and distill the general control laws for typical operating cycles in a data-rich source domain. Then, through parameter transfer, the relevant law features are introduced into the target domain model, which is then fine-tuned with a small amount of data to adapt to specific operating conditions. Finally, by establishing the intrinsic relationship between the structured cyclic characteristics of the operating conditions and transfer learning, the adaptability to complex underground conditions is improved. The simulation results show that, compared with a rule-based control strategy, the fuel consumption rate of the proposed DQN-TL strategy is 189.21 g/(kW·h), the fuel economy is improved by 13.8%, its power allocation strategy is closer to the global optimal solution, and good potential for engineering application is demonstrated.
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |