The artificial potential field approach is an efficient path planning method. However, to deal with the local-stable-point problem in complex environments, it needs to modify the potential field and increases the complexity of the algorithm. This study combines improved black-hole potential field and reinforcement learning to solve the problems which are scenarios of local-stable-points. The blackhole potential field is used as the environment in a reinforcement learning algorithm. Agents automatically adapt to the environment and learn how to utilize basic environmental information to find targets. Moreover, trained agents adopt variable environments with the curriculum learning method. Meanwhile, the visualization of the avoidance process demonstrates how agents avoid obstacles and reach the target. Our method is evaluated under static and dynamic experiments. The results show that agents automatically learn how to jump out of local stability points without prior knowledge.

No abstract

No abstract

No abstract

Bearing remaining useful life (RUL) prediction plays a key role in guaranteeing safe operation and reducing maintenance costs. In this paper, we present a novel deep learning method for RUL estimation approach through time Empirical Mode Decomposition (EMD) and Convolutional Neural Network (CNN). EMD can reveal the nonstationary property of bearing degradation signals effectively. After acquiring time-series degradation signals, namely Intrinsic Mode Functions (IMF), we can utilize the featured information as the input of Convolution layer of models. Here, we introduce an EMD-CNN model structure, which keeps the global and local information synchronously compared to a traditional CNN. In order to get a more accurate prediction, an ensemble model with several weighting methods are proposed, where the experiment indicates an improvement of performance.

The biofuel management of a biofuel-penetrated district heating system is complicated due to its association with multiple and polymorphic uncertainties. To handle uncertainties and system dynamic complexities, an inexact two-stage compound-stochastic mixed-integer programming technique is proposed, innovatively based on the integration of different uncertain optimization approaches. The proposed technique can not only address the inexact recourse problems sourced from multiple and compound uncertainties existing in the pre-regulated biofuel supply–demand match mode, but can also quantitatively analyze the conflicts between the economic target that minimizes the system cost and the risk preference that maximizes the heating service satisfaction. The developed model is applied to a real-world biofuel management case study of a district heating system to obtain the optimal biofuel management schemes subject to supply–demand, policy requirement constraints, and the financial minimization objective. The results indicate that biofuel allocation and expansion schemes are sensitive to the multiple and compound uncertainty inputs, and the corresponding biofuel-deficit change trends of three heat sources are obviously distinct with the system’s condition, varying due to the complicated interactions of the system’s components. Beyond that, a potential trade-off relationship between the heating cost and the constraint-violation risk can be obtained by observing system responses with thermalization coefficient varying.

No abstract