A thermoelectric generation (TEG) system has the weakness of relatively low thermoelectric conversion efficiency caused by heterogeneous temperature distribution (HgTD). Dynamic reconfiguration is an effective technique to improve its overall energy efficiency under HgTD. Nevertheless, numerous combinations of electrical switches make dynamic reconfiguration a complex combinatorial optimization problem. This paper aims to design a novel adaptive coordinated seeker (ACS) based on an optimal configuration strategy for large-scale TEG systems with series–parallel connected modules under HgTDs. To properly balance global exploration and local exploitation, ACS is based on ‘divide-and-conquer’ parallel computing, which synthetically coordinates the local searching capability of tabu search (TS) and the global searching capability of a pelican optimization algorithm (POA) during iterations. In addition, an equivalent re-optimization strategy for a reconfiguration solution obtained by meta-heuristic algorithms (MhAs) is proposed to reduce redundant switching actions caused by the randomness of MhAs. Two case studies are carried out to assess the feasibility and superiority of ACS in comparison with the artificial bee colony algorithm, ant colony optimization, genetic algorithm, particle swarm optimization, simulated annealing algorithm, TS, and POA. Simulation results indicate that ACS can realize fast and stable dynamic reconfiguration of a TEG system under HgTDs. In addition, RTLAB platform-based hardware-in-the-loop experiments are carried out to further validate the hardware implementation feasibility. 相似文献
Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided sel-attention network ( SGSA-Net) was proposed to weakly supervise attribute localization, without annotations of attribute-related regions. Saliency priors were integrated into the spatial attention module ( SAM ). Meanwhile,channel-wise attention and spatial attention were introduced into the network. Moreover, a weighted binary cross-entropy loss ( WCEL) function was employed to handle the imbalance of training data. Extensive experiments on richly annotated pedestrian ( RAP) and pedestrian attribute ( PETA) datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods. 相似文献
The traditional emotion–cause extraction task needs to give the exact emotion annotation contained in the document before extracting the cause. Different from this, the emotion–cause pair extraction (ECPE) task, which aims to extract emotion–cause pairs with causal relationships directly from the document, is a task proposed in the natural language processing field recently. At present, the task of ECPE is divided into two steps: emotion annotations and cause clause extraction, emotion–cause clause pair combining and filtering. In this article, we optimize these two steps. On the one hand, in the first step of ECPE, a mutual assistance single-task model proposed by us is used to replace the original multi-task model. On the other hand, the position information of the clause is added as an additional feature in the second step of ECPE. Furthermore, based on different levels of semantic features, we design three filtering models and explore their performance on ECPE tasks. The experimental results on the benchmark corpus show that our approach can make the ECPE task achieve better performance. Compared with the referenced method, F1-score is increased by 5.3%. Moreover, these optimization strategies improve the subtasks contained in ECPE to varying degrees.