Photovoltaic (PV) power prediction plays a significant role in supporting the stable operation and resource scheduling of integrated energy systems. However, the randomness and volatility of photovoltaic power generation will greatly affect the prediction accuracy. Focusing on this issue, a prediction framework is proposed in this research by developing an improved sparrow search algorithm (ISSA) to optimize the hyperparameters of long short-term memory (LSTM) neural networks. The ISSA is specially designed from the following three aspects to support a powerful search performance. Firstly, the initial population variety is enriched by using an enhanced sine chaotic mapping. Secondly, the relative position of neighboring producers is introduced to improve the producer position-updating strategy to enhance the global search capabilities. Then the Cauchy–Gaussian variation is utilized to help avoid the local optimal solution. Numerical experiments on 20 test functions indicate that ISSA could identify the optimal solution with better precision compared to SSA and PSO algorithms. Furthermore, a comparative study of PV power prediction methods is provided. The ISSA-LSTM algorithm developed in this paper and five benchmark models are implemented on a real dataset gathered from the Alice Springs area in Australia. In contrast to the SSA-LSTM model, most MAE, MAPE, and RMSE values of the proposed model are reduced by 20∼60%, demonstrating the superiority of the proposed model under various weather conditions and typical seasons.

This work focuses on developing a task-driven formation framework in the presence of communication constraints for a group of nonholonomic mobile vehicles. The center of this framework is a cost function that characterizes both the task-related and the communication constraint related costs followed by a newly defined concept of compatible task and communication constraints. It is shown that, if the task and communication constraints are compatible as defined, then the formation problem can be solved as an optimization for the given cost function through a family of formation control laws obtained from off-the-shelf optimization algorithms. In particular, the gradient-like control laws can be developed to find non-unique local optimal solutions of this optimization problem under some sufficient conditions and, hence, achieve the desired formation for the underlying group of mobile vehicles with communication constraints. In order to demonstrate the effectiveness of this framework, an illustrative example is presented for the formation task of a group of vehicles under communication constraints from the field of view (FOV) of visual camera sensors. It can be observed that, although cameras are the only ways of communication, the proposed gradient-like control law can drive the group of vehicles to achieve the desired formation with guaranteed collision avoidance.

The three-ring horizontal assembly test is essential to evaluate the accumulation of manufacturing errors in shield segments. However, traditional manual assembly suffers from poor precision and low efficiency. In response to the practical demands of the tunneling industry, this article proposes a point cloud-based, automated assembly framework for shield segments. To address practical engineering challenges in the proposed assembly framework, this study proposes three innovative methods. To address the uncertainty in the pose of scanned point clouds, a unified main direction positioning method based on structural features (UMDP) is proposed to achieve unified calibration of point cloud poses. To meet the requirement of assembling discrete segments into a smooth lining ring, a joint assembly method based on curvature consistency and seam vector is presented to integrate segments into a continuous smooth ring structure. To solve the gap coupling problem in inter-ring assembly, an inter-ring assembly method based on key surface positioning and iterative adjustment (KPIA) is developed to obtain the segment pose that meets engineering standards. Experiments conducted on a Redmi G Pro 2022 laptop equipped with an AMD Ryzen 7 6800 H processor and 16 GB of RAM demonstrated that the assembly test of three rings containing 7.17 × 10 8 points could be accomplished with 180.85 s with the assembly accuracy strictly controlled within 1 mm. Thus, the proposed framework offers an efficient and practical approach to assessing segment dimensions.