Zhang Jinwei, Zhu Xijing, Li Jing
School of Mechanical Engineering, North University of China, Taiyuan 030051, China.
Shanxi Provincial Key Laboratory of Advanced Manufacturing Technology, North University of China, Taiyuan 030051, China.
Sensors (Basel). 2024 Feb 8;24(4):1104. doi: 10.3390/s24041104.
Intelligent workshop UAV inspection path planning is a typical indoor UAV path planning technology. The UAV can conduct intelligent inspection on each work area of the workshop to solve or provide timely feedback on problems in the work area. The sparrow search algorithm (SSA), as a novel swarm intelligence optimization algorithm, has been proven to have good optimization performance. However, the reduction in the SSA's search capability in the middle or late stage of iterations reduces population diversity, leading to shortcomings of the algorithm, including low convergence speed, low solution accuracy and an increased risk of falling into local optima. To overcome these difficulties, an improved sparrow search algorithm (namely the chaotic mapping-firefly sparrow search algorithm (CFSSA)) is proposed by integrating chaotic cube mapping initialization, firefly algorithm disturbance search and tent chaos mapping perturbation search. First, chaotic cube mapping was used to initialize the population to improve the distribution quality and diversity of the population. Then, after the sparrow search, the firefly algorithm disturbance and tent chaos mapping perturbation were employed to update the positions of all individuals in the population to enable a full search of the algorithm in the solution space. This technique can effectively avoid falling into local optima and improve the convergence speed and solution accuracy. The simulation results showed that, compared with the traditional intelligent bionic algorithms, the optimized algorithm provided a greatly improved convergence capability. The feasibility of the proposed algorithm was validated with a final simulation test. Compared with other SSA optimization algorithms, the results show that the CFSSA has the best efficiency. In an inspection path planning problem, the CFSSA has its advantages and applicability and is an applicable algorithm compared to SSA optimization algorithms.
智能车间无人机巡检路径规划是一种典型的室内无人机路径规划技术。无人机可对车间的各个工作区域进行智能巡检，以解决工作区域中的问题或及时提供反馈。麻雀搜索算法（SSA）作为一种新型群智能优化算法，已被证明具有良好的优化性能。然而，SSA在迭代中后期搜索能力下降，导致种群多样性降低，从而使算法存在收敛速度慢、求解精度低以及陷入局部最优的风险增加等缺点。为克服这些困难，通过融合混沌立方映射初始化、萤火虫算法扰动搜索和帐篷混沌映射扰动搜索，提出了一种改进的麻雀搜索算法（即混沌映射-萤火虫麻雀搜索算法（CFSSA））。首先，利用混沌立方映射对种群进行初始化，以提高种群的分布质量和多样性。然后，在麻雀搜索之后，采用萤火虫算法扰动和帐篷混沌映射扰动来更新种群中所有个体的位置，使算法能够在解空间中进行全面搜索。该技术可有效避免陷入局部最优，提高收敛速度和求解精度。仿真结果表明，与传统智能仿生算法相比，优化后的算法收敛能力有了很大提高。通过最终的仿真测试验证了所提算法的可行性。与其他SSA优化算法相比，结果表明CFSSA具有最佳效率。在巡检路径规划问题中，CFSSA具有其优势和适用性，是一种相对于SSA优化算法更适用的算法。
