基于改进 PSO 算法的红外气体传感器温度补偿

摘要

Focused on the issue that the precision of infrared gas sensor is affected greatly by temperature, a new method is put forward for sensor temperature compensation based on Hybrid Immune Particle Swarm Optimization Algorithm of Dynamic Grouping with Adaptive Levy mutation-Least Square Support Vector Machine (DLIPSO-LSSVM). DLIPSO introduces dynamic topology Dbest mechanism into the PSO algorithm; the Levy mutation is introduced in the adaptive mutation of offspring in the IPSO to ensure the diversity, and opposition-based learning is used to train the offspring to improve the convergence speed. The DLIPSO algorithm is tested by benchmark test functions and the numerical experiment results show that the new algorithm has good convergence efficiency, high accuracy, strong global search ability and good stability. Based on the DLIPSO, the optimum parameter selection of Least Squares SVM(LS-SVM) is studied, and the temperature compensation model of infrared gas sensor is established. The numerical simulation results show that the relative error can be controlled within 5%.%针对红外型气体传感器测量精度受环境温度影响较大的问题，提出一种基于嵌入自适应列维变异的动态拓扑免疫粒子群-最小二乘支持向量机（DLIPSO-LSSVM）温度补偿算法。DLIPSO 算法在粒子群优化过程中采用动态拓扑 Dbest 机制以更好地适应粒子群进化过程；为确保粒子多样性，平衡局部搜索与全局搜索，算法嵌入自适应列维变异对粒子进行变异。利用基准测试函数对 DLIPSO 算法进行性能对比评价，仿真结果表明算法具有较强的全局搜索能力、精度高且稳定性较好。利用 DLIPSO算法对 LS-SVM 的参数进行优化，将混合算法用于实际红外气体传感器的温度补偿，实验数值结果表明算法可将补偿结果的相对误差控制在5%范围内。