基于量子迭代混沌的涡流搜索算法预测锅炉飞灰含碳量

Prediction of Carbon Content in Boiler Fly Ash Based on Quantum and Iterative Chaos Vortex Search Algorithm

为了准确建立锅炉飞灰含碳量预测模型,首先提出了基于量子比特的Bloch球面坐标编码和迭代混沌映射的改进涡流搜索(I-VS)算法,然后对I-VS算法、涡流搜索(VS)算法、粒子群优化(PSO)算法、正余弦(SCA)算法和樽海鞘群(SSA)算法的性能进行比较。基于某热电厂300 MW循环流化床锅炉现场运行数据,采用I-VS算法优化并行感知机的极端学习机(PELM),得到飞灰含碳量的综合预测模型(即I-VS-PELM模型)。最后将I-VS-PELM模型的预测结果与PELM、PSO-PELM、SCA-PELM、SSA-PELM和VS-PELM模型的预测结果进行比较。结果表明:与其他模型相比,I-VS-PELM模型具有更高的预测精度和更好的泛化性能,能更准确地预测锅炉飞灰含碳量。

To accurately predict the carbon content in boiler fly ash,an improved vortex search(I-VS)algorithm was proposed based on Bloch coordinates and iterative chaos mapping,following which,a performance comparison was conducted among the original vortex search(VS)algorithm,I-VS algorithm,particle swarm optimization(PSO)algorithm,sine cosine algorithm(SCA)and salp swarm algorithm(SSA).Based on the operation data of a 300 MW circulating fluidized bed boiler,the I-VS algorithm was used to optimize the extreme learning machine with parallel layer perception(PELM)to form the I-VS-PELM model for prediction of carbon content in fly ash.The prediction results of I-VS-PELM were then compared with those of PELM,PSO-PELM,SCA-PELM,SSA-PELM and VS-PELM.Results show that,compared with other models,the I-VS-PELM model has not only higher prediction precision,but also better generalization ability,which could then be used to effectively predict the carbon content in boiler fly ash.