面向生物氧化提金槽温度监测的数据融合策略  

Data fusion strategy for temperature monitoring in bio-oxidation gold extraction tanks

作　　者：李海龙 南新元[1] 蔡鑫[1] 侯登云 LI Hai-long;NAN Xin-yuan;CAI Xin;HOU Deng-yun(School of Electrical Engineering,Xinjiang University,Urumqi 830017,China)

机构地区：[1]新疆大学电气工程学院,新疆乌鲁木齐830017

出　　处：《计算机工程与设计》2025年第1期282-289,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(52065064、62263031);新疆维吾尔自治区高校基本科研业务费科研基金项目(XJEDU2023P025)。

摘　　要：为提高生物氧化槽温度估计的准确性,提出一种数据融合策略。利用鲁棒自适应无迹卡尔曼滤波算法对底层采集的数据进行处理,克服噪声对系统性能的影响。利用序贯自适应加权融合算法对滤波后的数据进行局部融合,保证融合结果的一致性与高精度。利用改进的斑马优化算法优化核极限学习机进行全局融合,提升算法的泛化能力与鲁棒性。实验结果表明,提出的融合方法能够提高生物氧化槽温度估计的精度,为后续的控制决策提供有力的数据保障。A data fusion strategy was proposed to improve the accuracy of temperature estimation in biological oxidation tanks.The robust adaptive unscented Kalman filtering algorithm was used to process the collected data and overcome the effects of noise on system performance.The filtered data were locally fused using the sequential adaptive weighted fusion algorithm to ensure the consistency and high accuracy of the fusion results.The improved zebra optimization algorithm was used to optimize the kernel limit learning machine for global fusion to improve the generalization ability and robustness of the algorithm.The results show that the fusion method proposed can improve the accuracy of temperature estimation in the bio-oxidation tank and provide mea-ningful data for subsequent control decisions.

关 键 词：生物氧化提金 温度监测 多传感器数据融合 无迹卡尔曼滤波 序贯分析 自适应加权融合 核极限学习机 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]