摘要
采用指数加权移动平均(EWMA)滤波器对实际运行数据剔除野值,利用改进的自适应支持向量机(ASVM)建立远置立式敞开型制冷陈列柜性能模型,并通过动态损失系数调整而实现支持向量机的自适应.理论分析和仿真实验结果表明:与反向传播神经网络(BPNN)模型相比,AS-VM模型结构简单、运算速度快和泛化能力强;所建立的陈列柜仿真模型切实可行,优化后陈列柜的单位展示面积每日耗电量可降低20.7%.
Based on pretreatment of practical operation data, such as eliminating outliers by exponential weighted moving average （EWMA） filter, the performance model for a remote open vertical display cabinet was built up using the adaptive support vector machine （ASVM） method. Using the dynamic loss coefficient adjustment, the adaptation of the SVM was realized. Compared to the back propagation neural network model （BPNN）, the ASVM simulation model of the display cabinet was characterized by its simple structure, fast convergence speed and high generalization ability. It was revealed by the theoretic analysis and simulation result that the simulation model of a display cabinet built by ASVM method is feasible. After being validated, the power consumption of optimized display case is found to be reduced by 20. 7%.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2009年第9期1427-1431,共5页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金资助项目(50876059)
关键词
制冷陈列柜
控制
支持向量机
自适应
refrigerated display cabinet
control
support vector machine（SVM）
adaptation
