基于稳健回归的油液光谱分析界限值制定  

Threshold Setting of Oil Spectral Analysis Based on Robust Regression

作　　者：周平[1] 刘东风[1] 石新发[1] 李广太[1] 

机构地区：[1]海军工程大学青岛油液检测分析中心,山东青岛266012

出　　处：《润滑与密封》2010年第5期85-88,共4页Lubrication Engineering

摘　　要：利用原子发射光谱监测柴油机磨损状态时必须首先制定各磨损元素的浓度界限值。针对传统最小二乘法在制定界限值时受异常数据影响较大的局限性,引入稳健回归方法提高其抗异常点干扰的能力;通过对实际柴油机监测获得的数据进行界限值制定,结果表明,该方法避免了因异常数据干扰而导致结果偏离实际过大的问题,从而能真实准确地监测柴油机的运行状态。Concentration threshold of wear elements should be established in order to monitor diesel engine’s wear condition by using oil spectral analysis.For the limit of traditional Least-Squares method was obviously influenced by abnormal data,robust regression was introduced to improve it’s capability and resist abnormal data’s disturbing.Through setting threshold for diesel engine’s practical monitoring data,the result shows that this method can avoid the big deviation caused by abnormal data,so it can monitor diesel engine’s real running state.

关 键 词：柴油机 油液光谱分析 稳健回归 界限值 

分 类 号：TH117[机械工程—机械设计及理论]