一种油液不确定状态的信度表征与状态识别的方法,对油液监测数据进行归一化处理,获得油液指标监测数据;根据油液的属性状态﹐从好到坏划分为N个状态等级;对油液指标监测数据进行模糊评估;对评估结果进行概率赋值,得到某个属性隶属于每一个状态等级的联合概率，最终形成一个综合的属性状态,即模糊隶属度;将模糊隶属度作为证据推理ER的证据,根据不同属性状态的权重计算每条证据的不确定度,应用证据推理ER算法实现油液不确定状态的信度表征;制定油液状态证据推理结果判定标准,实现油液状态的识别,本发明解决了多指标油液监测过程中,由于多指标信息不一致导致油液状态表征困难及评估结果不确定性大的问题。

A method for confidence characterization and state identification of oil fluid uncertainty states,normalizing the oil fluid monitoring data to obtain oil fluid indicator monitoring data;dividing the oil fluid into N state classes from good to bad according to their attribute states;fuzzy evaluating the oil fluid indicator monitoring data;probabilistically assigning values to the evaluation results to obtain the joint probability of an attribute belonging to each state class,finally forming a The fuzzy affiliation degree is used as the evidence for the evidence inference ER, and the uncertainty of each piece of evidence is calculated according to the weights of different attribute states, and the evidence inference ER algorithm is applied to achieve the confidence characterization of the uncertain state of oil; the judgment standard of the oil state evidence inference result is formulated to achieve the identification of the oil state, and the invention solves the problem of oil state characterization due to the inconsistent information of multiple indicators in the process of multi-indicator oil monitoring. This invention solves the problem of difficult oil state characterization and large uncertainty of evaluation results due to inconsistent information in the process of multi-indicator oil monitoring.