各单一选线判据从原始故障数据中提取出各自需要的故障特征量并离散化。
The fault characteristic quantity with each selection method is extracted from the original data and discretized.
给出了该方法的理论分析，故障特征量的选取，神经网络设置和训练的具体步骤。
Theoretical analysis, choice of fault characteristics and practical procedure of neural network setting and training are given out.
本文着重讨论了在内燃机故障诊断中常用的故障特征量。通过理论和实验方法，对这些故障特征量的敏感性进行了分析。
This paper discusses some common fault eigenvalues in the fault diagnosis of internal combustion engines and makes analysis of this eigenvalues by using theoretical and experimental methods.
为了分析发电机组振动信号在能量和波形方面的细小变化，从而反映发电机组的早期故障趋势，提出了基于数学形态谱的故障特征量。
Fault features based on pattern spectrum were presented for analyzing tiny changes of energy and waveform of generator sets vibration and reflecting the trend of early faults.
揭示了过去人们试图把定子电流中故障特征量的大小作为电机转子断条根数多少的判据的局限性，提出了把断条引起电机的不对称性作为电机故障程度判据的新的理论。
Finally, a new theory is proposed, in which the asymmetry of the motor induced by broken bars is taken as the criterion for determination of the degree of motor faults.
因此，本文选用油中溶解气体作为故障诊断的特征量。
Thus, Dissolved Gases in oil is used as character of the fault diagnosis.
以油中溶解气体为特征量对变压器进行故障诊断是一种使用广泛而十分有效的方法。
It is a widely used and quit efficient method to use gas dissolved in oil as character to diagnose transformer fault.
电机故障特征相量的确立是进行故障诊断的前提。
The establishment of fault feature vector is a precondition to fault diagnosis.
在对采集到的信号降噪后，利用“小波包-能量”法提取特征量，并将其输入到神经网络中进行故障识别。
After noise reduction in the signal, using "wavelet packet-energy" to extract the characteristic vector and input them to the neural network for fault identification.
可以将三阶谱的峰值作为判断气阀是否漏气的一个诊断特征量，同时也为诊断内燃机气阀的早期漏气故障提供了依据。
The peak value varies in different fault conditions and it can be used as a characteristic for diagnosing leakage fault of exhaust valve, the fault in initial stages can also be diagnosed.
应用结果表明，不必进行信号预处理以提取特征量，只需要用少量的时域故障数据样本建立故障分类器。
Training the multi-fault classifier only needs a small quantity of fault data samples in time domain, and does not need signal preprocessing for extracting signal features.
最后根据故障特征表计算信息量，作出最大故障二元树，并最终确定故障产生的源头。
At last, the binary tree of the possible maximum failure is made according to the calculated information from the features of...
最后根据故障特征表计算信息量，作出最大故障二元树，并最终确定故障产生的源头。
At last, the binary tree of the possible maximum failure is made according to the calculated information from the features of...
应用推荐