- 學位論文
馬達品質類別的辨識法：馬式距離測量法
Determining the motor’s quality types: Mahalanobis Distance Measurement method
摘要
本論文提出以馬氏距離測量法(MDM)分析馬達電流波形及辨識馬達的品質類別。MDM法分成馬達電流訊號處理及馬達品質類別辨識兩大部份說明。其中之一的馬達電流訊號處理，是由三個部分組成，分別為：(1)馬達信號的前置處理；(2)主要特徵點的選取；及(3)Procedure-CPSCM。此部份之用途是計算 pooled sample covariance matrix，而後提供給馬達品質類別辨識使用。另一個部份，是馬達品質類別辨識，它是由二個部分所組成，分別為：(1)馬達信號的前置處理；及(2) Procedure-MQTD。此部份之用途是決定待測試馬達的最終品質類別。辨識一個馬達的品質類別，平均所需時間約為0.5秒。經多次實驗，平均辨識正確率為99.01%。本論文提出的MDM，其優點為：高的辨識結果、簡單的數學運算、高的辨識速度、及高的可靠度。
並列摘要
This dissertation proposes a Mahalanobis Distance Measurement (MDM) method to analyze current waveform for determining the motor’s quality types. In this dissertation, some novel and efficient algorithms in two related research topics about current waveform of motor will be presented and discussed. In the first research topic, signal processing. Which consists of three major stages: (i) the preprocessing stage which is for enlarging motor current waveforms’ amplitude and eliminating noises, (ii) the qualitative features stage which is for qualitative feature selection on motor current waveforms, and (iii) Procedure-CPSCM which is for compute pooled sample covariance matrix. In the second research topic, the Procedure-MQTD which is for determining motor’s quality types using the MDM method. It can recognize defective motors and their defective types in less than 0.5 second. In the experiment, the total classification accuracy (TCA) was approximately 99.01% in average. The proposed method has the advantages of good detection results, no complex mathematic computations, hi-speed, and hi-reliability.