Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Diagnostyka

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

A methodology for non-invasive diagnosis of diesel engines through characteristics of starter system performance

Ramírez Juan D., Romero Carlos A., Mejía Juan C., Quintero Héctor F.

Diagnostyka

2022

Vol. 23, No. 2

art. no. 2022202

In this work, a methodology to diagnose ten diesel bus engines is carried out by means of some characteristics of the starting system performance. The signals of battery voltage, electric current supplied to the starter motor and crankshaft revolutions during cold and warm engine starting processes are analysed. Characteristics and patterns of the signals that are attributable to engine compression and combustion failures are pointed out, which are related to the kilometres travelled by each vehicle after the last engine repair and the shutdown time of the engine in warm condition. It is obtained that the rise of the current required by the starter motor during the second and third compression process, and the mean crankshaft angular acceleration after the second compression process are characteristics that are related to the engine condition.

Detection of ice states from mechanical vibrations using entropy measurements and machine learning algorithms

Mejía Juan C., Quintero Héctor F., Echeverry-Correa Julián D., Romero Carlos A.

Diagnostyka

2020

Vol. 21, No. 4

87--94

Entropy measurements are an accessible tool to perform irregularity and uncertainty measurements present in time series. Particularly in the area of signal processing, Multiscale Permutation Entropy (MPE) is presented as a characterization methodology capable of measuring randomness and non-linear dynamics present in non-stationary signals, such as mechanical vibrations. In this article, we present a robust methodology based on MPE for detection of Internal Combustion Engine (ICE) states. The MPE is combined with Principal Component Analysis (PCA) as a technique for visualization and feature selection and KNearest Neighbors (KNN) as a supervised classifier. The proposed methodology is validated by comparing accuracy and computation time with others presented in the literature. The results allow to appreciate a high effectiveness in the detection of failures in bearings (experiment 1) and ICE states (experiment 2) with a low computational consumption.