Wyniki wyszukiwania - BazTech

1

Anomaly detection in a cutting tool by k-means clustering and support vector machines

Lahrache A., Cocconcelli M., Rubini R.

Diagnostyka

|

2017

|

Vol. 18, No. 3

21--29

EN

This paper concerns the analysis of experimental data, verifying the applicability of signal analysis techniques for condition monitoring of a packaging machine. In particular, the activity focuses on the cutting process that divides a continuous flow of packaging paper into single packages. The cutting process is made by a steel knife driven by a hydraulic system. Actually, the knives are frequently substituted, causing frequent stops of the machine and consequent lost production costs. The aim of this paper is to develop a diagnostic procedure to assess the wearing condition of blades, reducing the stops for maintenance. The packaging machine was provided with pressure sensor that monitors the hydraulic system driving the blade. Processing the pressure data comprises three main steps: the selection of scalar quantities that could be indicative of the condition of the knife. A clustering analysis was used to set up a threshold between unfaulted and faulted knives. Finally, a Support Vector Machine (SVM) model was applied to classify the technical condition of knife during its lifetime.

2

Effectiveness of the spatial acceleration modulus for rolling elements bearing fault detection

Cotogno M., Cocconcelli M., Rubini R.

Diagnostyka

|

2013

|

Vol. 14, No. 4

27--34

EN

Rolling Elements Bearing (REB) condition monitoring is mainly based on the analysis of acceleration (vibration) signal in the load direction. This is one of the three components of the acceleration vector in 3D space: the main idea of this paper is the recovery of additional fault information from the other two acceleration vector components by combining them to obtain the modulus of the spatial acceleration (SAM) vector. The REB diagnostic performances of the SAM are investigated and compared to the load direction of vibration by means a rough estimator of the “Signal-to-Noise” Ratio and the Spectral Kurtosis. The SAM provides a higher SNR than the single load direction. Finally, Spectral Kurtosis driven Envelope analysis is performed for further comparison of the two signals: its results highlight that demodulation of the SAM isn’t stricly necessary to extract the fault features, which are already available in the raw signal spectrum.

3

A window based method to reduce the end-effect in Empirical Mode Decomposition

Cotogno M., Cocconcelli M., Rubini R.

Diagnostyka

|

2013

|

Vol. 14, No. 1

3--10

EN

Empirical Mode Decomposition technique (EMD) is a recent development in non-stationary and non-linear data analysis. It is an algorithm which adaptively decomposes the signal in the sum of Intrinsic Mode Functions (IMFs) from which the instantaneous frequency can be easily computed. EMD has proven its effectiveness but is still affected from various problems. One of these is the “end-effect”, a phenomenon occurring at the start and at the end of the data due to the splines fitting on which the EMD is based. Various techniques have been tried to overcome the end-effect, like different data extension or mirroring procedures at the data boundary. In this paper we made use of the IMFs orthogonality property to apply a symmetrical window to the data before EMD for end-effect reduction. Subsequently the IMFs are post-processed to compensate for data alteration due to windowing. The simulations show that IMFs obtained with this method are of better quality near the data boundaries while remaining almost identical to classical EMD ones.

4

On the detection of distributed roughness on ball bearings via stator current energy: experimental results

Curcuru G., Cocconcelli M., Immovilli F., Rubini R.

Diagnostyka

|

2009

|

nr 3(51)

17-21

EN

This paper deals with the detection of distributed roughness on ball-bearings mounted on electric motors. Most of the literature techniques focus on the early detection of localized faults on bearing (e.g. on the outer ring) in order to determine the bearing life and to plan the bearing replacing. Localized faults can be detected because they have characteristic signatures which is revealed in the frequency spectrum of the vibration signal acquired by an external sensor, e.g. accelerometer. Unfortunately other faults exist which do not have a characteristic signatures and then they could not be foreseen accurately: e.g. the distributed roughness. In this paper the motor stator current energy is proposed as a fault indicator to identify the presence of the distributed roughness on the bearing. Moreover an orthogonal experiment is set to analyse, through a General Linear Model (GLM), the dependencies of the current energy to the roughness level, and two environmental conditions: the motor velocity and the loads applied externally. ANOVA investigates the statistical significance of the considered factors.