Piston scuffing fault and its identification in an IC engine by vibration analysis

Moosavian, Ashkan; Najafi, G.; Ghobadian, Barat; Mirsalim, Mojtaba; Jafari, Seyed Mohammad; Sharghi, Peyman

doi:10.1016/j.apacoust.2015.09.002

Cited by 58 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The fault detection in which there is no need to direct access to the faulted part has been investigated in some literature and some processes are proposed. In the articles, the fault detection is carried out using acoustic signals [2][3][4][5], vibration signals [6][7][8][9][10][11], some other types of signals [12][13][14][15], and the combination of some signals [16][17][18][19][20]. The KNN method is utilized to classify the short-circuit fault in the main winding and auxiliary coil of the single-phase induction motor using acoustic signals [2].…”

Section: Introductionmentioning

confidence: 99%

Machine‐learning approach for fault detection in brushless synchronous generator using vibration signals

Rahnama

Vahedi

Mohammad‐Alikhani

et al. 2019

IET Science, Measurement & Technology

View full text Add to dashboard Cite

In order to maintain continuous production and to avoid the maintenance cost increment in power plants, it is important to monitor the condition of equipment, especially the generator. Regarding the impossibility of direct access to rotating diodes in brushless synchronous generators, the condition monitoring of these elements is very important. In this paper, a novel fault detection method is proposed for the diode rectifier of brushless synchronous generator. At the first stage of this method, the vibration signals are recorded and feature extraction is performed by calculating the relative energy of discrete wavelet transform components. Multiclass support vector machine (MSVM) is used for classification, and the best mother wavelet and number of decomposition level are chosen based on classification performance. To enhance the performance of the classification, a modified sequential forward subset selection approach is included by which the best statistical features are selected. In this approach, besides selecting the best subset of statistical features, the classification parameter is tuned according to the selected subset to achieve the best performance. The result of the proposed method is eventually compared with those results of classification performance using conventional subset selection. Experimental results show that the proposed method can detect rectifier faults effectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine‐learning approach for fault detection in brushless synchronous generator using vibration signals

Rahnama

Vahedi

Mohammad‐Alikhani

et al. 2019

IET Science, Measurement & Technology

View full text Add to dashboard Cite

show abstract

“…In engineering practice, experienced technicians hear abnormal sounds when engines are in faulty conditions. [5][6][7] Our study aims to confirm whether a fault diagnosis system can automatically identify engine conditions and whether engines remain functional under faulty. Several methods are used to detect engine or machine conditions.…”

Section: Introductionmentioning

confidence: 99%

Auto-identification of engine fault acoustic signal through inverse trigonometric instantaneous frequency analysis

Ning

Hou

Gong

et al. 2016

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The acoustic signals of internal combustion engines contain valuable information about the condition of engines. These signals can be used to detect incipient faults in engines. However, these signals are complex and composed of a faulty component and other noise signals of background. As such, engine conditions' characteristics are difficult to extract through wavelet transformation and acoustic emission techniques. In this study, an instantaneous frequency analysis method was proposed. A new time-frequency model was constructed using a fixed amplitude and a variable cycle sine function to fit adjacent points gradually from a time domain signal. The instantaneous frequency corresponds to single value at any time. This study also introduced instantaneous frequency calculation on the basis of an inverse trigonometric fitting method at any time. The mean value of all local maximum values was then considered to identify the engine condition automatically. Results revealed that the mean of local maximum values under faulty conditions differs from the normal mean. An experiment case was also conducted to illustrate the availability of the proposed method. Using the proposed time-frequency model, we can identify engine condition and determine abnormal sound produced by faulty engines.

show abstract

“…Acoustic emission signals through transformed wavelet packets are employed to decompose the signals into different frequency ranges in order to detect valve abnormalities in a reciprocating compressor. This method believes that valve problems can be identified effectively [23]. A frequency-domain method was proposed by [24] for the on-line identification of parameters describing the torsional dynamics of internal combustion engines.…”

Section: Introductionmentioning

confidence: 99%

Classification of crankshaft remanufacturing using Mahalanobis-Taguchi system

Abu

Jamaluddin

Zakaria

2016

Int. J. Automot. Mech. Eng.

View full text Add to dashboard Cite

Remanufacturing is a process of returning a used product to at least its original performance with a warranty that is equivalent or better than that of a newly manufactured product. During a preliminary inspection on remanufacturing companies, it was found that there is no end life for crankshafts in terms of classifying it either to remanufacture, repair or reject due to limited information provided by the original equipment manufacturer. The manufacturer did not provide any information on the annual quantity produced and their specifications to the remanufacturing company for the purpose of referencing. Eventually, the distinctiveness of the remanufactured crankshaft from the original cannot be measured. Thus, the aim of this work is to classify crankshafts' end life into recovery operations based on the Mahalanobis-Taguchi System. The crankpin diameter of six engine models were measured in order to develop a scale that represents their population in a scatter diagram. It was found that on the diagram of each engine model, the left distributions from the center point belong to rejected crankshafts, the right distributions belong to re-manufacturable crankshafts, and the upper distributions belong to the repairable crankshafts. The developed scale is believed to be able to help remanufacturers instantaneously identify and match any unknown model crankshafts to its right category. The Ministry of International Trade & Industry (MITI) has established a remanufacturing policy under RMK11 and put in efforts to encourage Malaysians to venture into the remanufacturing business. Thus, this model will help the industry to understand and formulate their decision-making to sustain the end of life of their products.

show abstract

Piston scuffing fault and its identification in an IC engine by vibration analysis

Cited by 58 publications

References 18 publications

Machine‐learning approach for fault detection in brushless synchronous generator using vibration signals

Machine‐learning approach for fault detection in brushless synchronous generator using vibration signals

Auto-identification of engine fault acoustic signal through inverse trigonometric instantaneous frequency analysis

Classification of crankshaft remanufacturing using Mahalanobis-Taguchi system

Contact Info

Product

Resources

About