Papers by Keyword: Condition Monitoring

Paper TitlePage

Authors: David A. Clifton, Peter R. Bannister, Lionel Tarassenko
Abstract: A novelty detection approach to condition monitoring of aerospace gas-turbine engines is presented, providing a consistent framework for on- and off-line analysis, each with differing typical implementation constraints. On-line techniques are introduced for observing abnormality in engine behaviour during aircraft flights, and are shown to provide early warning of engine events in real-time. Off-line techniques within the same analysis framework are shown to allow the tracking of single engines and fleets of engines from ground-based monitoring stations on a flight-by-flight basis. Results are validated by comparison to conventional techniques, in application to aerospace engines and other industrial high-integrity systems.
Authors: Chun Liang Zhang, Xia Yue, Yong Tao Jiang, Wei Zheng
Abstract: The Hidden Markov Model (HMM) offers a powerful framework for temporal modeling of features extracted from time varying signals, and the Artificial Neural Network (ANN) has been widely used for pattern recognition, time series prediction, and optimization and forecasting. This paper describes a hybrid HMM/ANN approach which is a very competitive alternative to standard HMM for cutting chatter monitoring both in terms of performances and recognition accuracy. The hybrid HMM/ANN system uses ANN, usually a Multi-layer Perceptron ANN, to integrate the multi-stream inputs as feature transformation, whose goal is to take the advantages from the properties of both HMM and ANN. Experimental results show the efficiency of the hybrid system in monitoring of cutting process.
Authors: Yu Liu, Zhen Tao Wang, Zhen Dong Tan, Hong Xiang Tian
Abstract: The faults of the machines appeared suddenly usually cause to huge losing. So it’s important to monitor and analyze the condition of the machines. Now, more and more methods have been applied to condition monitoring and fault diagnoses. The spectral analysis technique has been widely used to detect the contents of abrasive metal in the lubricating oil. To mine the spectral data better, a method was put forward, which can be used to build the healthy record and reveal the important information about the operated conditions of the equipment. In the method, the similar information of the principal component in oil was obtained in the stable abrasion of the different friction pairs of equipment. The composition of mechanical and electrical equipment was also gained. The healthy record was created preliminarily according to all the information. In the malfunction detection of the equipment, cooperated with the data of the threshold of oil, the analysis results of spectra can be compared with the healthy record. So, the abnormal abrasion can be judged accurately.
Authors: Juggrapong Treetrong
Abstract: This paper proposes a new method of motor fault detection by applying the eliminated-signal as data sources for motor fault analysis. Bi-spectrum is used as a key method for processing the signal. The expectation is that the eliminated-signal may contain information for fault analysis. The spectrum and bi-spectrum of the signal are applied as signal processing methods to analyze the motor faults. The method is tested on 3 different motor conditions: healthy, stator fault, and rotor fault motor at full load condition. Based on experiments, the method can differentiate conditions clearly. They seem also to be able to measure fault severity levels by observing the change in among harmonic amplitudes.
Authors: Zhao Qian Zhu, Wen Ming Zhang, Xiao Ming Zhang, Yu Peng Shi
Abstract: This paper studied the time-domain waveform characteristics of diesel engine cylinder head vibration. The relative relationship between the various explosions of diesel engine were analyzed and compared. Seven criteria were proposed under which to achieve the time domain waveform peak identification in the absence of TDC signal. According to the criteria computer algorithms for the time domain waveform peak identification were given. The method can reduce the vibration diagnosis system using request such as can achieve misfire fault diagnosis in the absence of TDC signal.
Authors: Zhi Qiang Xu, Jian Hua Zhang, Jing Fang Ji, Xiang Jun Yu
Abstract: Due to gearbox is one of the high failure rate component in the wind turbine, the research of it has been paid wide attention in recent years. This paper reviewed the two aspects about the wind turbine gearbox. First, some signal process methods including how to determine the threshold were summarized. Then, the condition monitoring and fault diagnosis of gearbox were reviewed using the measured signals. These researches are benefited for reducing economic losses which is caused by the gearbox failure. Based on the above reviews, this paper gives some developmental direction.
Authors: Pawel Kostka, Angelos Filippatos, Robin Höhne, Werner Hufenbac
Abstract: The unique potential to integrate functional elements into fibre-reinforced components combined with the recent progress in the simulation models of composite materials provides new perspectives for reliability improvement of the next generation components. Such combination is presented on the example of a carbon-fibre reinforced composite plate with integrated vibration measurement and excitation systems. The investigated structure was consolidated in an adapted resin transfer moulding process using additional layers for positioning, contacting and isolating of the active elements. The integrated elements enable an online estimation of the structural dynamic behaviour and its damage-dependent changes.The article considers the identification problem of diagnostic models enabling a precise interpretation of the measured vibration responses. An approach based on the generation of classifiers by means of inductive machine learning algorithms is applied. At the baseline phase, modal properties are measured that correspond to the undamaged state of the structure. Using these experimental data, a simulation model of the structure was fitted by means of a mixed numerical experimental technique and used for the generation of multiple vibration patterns resulting from different mass distributions. The unique combination of experimental and numerical results enables a generation of high resolved learning datasets for machine learning algorithms using a minimum amount of experimental data. The verification of the estimated classifiers by means of the achievable diagnostic performance is firstly conducted theoretically using standardised validation techniques and a high performance is identified. Then, at the inspection phase, the performance of the whole diagnostic system is additionally experimentally confirmed based on the dynamic response resulting from different unseen structural disturbances.
Authors: Mohd Zaki Nuawi, Nor Kamaliana Khamis, Z. Zali, Wan Mohd Faizal Wan Mahmood, Shahrum Abdullah, Zulkifli Mohd Nopiah
Abstract: Various condition monitoring techniques were applied during a laboratory engine test in order to understand the wear processes occurring and to determine a suitable method which could be applicable to the detection and diagnosis of abnormal engine condition in practice. The goal of the research presented in this study is to monitor the internal combustion engine block. The proposed engine block approach is based on measuring and monitoring the engine operation in variable speed and torque using Piezoelectric Sensor. However, it normally requires analyzing the obtained signal for providing valuable information. This research involves two main procedures including data collecting as well as data analyzing. Data collecting is processes of sensor attach, run the engine and record the data while data analyzing is translating the data using data acquisition and filtering by fast furrier transform and analyzing by I-kaz and MZN methods.
Authors: Zhong Sheng Wang
Abstract: The aircraft sudden failures seriously affect the flight safety of aircraft, and the revelation of the evolution mechanism of aircraft sudden failures is of far reaching importance to the realization of evolution law of sudden failure, and the improvement of the safety and reliability of aircraft. By utilizing the dissipative structure theory, this paper carries out the analysis and research on the characteristics, causes and conditions of aircraft sudden failures from the perspective of mass and energy conversion. Moreover, it also targets on the engine surge, proposes the anti-surge monitoring program by taking the surge margin as monitoring parameters, and verifies the effectiveness and feasibility of proposed method through simulation and actualization.
Authors: Mark John Leahy, D. Mba, P. Cooper, A. Montgomery, D. Owen
Abstract: An empirical investigation is undertaken in order to assess the potential of the AE technique for the detection of seal-to-rotor rubbing in steam turbines. Rubbing was induced at various axial locations along a 4 ½ tonne test rotor, rotating at 3000 rpm and supported by 7” (178mm) journal bearings. This paper examines the capabilities of bearing mounted AE transducers for the detection of seal-to-rotor rubbing.
Showing 1 to 10 of 166 Paper Titles