Search

To accurately extract fault information from rolling bearing (RB) vibration signals with strong nonlinear and non-stationary characteristics, a novel method using adaptive variational mode decomposition with noise suppression and fast spectral correlation (AVMDNS-FSC) is proposed. The AVMDNS algorithm can adaptively select VMD parameters K and α, which reduces the error caused by the improper selection of VMD parameters based on experience or prior knowledge of the signal. Meanwhile, the AVMDNS also effectively suppresses noise in intrinsic mode function (IMFs) and avoids unexpected removal of the IMFs containing important fault information. In addition, the FSC can further suppress residual noise and interference harmonics to enhance the periodic fault pulses and hence accurately extract bearing fault features. Simulation analysis and experimental studies are carried out through comparison with other methods. Results show that the AVMDNS-FSC method has higher sensitivity and effectiveness in extracting early periodic fault pulses of RB vibration signals.

Large and expensive mechanical equipment such as wind turbines generally has limited fault datasets from real-world operations for digital model development. This often leads to poor accuracy in implementing a model based on the life prediction. To address this data shortage issue in developing deep learning models, a remaining useful life prediction approach is proposed in this paper, which combines digital twin technology with transfer learning theory and the embedded convolutional long short-term memory (CLSTM) extended model. First, the main bearing of a direct-drive wind turbine is mapped to the digital world using digital twin technology, allowing the fault datasets of main bearings to be generated and thereby ensuring the model is trained sufficiently with a balanced dataset. The CLSTM network then performs convolutional operations on input-to-state and state-to-state transitions, thereby integrating the time dependence and time-frequency characteristics of the data. Meanwhile, transfer learning is used to transfer the trained model to the wind field for real-world fault diagnostics and the life prediction of the main bearings. Finally, the approach is applied to predict the life of the main bearings, and is also compared with other methods of similar type. The results verified that the proposed approach can effectively overcome the low data density of large equipment, greatly improving the accuracy of life prediction.

The fault features of planetary gearboxes are modulated complexly and are submerged by other signal components, for its vibration signal has the characteristics of multi-source and multi transmission path. A fault detection method of planetary gearboxes based on informative singular value decomposition and envelope spectrum analysis (ISVD-ESA) is proposed in this paper. In this method, the advantage of blind source separation of singular value decomposition (SVD) method is combined with the ability of negentropy and cyclic autocorrelation (CA) in non-Gaussian characteristics recognition. The fast SVD is firstly performed to decompose the vibration signal into a series of singular value decomposition component signals (SVCSs). Secondly, the detector of negentropy combined with CA is applied to estimate the fault informativeness of each SVCS. The SVCSs are amplified by the fault informativeness and reconstructed to the out signal of ISVD. Finally, the fault features can be extracted by the ESA from the output signal of ISVD. The performance of the proposed method is verified by simulation and experimental studies. Results show that the proposed ISVD-ESA strategy can enhance the weak features of multi-modulation and accurately extract the faults of tooth tip pitting and misalignment of sun gear of the planetary gearbox.

Tooth wear is one of the most common faults in gear transmission systems. However, due to its limited influences on gear dynamics, the condition monitoring of gear wear experiences more challenges. To investigate the relationship between tooth wear and gear dynamics, this study develops an eight-degree of freedom dynamic model which takes into account the gear mesh impact induced by tooth wear. In this model, the gear mesh impact force induced by tooth wear was calculated as an extra input excitation for the gear dynamic model. Besides, a comparative study was carried out to explore the real reason that causes the poor dynamic behaviour due to the wear from two points of view: 1) the reduction in gear mesh stiffness; 2) the increase in gear mesh impact force. The simulation results show that the wear causes a slight reduction in gear mesh stiffness, thus leading to the decrease in the amplitude of gear mesh frequency. This is not consistent with the phenomena observed in the lab experiment which shows the increase in the gear vibrations. The second simulation of impact force demonstrates that the wear causes an increase in the impact force which further leads to the increase in the amplitude of gear mesh frequency. This study investigates the cause for the deterioration in gear dynamics induced by gear wear, which can benefit the early condition monitoring and fault diagnosis of the gear tooth wear.

Accurate state of health (SOH) estimation of lithium-ion batteries is of great importance to ensure the reliability and safety of battery management systems (BMS). The difficulty of modelling the complex degradation mechanism has made the data-driven methods gain much attention in battery SOH prediction. To improve the estimation accuracy of battery SOH, extracting the suitable health indicators is still a challenging work. In this work, the health indication features are attracted from the charging voltage profile based on the experimental data measured under constant current charging mode. Subsequently, the Pearson correlation coefficient is used to evaluate the relationships between the extracted health features and battery capacity, thus selecting the most effective health features for establishing the prediction models. Finally, the battery SOH is estimated using a Gaussian process regression (GPR) method. The estimation results with R 2 of 1 and lower mean absolute error (MAE) and maximum error (MAX) provide higher accuracy based on the extracted health feature.

Lathe machining occupies a large proportion in modern production and processing, which affects the machining accuracy of the workpiece and results in vibration and noise of the machine tool. To improve the efficiency of lathe cutting state monitoring, this paper presents a new method on studying the monitoring of lathe tool, with Motor Current Signal Analysis (MCSA) as the main research method, the characteristics of stator’s working current are selected as the analysis object. Three cutting depths, 1mm, 2mm, and 3mm are respectively performed on the same workpiece material, and the cutting conditions are blunt tool and sharp tool. The frequency characteristic of the current is analyzed the under various cutting conditions mentioned above and the internal relation of the current variation and the cutting condition is presented as the conclusion of this paper, by which provides a new idea for the research of conditions monitoring and fault diagnosis in field operation on lathe tool.

The underground mining environment of coal mine is complex. Once the water supply or gas supply pipes leak, the location and time of leakage are unpredictable. If the leakage can not be found in time, it will seriously threaten the life safety of underground workers. Therefore, it is very necessary to automatically detect the pipeline leakage. In order to solve the problem of automatic detection of coal mine pipeline leakage, this paper proposes an image processing method based on gray level co-occurrence matrix to extract the features of time-frequency image of vibration signal. Firstly, the data in a relatively short time is divided into one frame to reduce the amount of calculation. Secondly, each frame of signal is processed by SPWVD to get the time-frequency image. Then, the time-frequency image after time-frequency analysis is transformed into gray-scale image, and the gray-scale co-occurrence matrix (GLCM) of the image is extracted. Finally, the energy, contrast and correlation of the co-occurrence matrix are extracted and input to SVM for learning and training. Through the design and build of the experimental pipeline to test the algorithm proposed in this paper, the detection result of SVM is 96.67%, which shows that this method can effectively detect the pipeline leakage.

Motor current signal analysis has been an effective way for many years of monitoring electrical machines themselves. However, little work has been carried out in using this technique for monitoring their downstream equipment because of difficulties in extracting small fault components in the measured current signals. This paper investigates the characteristics of electrical current signals for monitoring the faults from a downstream gearbox using a modulation signal bispectrum (MSB), including phase effects in extracting small modulating components in a noisy measurement. An analytical study is firstly performed to understand amplitude, frequency and phase characteristics of current signals due to faults. It then explores the performance of MSB analysis in detecting weak modulating components in current signals. Experimental study based on a 10kw two stage gearbox, driven by a three phase induction motor, shows that MSB peaks at different rotational frequencies can be based to quantify the severity of gear tooth breakage and the degrees of shaft misalignment. In addition, the type and location of a fault can be recognized based on the frequency at which the change of MSB peak is the highest among different frequencies.

In this paper, an experimental investigation has been carried out on the acoustic characteristics of a compression ignition (CI) engine running with biodiesel blends under steady state operating conditions. The experiment was conducted on a four-cylinder, four-stroke, direct injection and turbocharged diesel engine which runs with biodiesel (B50 and B100) and pure diesel. The signals of acoustic, vibration and in-cylinder pressure were measured during the experiment. To correlate the combustion process and the acoustic characteristics, both phenomena have been investigated. The acoustic analysis resulted in the sound level being increased with increasing of engine loads and speeds as well as the sound characteristics being closely correlated to the combustion process. However, acoustic signals are highly sensitive to the ambient conditions and intrusive background noise. Therefore, the spectral subtraction was employed to minimize the effects of background noise in order to enhance the signal to noise ratio. In addition, the acoustic characteristics of CI engine running with different fuels (biodiesel blends and diesel) was analysed for comparison. The results show that the sound energy level of acoustic signals is slightly higher when the engine fuelled by biodiesel and its blends than that of fuelled by normal diesel. Hence, the acoustic characteristics of the CI engine will have useful information for engine condition monitoring and fuel content estimation.

A modern railway system relies on sophisticated monitoring systems for maintenance and renewal activities. Some of the existing conditions monitoring techniques perform fault detection using advanced filtering, system identification and signal analysis methods. These theoretical approaches do not require complex mathematical models of the system and can overcome potential difficulties associated with nonlinearities and parameter variations in the system. Practical applications of condition monitoring tools use sensors which are mounted either on the track or rolling stock. For instance, monitoring wheelset dynamics could be done through the use of track-mounted sensors, while vehicle-based sensors are preferred for monitoring the train infrastructure. This paper attempts to collate and critically appraise the modern techniques used for condition monitoring of railway vehicle dynamics by analysing the advantages and shortcomings of these methods.

A Self aligning spherical journal bearing is a plain bearing which has spherical surface contact that can be applied in high power industrial machinery. This type of bearing can accommodate a misalignment problem. The journal bearing faults degrade machine performance, decrease life time service and cause unexpected failure which are dangerous for safety issues. Non-intrusive measurements such as surface vibration (SV), airborne sound (AS) and acoustic emission (AE) measurement are appropriate monitoring methods for early stage journal bearing fault in low, medium and high frequency. This paper focuses on the performance comparison using SV, AS and AE measurements in monitoring a self aligning spherical journal bearing for normal and faulty (scratch) conditions. It examines the signals in the time domain and frequency domain and identifies the frequency ranges for each measurement in which significant changes are observed. The results of SV, AS and AE experiments indicate that the spectrum can be used to detect the differences between normal and faulty bearing. The statistic parameter shows that RMS value and peak value for faulty bearing is higher than normal bearing.

The proactive multidisciplinary conceptual philosophy of Condition Monitoring and Diagnostic Engineering Management (COMADEM) was conceived and has been nurtured, developed and sustained since 1988. Since then, it is gratifying to note that the condition monitoring, diagnostic and prognostic community worldwide (representing industrialists, academics, research and development organizations, professional/private establishments and many hardware/software vending organizations) has warmly welcomed and supported this venture. As is evidenced, many have reaped (and are reaping) the benefits of COMADEM interdiscipline through continuous knowledge discovery, generation and dissemination. We are now proud to celebrate the 25th Annual Event (Silver Jubilee) in Huddersfield, the most beautiful part of the United Kingdom. The theme of this Congress is 'Sustained Prosperity through Proactive Monitoring, Diagnosis, Prognosis and Management'. This proceedings is enriched by contributions from many keynote experts representing many industry and academic establishments worldwide. Authors from more than 30 different countries have pooled their rich multidisciplinary up-to-date knowledge, in order to share their invaluable experience with the COMADEM community. In this proceedings, the readers will find more than 120 refereed papers encompassing a number of topical areas of interest relating to the theme of the congress. The proceedings of COMADEM 2012 will appear in the Open Access Journal of Physics: Conference Series (JPCS), which is part of the IOP Conference Series. All papers published in the IOP Conference Series are fully citable and upon publication will be free to download. We would like to express our deep gratitude to all the keynote speakers, authors, referees, exhibitors, Technical Co-Sponsoring Organizations, Gold Sponsors, IOP Publishers, COMADEM 2012 organizing committee members, delegates and many others on whom the success of this prestigious event depends. Professor Rakesh Mishra Professor Andrew Ball Dr Fengshou Gu Professor B K N Rao The Editors The PDF also contains details relating to the International Journal of COMADEM.

Vibration signals from a gearbox are usually very noisy which makes it difficult to find reliable symptoms of a fault in a multistage gearbox. This paper explores the use of time synchronous average (TSA) to suppress the noise and Continue Wavelet Transformation (CWT) to enhance the non-stationary nature of fault signal for more accurate fault diagnosis. The results obtained in diagnosis an incipient gear breakage show that fault diagnosis results can be improved by using an appropriate wavelet. Moreover, a new scheme based on the level of wavelet coefficient amplitudes of baseline data alone, without faulty data samples, is suggested to select an optimal wavelet.

The problem of failures in induction motors is a large concern due to its significant influence over industrial production. Therefore a large number of detection techniques were presented to avoid this problem. This paper presents the comparison results of induction motor rotor fault detection using three methods: motor current signature analysis (MCSA), surface vibration (SV), and instantaneous angular speed (IAS). These three measurements were performed under different loads with three rotor conditions: baseline, one rotor bar broken and two rotor bar broken. The faults can be detected and diagnosed based on the amplitude difference of the characteristic frequency components of power spectrum. However IAS may be the best technique because it gives the clearest spectrum representation in which the largest amplitude change is observed due to the faults.

Dynamic time warping (DTW) is a time-domain-based method and widely used in various similar recognition and data mining applications. This paper presents a phase-compensation-based DTW to process the motor current signals for detecting and quantifying various faults in a two-stage reciprocating compressor under different operating conditions. DTW is an effective method to align two signals for dissimilarity analysis. However, it has drawbacks such as singularities and high computational demands that limit its application in processing motor current signals for obtaining modulation characteristics accurately in diagnosing compressor faults. Therefore, a phase compensation approach is developed to reduce the singularity effect and a sliding window is designed to improve computing efficiency. Based on the proposed method, the motor current signals measured from the compressor induced with different common faults are analysed for fault diagnosis. Results show that residual signal analysis using the phase-compensation-based DTW allows the fault-related sideband features to be resolved more accurately for obtaining reliable fault detection and diagnosis. It provides an effective and easy approach to the analysis of motor current signals for better diagnosis in the time domain in comparison with conventional Fourier-transform-based methods.

Vibration-based fault diagnosis is widely used for gearbox monitoring. However, it often needs considerable effort to extract effective diagnostic feature signal from noisy vibration signals because of rich signal components contained in a complex gear transmission system. In this paper, an adaptive fractional Fourier transform filter is proposed to suppress noise in gear vibration signals and hence to highlight signal components originated from gear fault dynamic characteristics. The approach relies on the use of adaptive filters in the fractional Fourier transform domain with the optimised fractional transform order and the filter parameters, while the transform orders are selected when the signal have the highest energy gathering and the filter parameters are determined by evolutionary rules. The results from the simulation and experiments have verified the performance of the proposed algorithm in extracting the gear failure signal components from the noisy signals based on a multistage gearbox system.

This paper presents the analysis of phase current signals to identify and quantify common faults from an electrical motor based on dynamic time warping (DTW) algorithm. In condition monitoring, measurements are often taken when the motor undertakes varying loads and speeds. The signals acquired in these conditions show similar profiles but have phase shifts, which do not line up in the time-axis for adequate comparison to discriminate the small changes in machine health conditions. In this study, DTW algorithms are exploited to align the signals to an ideal current signal constructed based on average operating conditions. In this way, comparisons between the signals can be made directly in the time domain to obtain residual signals. These residual signals are then based on to extract features for detecting and diagnosing the faults of the motor and components operating under different loads and speeds. This study provides a novel approach to the analysis of electrical current signal for diagnosis of motor faults. Experimental data sets of electrical motor current signals have been studied using DTW algorithms. Results show that DTW based residual signals highlights more the modulations due to the compressor process. And hence can obtain better fault detection and diagnosis results.

The rear axle gear is one of the key parts of transmission system for automobiles. Its healthy state directly influences the security and reliability of the automotives. However, non-stationary and nonlinear characteristics of gear vibration due to load and speed fluctuations, makes it difficult to detect and diagnosis the faults from the transmission gear. To solve this problem a fault prognosis and diagnosis method based on a combination of radial basis function(RBF) and back-propagation (BP) neural networks is proposed in this paper. Firstly, a moving average pretreatment is used to suppress the time series fluctuation of vibration characteristic parameter tie series and reduce the interference of random noise. Then, the RBF network is applied to the pretreated parameter sequences for fault prognosis. Furthermore, based on self-learning ability of neural networks, characteristic parameters for different common faults are learned by a BP network. Then the trained BP neural network is utilized for fault diagnosis of the rear axle gear. The results show that the proposed method has a good performance in prognosing and diagnosing different faults from the rear axle gear.

Floating ring bearing is widely used in turbochargers to undertake the extreme condition of high rotating speed and high operating temperature. It is also the most concerned by the designers and users alike due to its high failure rate and high maintenance cost. Any little clearance change may result in oil leakage, which in turn cause blue smoke or black smoke according to leakage types. However, there is no condition monitoring of this bearing because it is almost impossible to measure the clearance especially the inner clearance, in which the inner oil film directly bears the high speed rotation. In stead of measuring clearance directly, this paper has proposed a method that uses film pressure as a measure to monitor the bearing clearance and its variation. A non-linear mathematical model is developed by using Reynolds equations with non-linear oil film pressure. A full description of the outer and inner film is provided along both axial and radial directions. A numerical simulation is immediately carried out. Variable clearance changes are investigated using the mathematical model. Results show the relationship between clearance and film pressure.