Fault Symptoms Research Articles

Система обработки данных для диагностирования системы управления газотурбинным двигателем

A system for processing diagnostic data of a gas turbine control system is considered. The procedures for obtaining diagnostic signs, identifying the symptoms of faults, and diagnosing the technical state of the control system have been implemented. It is proposed to sequentially complicate the structure of the neural network data processing system to achieve the required quality of classification of the diagnosed object technical state. An example of diagnostics of a model of a gas turbine control system proposed by W. Rowen is given.

A fault model extension for a geometric fault isolation methodology to detect leakages and sensor faults on engine test beds

Analytical model-based methods for fault diagnosis on engine test bench systems remain the subject of intensive research. In some cases, such methods are also being used productively even though their application is mainly limited to the isolation of sensor faults. This paper presents a method for isolating process faults—and leakages in particular—that does not require any direct changes to the analytical models used for residual generation. Based on a geometric isolator, this method generates relations between fault causes and fault symptoms through the definition of fault models using latent variables. The application of the methodology is first explained in detail using a simple example. Taking data from a simulated engine test bench, we then show how different causes of faults, including sensor faults and leakages at different positions, can be correctly isolated.

A sparsity-enhanced periodic OGS model for weak feature extraction of rolling bearing faults

The fault symptom of rolling bearings is usually characterized by transient impulses formed at equal intervals, but the impulse signal is easily affected by noise and harmonic interferences, which increases the difficulty of extracting impulse features. In order to realize the effective extraction of weak periodic impulses under strong noise, this paper constructs a non-convex penalty function based on elastic net and Lp norm, and proposes a sparsity-enhanced periodic overlapping group shrinkage (POGS) method to detect rolling bearing faults. In the proposed sparse model, the internal function of the non-convex penalty function adopts the period-guided elastic net group sparse constraint, and the envelope autocorrelation function is used to dynamically update the period prior information to improve the extraction accuracy of highly correlated features within the group. Meanwhile, the non-convex Lp norm is introduced into the penalty function to constrain the sparsity of the overall variables, so as to guide the sparsity within and across groups (SWAG) of faults features while maintaining the weak impulse amplitudes. A comprehensive evaluation indicator is constructed as the fitness function of the moth-flame optimization (MFO) algorithm to realize automatic selection of model parameters. On the basis of the majorization-minimization (MM) algorithm and the improved soft threshold algorithm, the process of solving the objective function of the proposed model is given, and the performance of the proposed method is analyzed. The analysis results of the experimental data of rolling bearings suggest that in comparison with some existing sparse denoising methods, the proposed method exhibits better performance in the extraction of weak periodic impulses.

Application of Genetic Algorithm for Inter-Turn Short Circuit Detection in Stator Winding of Induction Motor

This paper presents a new method of inter-turn short-circuit detection in cage induction motors. The method is based on experimental data recorded during load changes. Measured signals were analyzed using a genetic algorithm. This algorithm was next used in the diagnostics procedure. The correctness of fault detection was verified during experimental tests for various configurations of inter-turn short-circuits. The tests were run for several relevant diagnostic signals that contain symptoms of faults in an examined cage induction motor. The proposed algorithm of inter-turn short-circuit detection for various levels of winding damage and for various loads of the examined motor allows one to state the usefulness of this diagnostic method in normal industry conditions of motor exploitation.

Hybrid Random Forest and Support Vector Machine Modeling for HVAC Fault Detection and Diagnosis.

The malfunctioning of the heating, ventilating, and air conditioning (HVAC) system is considered to be one of the main challenges in modern buildings. Due to the complexity of the building management system (BMS) with operational data input from a large number of sensors used in HVAC system, the faults can be very difficult to detect in the early stage. While numerous fault detection and diagnosis (FDD) methods with the use of statistical modeling and machine learning have revealed prominent results in recent years, early detection remains a challenging task since many current approaches are unfeasible for diagnosing some HVAC faults and have accuracy performance issues. In view of this, this study presents a novel hybrid FDD approach by combining random forest (RF) and support vector machine (SVM) classifiers for the application of FDD for the HVAC system. Experimental results demonstrate that our proposed hybrid random forest–support vector machine (HRF–SVM) outperforms other methods with higher prediction accuracy (98%), despite that the fault symptoms were insignificant. Furthermore, the proposed framework can reduce the significant number of sensors required and work well with the small number of faulty training data samples available in real-world applications.

Fault and calibration shift detection in a robust MEMS accelerometer array

The latest generation micro-electro-mechanical system(MEMS) accelerometers offer high bandwidth and low noisefloors previously limited to piezoelectric (PZT) based sensors.These relatively low cost MEMS sensors drastically expandthe financially practical applications for high frequency,vibration based, prognostics health management (PHM).This paper examines a robust array of MEMS accelerometersfor applications where sensor access after deploymentis difficult or infeasible. Three identical single axis MEMSaccelerometers were place in an array for testing. Insteadof a typical tri-axial configuration, the three sensors werealigned on a common axis. An auto-correlation algorithmwas used to detect gross system faults of individual sensorsin the array. A separate algorithm was developed to detectabnormal sensor sensitivity drift. The 3 sensor array wastested under a variety of conditions to test the developedalgorithms; power supply voltages were systematically variedaffecting the ratio-metric accelerometer sensitivity andindividual sensor mounts were purposely compromised tosimulate common fault symptoms. A decision logic treewas then implemented to respond to both types of faults.Results show the feasibility of implementing robust MEMSaccelerometer arrays using the latest generation of high bandwidthMEMS accelerometers. Planned future work includesdeploying the sensor array on tribology test equipment tovalidate MEMS sensor effectiveness compared to traditionalPZT based accelerometers.

Research on the Electromagnetic Conversion Method of Stator Current for Local Fault Detection of a Planetary Gearbox

Motor current signature analysis (MCSA) is a useful technique for planetary gear fault detection. Motor current signals have easier accessibility and are free from time-varying transfer path effects. If the fault symptoms in current signals are well understood, it will be more beneficial to develop effective current signal processing methods. Some researchers have developed mathematical models to study the characteristics of current signals. However, no one has considered the coupling of rotor eccentricity and gear failures, resulting in an inaccurate analysis of the current signals. This study considers the sun gear failure of a planetary gearbox and the eccentricity of the motor rotor. An improved induction motor model is proposed based on the magnetomotive force (MMF) to simulate the stator current. By analyzing the current, the modulation relationships of gearbox meshing frequency, fault frequency, power supply frequency, and gear rotating frequency are obtained. The proposed model is validated to some extent using experimental data.

OASIS-P: Operable Adaptive Sparse Identification of Systems for fault Prognosis of chemical processes

With the increasing process complexities, data-driven fault prognosis has emerged as a promising fault management tool that predicts and manages abnormal events well in advance. In this paper, we develop a fault prognosis framework named ‘OASIS-P’ by integrating operable adaptive sparse identification of systems (OASIS), which is a data-driven adaptive modeling technique, with a risk-based process monitoring approach and contribution plots. Firstly, OASIS is employed with the risk assessment procedure for the prediction of impending faults. As the OASIS model is adaptive, it copes with the initial fault symptoms and forecasts the future behavior of the process under faulty conditions reasonably well, thereby providing an early fault prediction. Next, the fault isolation step is immediately initiated using contribution plots to identify the faulty variables. Unlike in fault diagnosis, the problem of ambiguity in interpreting contribution results due to fault propagation is not an issue in fault prognosis, if the fault isolation step is implemented at an early stage of the fault before it affects the other variables. Hence, the contribution plots together with OASIS can proactively monitor the process in real-time. As a case study, we demonstrate OASIS-P for fault prognosis of a reactor–separator system.

Dynamic simulation of a cylindrical roller bearing with a local defect by combining finite element and lumped parameter models

Rolling element bearings are one of the key components of many rotating machines. Through condition monitoring and vibration analysis of bearings, valuable information about the health status of the machine can be obtained, such as detection of a local fault, unbalance, and misalignment. For more than three decades, various bearing dynamic models have been developed by researchers to simulate the acceleration signal of the bearing and enhance the understanding of bearing vibration response in case of having local defects. Nevertheless, recent studies have shown that measurement of local strain in the bearing can be more effective in fault diagnosis of bearings since local strain signal is less subjected to surrounding noise and non-fault interferences. However, previously developed dynamic models lack a deep study on simulating strain signals at different locations in a bearing. Therefore, this paper presents the result of a combined lumped parameter and finite element models (FEMs) for simulating strain signals of a cylindrical roller bearing in healthy and defective conditions. Contrary to previous combined dynamic models, more realistic modeling assumptions are adopted, such as applying contact pressure to the raceway rather than concentrated nodal forces. The contact pressures are obtained from the lumped parameter model and exported to the FEM for transient analysis. The accuracy of the model in generating stress distribution is validated by a static 2D finite element contact model and theoretical formulas. Dynamic responses of the bearing, such as strain changes at different locations, are investigated in the time and frequency domains to investigate the fault symptoms such as sharp impulses and amplitude modulation. Lastly, the effect of a transmission path on strain measurement and using residual strain signal for fault diagnosis are discussed. Overall, the proposed model is an effective method for strain simulation of healthy and defective roller bearings.

Vibration modelling and fault evolution symptom analysis of a planetary gear train for sun gear wear status assessment

The diagnosis and monitoring of surface wear are very critical for the prevention of shutdown and even catastrophic destruction of a geared transmission system. However, the detection for the evolutionary status of surface wear in a planetary gear train is quite challengeable due to the complicated and weak characteristics buried in the vibration signals. To assess the wear status of gears in a planetary gear train, a sophisticated vibration signal analysis based methodology is proposed. First, an analytical dynamic model of single-stage planetary gear train is established, which incorporates the effects of distributed surface wear of mating gears. With the analytical dynamic model, a resultant vibration signal model is further established after considering the influences of transfer path, direction variation of gear action lines and background noise. This vibration signal model is used to represent the actual vibration signals collected by transducers installed on the housing of planetary gearbox. Based on the constructed resultant vibration signals, two novel fault indicators are defined to reveal the evolution law of fault symptom. The fault evolution symptom analysis is used to identify healthy status and wear status of mating gears in the planetary transmission system. The effectiveness of the proposed model as well as the fault indicators are validated by both simulated signals and experimental signals.

A deep learning model for process fault prognosis

Early fault detection and fault prognosis are crucial functions to ensure safe process operations. Fault prognosis can detect and isolate early developing faults as well as predict fault propagation. To promptly detect potential faults in process systems, it is important to examine the fault symptoms as early as possible. In recent years, fault prognosis approaches have led to the remaining useful life prediction. Therefore, in a process system, advancing prognosis approaches will be beneficial for early fault detection in terms of process safety, and to predict the remaining useful life, targeting the system's reliability. In data-driven models, early fault detection is regarded as a time-dependent sequence learning problem; the future data sequence is predicted using the previous data pattern. Studying recent years' research shows that a recurrent neural network (RNN) can solve the sequence learning problem. This paper proposes an early potential fault detection approach by examining the fault symptoms in multivariate complex process systems. The proposed model has been developed using the Convolutional Neural Network (CNN)- Long Short-Term Memory (LSTM) approach to forecast the system parameters for future sampling windows' recognition and an unsupervised One-class-SVM used for fault symptoms' detection using forecasted data window. The performance of the proposed method is assessed using Tennessee Eastman process time-series data. The results confirm that the proposed method effectively detects potential fault conditions in multivariate dynamic systems by detecting the fault symptoms early as possible.

An adaptive order-band energy ratio method for the fault diagnosis of planetary gearboxes

Condition monitoring of planetary gearboxes in time-varying speed service is an important and actual engineering requirement, however, also an intractable task. The traditional sideband energy ratio (SER) method limits its application to complex operational conditions due to the frequency spectrum based and manual bandwidth selection. To this end, this paper proposes an adaptive order-band energy ratio (AOER) method, an enhanced version of the SER, to quantitatively and intelligently diagnose gear faults under different operational conditions. First, a signal model based on angular increment and order components is proposed to properly describe the vibrations for both stationary and non-stationary conditions. The proposed model provides the theoretical source and reliance for the order spectrum analysis and the diagnostic mechanism of the OER. Second, the OER is theoretically proved to be a reliable fault indicator by analyzing the proposed signal model. The offset of the uncertainty terms highlighting the fault symptoms demonstrates the potential success of using OER for the fault diagnosis. Finally, OERs generated from the vibration data and three typical machine learning algorithms are used to adaptively obtain the optimal bandwidth and thus the AOER. The AOER can be directly used for the remaining vibration data of the corresponding operational condition. Comparing with SER and the convolutional neural network, the experimental results demonstrate the effectiveness and outperformance of AOER for both stationary and non-stationary operational conditions. More importantly, since AOER can cope with diagnostic tasks for different operational conditions, it enables an improved ability to monitor a PG’s health in the actual complex environment.

On-line Detection and Classification of PMSM Stator Winding Faults Based on Stator Current Symmetrical Components Analysis and the KNN Algorithm

The significant advantages of permanent magnet synchronous motors, such as very good dynamic properties, high efficiency and power density, have led to their frequent use in many drive systems today. However, like other types of electric motors, they are exposed to various types of faults, including stator winding faults. Stator winding faults are mainly inter-turn short circuits and are among the most common faults in electric motors. In this paper, the possibility of using the spectral analysis of symmetrical current components to extract fault symptoms and the machine-learning-based K-Nearest Neighbors (KNN) algorithm for the detection and classification of the PMSM stator winding fault is presented. The impact of the key parameters of this classifier on the effectiveness of stator winding fault detection and classification is presented and discussed in detail, which has not been researched in the literature so far. The proposed solution was verified experimentally using a 2.5 kW PMSM, the construction of which was specially prepared for carrying out controlled inter-turn short circuits.

Bearing fault diagnosis based on optimized variational mode decomposition and 1D convolutional neural networks

Due to the fact that measured vibration signals from a bearing are complex and non-stationary in nature, and that impulse characteristics are always immersed in stochastic noise, it is usually difficult to diagnose fault symptoms manually. A novel hybrid fault diagnosis approach is developed for denoising signals and fault classification in this work, which combines successfully variational mode decomposition (VMD) and a one-dimensional convolutional neural network (1D CNN). VMD is utilized to remove stochastic noise in the raw signal and to enhance the corresponding characteristics. Since the modal number and penalty parameter are very important in VMD, a particle swarm mutation optimization as a novel optimization method and the weighted signal difference average as a new fitness function are proposed to optimize the parameters of VMD. The reconstructed signals of mode components decomposed by optimized VMD are used as the input of the 1D CNN to obtain fault diagnosis models. The performance of the proposed hybrid approach has been evaluated using sets of experimental data on rolling bearings. The experimental results demonstrate that the VMD can eliminate signal noise and strengthen status characteristics, and the proposed hybrid approach has a superior capability for fault diagnosis from vibration signals of bearings.

Current Vector Phase‐Based Diagnostic Method for Multiple Open‐Circuit Faults in Voltage‐Source Inverters

A simple and fast diagnostic method for multiple open‐circuit faults in voltage‐source inverters based on the current vector phase is proposed. The characteristics of the current vector phase in both healthy and faulty conditions are analyzed in detail, and simple fault symptom variables are defined to extract the features for fault isolation. The proposed method can diagnose 21 types of open‐circuit faults only by using current vector phase information, and it is fast, robust and easy to implement in existing systems without additional sensors. Several experimental results verify that the diagnostic algorithm has no false alarms under speed and load transient conditions, and the fault can be isolated within 15% of the current fundamental cycle in the case of the fastest diagnostic process and no more than 80% of the current cycle in the worst cases. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Automatic Transmission Fault Symptom Identification by Apply of Neural Network and D-S Evidence Theory

At present, the method of identifying the fault symptoms of various machines by combining the neural network and the D-S evidence theory is attracting attention from researchers because the identification time is fast and the diagnosis is accurate. In this paper, it was mentioned a method for identifying the fault symptoms of automatic transmission by combining these two theories. First, it was mentioned a method for identifying fault symptoms of the automatic transmission by combining a fuzzy neural network and an RBF neural network. Next, it was newly described a method to improve the accuracy of fault symptom identification by the D-S evidence theory. In addition, the accuracy of this method was verified by an experimental method. In the experiment Firstly, two sub neural networks are established to recognize the initial symptoms. That is, the first sub-neural network E1 be used as the fuzzy neural network, the second sub-neural network E2 be used as RBF neural network, respectively, for preliminary symptom recognition. And then, these outputs of the two sub neural networks are used as the evidence space of D-S evidence theory, so the global diagnosis is carried out. The results show that the test results are consistent with the actual fault symptoms. The success rate of fault diagnosis up to 96.3%, therefore, on the identification of the automatic transmission fault symptom, effectiveness, and feasibility of the D-S evidence theory based on information fusion is verified.

A Power Transformer Fault Diagnosis Method Based on Random Vector Functional-Link Neural Network

The random vector functional link (RVFL) network is suitable for solving nonlinear problems from transformer fault symptoms and different fault types due to its simple structure and strong generalization ability. However, the RVFL network has a disadvantage in that the network structure, and parameters are basically determined by experiences. In this paper, we proposed a method to improve the RVFL neural network algorithm by introducing the concept of hidden node sensitivity, classify each hidden layer node, and remove nodes with low sensitivity. The simplified network structure could avoid interfering nodes and improve the global search capability. The five characteristic gases produced by transformer faults are divided into two groups. A fault diagnosis model of three layers with four classifiers was built. We also investigated the effects of the number of hidden nodes and scale factors on RVFL network learning ability. Simulation results show that the number of implicit layer nodes has a large impact on the network model when the number of input dimensions is small. The network requires a higher number of implicit layer neurons and a smaller threshold range. The size of the scale factor has significant influence on the network model with larger input dimension. This paper describes the theoretical basis for parameter selection in RVFL neural networks. The theoretical basis for the selection of the number of hidden nodes, and the scale factor is derived. The importance of parameter selection for the improvement of diagnostic accuracy is verified through simulation experiments in transformer fault diagnosis.

Comparison of Selected Methods for the Stator Winding Condition Monitoring of a PMSM Using the Stator Phase Currents

Stator winding faults are one of the most common faults of permanent magnet synchronous motors (PMSMs), and searching for methods to efficiently detect this type of fault and at an early stage of damage is still an ongoing, important topic. This paper deals with the selected methods for detecting stator winding faults (short-circuits) of a permanent magnet synchronous motor, which are based on the analysis of the stator phase current signal. These methods were experimentally verified and their effectiveness was carefully compared. The article presents the results of experimental studies obtained from the spectral analysis of the stator phase current, stator phase current envelope, and the discrete wavelet transform. The original fault indicators (FIs) based on the observation of the symptoms of stator winding fault were distinguished using the aforementioned methods, which clearly show which symptom is most sensitive to the incipient fault of the stator winding of PMSMs.

Indirect Fault Diagnosis of Fixed Marine Observing Buoy Based on Bayesian Network

Abstract Fault diagnosis of a fixed marine observing buoy (FMOB) is important for ensuring the reliability of an ocean observing system. Aiming at the difficulty that most FMOB instruments lack direct operational status information in fault diagnosis, an indirect fault diagnosis method based on a Bayesian network (BN) for FMOBs is presented, through which the ocean observing series collected by the FMOB are effectively utilized and analyzed for fault diagnosis of FMOB equipment. The ocean observing series not only reflects the characteristics of the marine environment but also includes the operating status of FMOBs. Based on the analysis of an ocean observing series, the different fault symptoms of FMOBs are confirmed. According to the BN theory, the indirect fault diagnosis model is developed. The model structure is defined based on a comprehensive analysis of the causal relationships among faults and their symptoms. The model parameters are estimated according to experts' knowledge and statistical analysis of historical data. Three typical fault cases of FMOBs are selected for verifying the method. The results show that the BN-based indirect fault diagnosis method is reliable and effective for fault diagnosis of an FMOB even when the fault diagnosis evidence is incomplete and uncertain. Furthermore, this approach can work in a real-time way and help technicians to take effective measures to avoid big losses.

Fault detection and diagnosis for multiple faults of VAV terminals using self-adaptive model and layered random forest

Fault detection and diagnosis (FDD) can reduce a large amount of energy wasted by faults in variable air volume (VAV) systems. This paper presents a FDD method for detecting and diagnosing multiple faults of VAV terminals using a hybrid method. A self-adaptive zone air-temperature model is presented and used to detect faults of the VAV terminals by comparing the residuals between predicted and measured values with corresponding fault detection thresholds. The model parameters, which are normally constant and determined according to experience from short-period data, are periodically adjusted to improve the model prediction accuracy on the basis of operating data by using a chaos particle swarm optimization algorithm. Moreover, a two-layered random forest-based fault diagnosis method is presented to isolate multiple faults of VAV terminals according to the complexity of the fault symptoms. An expert rule-based fault diagnosis layer is used to isolate VAV terminal faults with simple fault symptoms. A random forest-based fault diagnosis layer is utilized to diagnose VAV terminal faults with complex fault symptoms by adopting a binary decision tree-based multi-label technique. The proposed FDD method is validated using operating data from real VAV systems involving 13 single-fault cases and 6 simultaneous-fault cases. The validation results indicate that the proposed FDD method can accurately detect and diagnose simultaneous multiple faults with only a few independent fault samples and a minimal number of simultaneous-fault samples.