Fault Signal Detection Research Articles

Bearing fault signal detection and prediction based on an improved particle filter method

Awareness and predicting bearing health are challenging because of uncertainties in the operating environment and noise in fault-signal measurements. Considering the sudden occurrence of bearing faults and their relatively brief duration over the bearing lifespan, this paper presents a fusion framework that combines an eighth-order polynomial model with a cuckoo search thought particle filter (CST-PF) method to estimate the failures occurrences. The fault characteristic signals are extracted from the amplitude spectrum within a specific frequency range and modeled by an eighth-order polynomial model. Cuckoo search (CS) is introduced to address the particle dilution in particle filter (PF). Furthermore, the proposed CST-PF refines the step size update equations and discovery probability for balancing the search speed and accuracy, thus enhancing the adaptability to bearing fault diagnosis and prediction. It ensures the parameter convergences in the prediction model by learning the fault characteristic signal during regular bearing operations, facilitating accurate predictions of subsequent failures. Validation results show that the eighth-order model accurately captures changes in fault characteristic signals throughout the bearing lifespan, with MAE and RMSE metrics surpassing those of traditional models. The CST-PF method demonstrates superior predictive ability compared to the Cuckoo search particle filter (CS-PF), traditional PF, and other PF variants.

Design of intelligent detection method for electricity transmission line equipment defect based on data mining algorithm

Electricity transmission line is the most significant way of power transmission. Regular detection of it can find and eliminate its defects and hidden dangers in time and prevent major accidents, which is of great significance to the power system. In order to find the problems in the electricity transmission line in time, this paper applied the data mining algorithm to the intelligent detection method of electricity transmission line equipment defects. An electricity transmission line equipment defect intelligent detection and monitoring system was constructed, and the differences between clustering analysis image recognition technology in data mining algorithms and the XGBoost algorithm were analyzed. The results showed that compared with using XGBoost algorithms, the highest accuracy rate of the intelligent detection method of electricity transmission line equipment defects using data mining algorithm in the detection results was 98 %, which was generally higher than that of XGBoost algorithms, and could reduce the consumption of time. From the perspective of replication rate, the overall average value of XGBoost algorithms was 52.38 % and the overall average value of data mining algorithms was 7.63 %. The replica rate of data mining algorithm was much lower than that of XGBoost algorithm and the performance of fault signal detection was better. Therefore, the application of data mining algorithm to the intelligent detection method of electricity transmission line equipment defects can be more suitable, thus significantly improving the efficiency of all aspects. At the same time, the method has the advantages of simple operation, fast, reliable and not affected by region.

Fourth-stable stochastic resonance and its application to weak fault signal detection of rotating machinery

Weak characteristic extraction is vital for weak fault signal detection of machinery. Stochastic resonance (SR) is able to transfer noise energy into weak fault characteristic frequency excited by a defect of machines. However, the potential function in SR is vital to enhance weak fault characteristic frequency and determines the capability of SR to improve the signal-to-noise ratio (SNR) of a noisy signal. Now, common potential functions include monostable, bistable and even tri-stable potentials but fourth-stable SR has not been studied and applied to detect early fault characteristic frequency. In this paper, thus, we would investigate the behaviors of SR with a fourth-stable potential subject to additive noise, in which the approximate theoretical expression of the power done by SR is derived to demonstrate the fourth-stable Sr Then, a SR method with the fourth-stable potential is proposed to enhance weak fault characteristic frequency, in which these system parameters are adjusted by using SNR as the objective function and using genetic algorithms adaptively. In this paper, thus, Finally, the proposed method is verified by using a simulated signal with noise and two early fault experiment of rolling element bearings with different levels of defects on the outer and inner races. Moreover, the proposed method is compared with wavelet denoising and fast kurtogram methods. The comparisons indicate that the proposed method has the better performance for enhancing weak fault characteristic frequency or weak useful signals than other two methods and is available to weak fault signal detection of machinery.

Transfer learning with cross-domain adaptation of vibro-acoustic signals for electric motor mechanical fault detection and diagnosis.

Contact-based vibration measurement techniques involving accelerometers are typically utilized for machine health monitoring and manufacturing end-of-line quality control. Acoustic signals, encompassing sound pressure and particle velocity, carry crucial information about the operational status of underlying equipment and can be utilized for detecting various machine faults. Utilizing one-dimensional Convolution Neural Networks (1D-CNN) based on deep learning for processing raw acoustic time signals has proven to be a valuable approach in detecting machinery faults, offering an effective alternative to using traditional accelerometer signals. However, the success of deep learning methods is heavily dependent on the quantity and availability of data for robust network training. When transitioning to new non-contact type sensor technology, manufacturers may face challenges due to insufficient data for training deep learning models. In such cases, leveraging existing historical accelerometer-based data becomes crucial. Transfer learning emerges as a promising solution, allowing deep learning models trained on a source domain (SD) to be applied to a separate but related target domain (TD). This paper hence introduces a domain adaptation methodology by implementing transfer learning, where the SD 1D-CNN network is trained on accelerometer signals, then the trained model weights are transferred to the TD 1D-CNN network that can process acoustic signals.

Machine Learning in Short-Reach Optical Systems: A Comprehensive Survey

Recently, extensive research has been conducted to explore the utilization of machine learning (ML) algorithms in various direct-detected and (self)-coherent short-reach communication applications. These applications encompass a wide range of tasks, including bandwidth request prediction, signal quality monitoring, fault detection, traffic prediction, and digital signal processing (DSP)-based equalization. As a versatile approach, ML demonstrates the ability to address stochastic phenomena in optical systems networks where deterministic methods may fall short. However, when it comes to DSP equalization algorithms such as feed-forward/decision-feedback equalizers (FFEs/DFEs) and Volterra-based nonlinear equalizers, their performance improvements are often marginal, and their complexity is prohibitively high, especially in cost-sensitive short-reach communications scenarios such as passive optical networks (PONs). Time-series ML models offer distinct advantages over frequency-domain models in specific contexts. They excel in capturing temporal dependencies, handling irregular or nonlinear patterns effectively, and accommodating variable time intervals. Within this survey, we outline the application of ML techniques in short-reach communications, specifically emphasizing their utilization in high-bandwidth demanding PONs. We introduce a novel taxonomy for time-series methods employed in ML signal processing, providing a structured classification framework. Our taxonomy categorizes current time-series methods into four distinct groups: traditional methods, Fourier convolution-based methods, transformer-based models, and time-series convolutional networks. Finally, we highlight prospective research directions within this rapidly evolving field and outline specific solutions to mitigate the complexity associated with hardware implementations. We aim to pave the way for more practical and efficient deployment of ML approaches in short-reach optical communication systems by addressing complexity concerns.

Performance evaluation of deep learning approaches for fault diagnosis of rotational mechanical systems using vibration, sound, and acoustic emission signals

The present study emphasizes an optimized deep learning algorithm for gearbox fault detection using vibration, sound, and acoustic emission signals. Statistical and acoustic features are extracted from these signals, and various neural network algorithms are explored. The supervised deep feed forward neural network (DFFNN) demonstrates excellent performance with vibration signals but limited accuracy with sound and acoustic emission signals. To address this, unsupervised algorithms are optimized and compared with vibration-based classification. The findings show that unsupervised neural networks, particularly the auto-encoder and stacked auto-encoder architectures, achieve improved classification accuracy by leveraging the unique characteristics of acoustic emission signals. The unsupervised models also effectively overcome the vanishing gradient problem via regularization, enhancing their training efficiency. The stacked auto-encoder, with multiple layers of encoders and decoders, reduces computation time by 40% and memory consumption. These optimized algorithms hold promise for automated fault detection systems. The auto-encoder and stacked auto-encoder, utilizing vibration, sound, and acoustic emission signals, offer enhanced classification accuracy and can facilitate real-time monitoring of rotating mechanical systems. However, further optimization is needed to maximize their performance. In a nutshell, the supervised DFFNN excels in utilizing vibration signals for fault detection, while the unsupervised models exploit the distinctive characteristics of acoustic emission signals. Future research will focus on refining these algorithms to enhance their effectiveness. Implementing these optimized deep learning approaches can lead to autonomous fault detection systems, eliminating the need for continuous human supervision.

State estimation based actuator fault detection for tandem rotor helicopter with experimental validation

Timely fault detection is essential to flight safety of tandem rotor helicopter. In this paper, a fault detection method is proposed based on state estimation and the deviation between the measured value and the estimated value. Firstly, a polyhedral linear parameter varying (LPV) model is established to solve the nonlinear coupling problem of the helicopter in different moving directions. Then, to obtain actuator fault information, a robust state observer is developed to generate the residual. Meanwhile, a mixed [Formula: see text] algorithm is designed to calculate observer gain by configuring performance parameters, which makes the residuals both sensitive to actuator faults and robust to external disturbances. Furthermore, a dynamic threshold method is introduced to evaluate the residual signal for actuator fault detection. Finally, based on the 3-dof helicopter platform, the effectiveness of the proposed method is verified through comparative simulation and experimental tests.

Operation Fault Detection of Electrical and Mechanical Equipment Based on Kalman Filter

In order to realize the remote collaborative diagnosis of electromechanical equipment fault in integrated energy system, a design method of remote collaborative diagnosis system of electromechanical equipment fault in integrated energy system based on Kalman filter is proposed. The hardware of the diagnosis system designed in this paper includes main control module, fault information parameter identification module, dynamic sensor acquisition module, fault signal filtering and detection module, adaptive control module, output interface module and so on. The collected fault information of electromechanical equipment in the system is fused by multi-source sensors, the fault information feature extraction is completed by Kalman filter, the information clustering processing is completed, and the algorithm design of electromechanical equipment operation fault diagnosis is realized. The fault diagnosis algorithm based on Kalman filter is loaded into the main control module of the motor equipment fault diagnosis system to realize the identification of motor equipment fault parameters and complete the development and design of the diagnosis system. The test results show that the text diagnosis system has good adaptability, high reliability and accuracy.

Enhancing Fault Detection and Diagnosis in Grid-Connected PV Systems under Irradiance Variations: A Novel Approach Using New Data Normalization Techniques on RBFNN Algorithm

With the global shift towards renewable energy, the reliability and efficiency of photovoltaic (PV) systems have become paramount. A crucial aspect of this is the timely detection and accurate classification of faults within the system. In fact, accurate fault detection and classification in the diagnostic systems can prevent severe damages, enhance operational efficiency, and prolong the lifespan of the installations. This paper introduces a novel data normalization technique tailored for enhancing the performance of meta-heuristic algorithms (namely RBFNN) applied to single-phase inverter current signals for fault detection in PV systems. While conventional normalization technics have shown their limitations in capturing the nuances of PV system faults, our proposed strategy demonstrates a more effective approach in preserving fault-specific features in the data. The proposed method is evaluated using multiple datasets encompassing a variety of fault scenarios. Empirical results show a significant improvement in both fault detection rates and classification accuracy. This study not only presents a breakthrough in PV system fault diagnosis but also sheds light on the broader potential of specialized normalization techniques in all signal-processing field, such as biomedical signal processing, industrial process control, or financial time series analysis, and other domains. The supremacy of the proposed diagnostic in reducing false alarms and providing more clear-cut classifications is highlighted by several simulations under Matlab-Simulink.

GCVIF: Pioneering Explainable Domain-Shared Representation Learning for Fault Signal Detection in Multiple Working States Simultaneously

GCVIF: Pioneering Explainable Domain-Shared Representation Learning for Fault Signal Detection in Multiple Working States Simultaneously

Machine learning approaches for fault detection in renewable microgrids

This study focuses on investigating and using machine learning (ML) methods to identify faults in renewable microgrids. It highlights the difficulties and intricacies associated with these dynamic energy systems. The examination of real-world data obtained from solar and wind power production, battery storage status, fault signals, and machine learning model performance highlights the complex nature of fault detection techniques in renewable microgrids. An analysis of data on renewable energy production demonstrates oscillations in the outputs of solar and wind power, highlighting differences of about 5-10% across certain time periods, thereby illustrating the intermittent characteristics of renewable energy sources. Simultaneously, the energy stored in batteries inside the microgrid shows a progressive decrease of about 3-5% in stored energy levels across time intervals, indicating possible consequences for the stability of the system. The fault detection signals display erratic patterns, which emphasize the intricacies involved in finding and categorizing issues inside the system. The assessment of machine learning models, which includes both supervised and unsupervised learning methods, reveals many performance measures. Supervised models provide greater accuracy rates, often ranging from 85% to 90%. However, they are prone to occasional misclassifications. In contrast, unsupervised models provide a moderate level of accuracy, often ranging from 75% to 80%. They exhibit flexibility in detecting faults, but their precision is limited. The study highlights the need of using a combination of supervised and unsupervised machine learning models to improve the accuracy of fault detection in renewable microgrids. These results provide valuable understanding of the intricacies and difficulties of fault detection procedures, which may lead to further progress in improving the dependability and durability of renewable microgrid systems.

Enhancing bearing fault diagnosis using motor current signals: A novel approach combining time shifting and CausalConvNets

In motor drive system, Bearing fault detection through motor current signal (MCS) analysis has gained recognition for its cost-effectiveness and non-invasive nature. However, two-dimensional (2D) convolutional neural networks (CNNs) exhibit suboptimal performance when directly applied to raw stator current signals for fault detection. Meanwhile, the training of Recurrent Neural Networks (RNNs) for processing one-dimensional (1D) temporal sequence can be a time-consuming task due to the inherent procedures of the network structure. To balance time-consuming and accuracy, this paper presents a novel MCS-based bearing fault detection model utilizing a 1D CNN and corresponding pre-processing methods. In the early stages, a noise cancellation strategy termed time shifting is implemented. Subsequently, wavelet transform is employed to further refine the processed signal by eliminating components with minimal significance. By compressing homogenous signals, the resultant tensor, referred to as the “root map”, is employed as the input for the proposed temporal causal network. Two groups of experimental results conducted on both laboratory and industrial conditions validate the effectiveness and convenience of the proposed methodology.

Machinery Fault Signal Detection with Deep One-Class Classification

Fault detection of machinery systems is a fundamental prerequisite to implementing condition-based maintenance, which is the most eminent manufacturing equipment system management strategy. To build the fault detection model, one-class classification algorithms have been used, which construct the decision boundary only using normal class. For more accurate one-class classification, signal data have been used recently because the signal data directly reflect the condition of the machinery system. To analyze the machinery condition effectively with the signal data, features of signals should be extracted, and then, the one-class classifier is constructed with the features. However, features separately extracted from one-class classification might not be optimized for the fault detection tasks, and thus, it leads to unsatisfactory performance. To address this problem, deep one-class classification methods can be used because the neural network structures can generate the features specialized to fault detection tasks through the end-to-end learning manner. In this study, we conducted a comprehensive experimental study with various fault signal datasets. The experimental results demonstrated that the deep support vector data description model, which is one of the most prominent deep one-class classification methods, outperforms its competitors and traditional methods.

An unsupervised end-to-end approach to fault detection in delta 3D printers using deep support vector data description

Fault detection in 3D printers is crucial for safety and quality assurance, emphasizing proactive prediction over reactive rectification based on manufacturing factors. Presently, most detection techniques rely on shallow models with limited representational capabilities, necessitating manual feature extraction from the captured signals. This manual process is not only cumbersome and potentially costly but often requires intricate domain-specific knowledge. Additionally, these handcrafted features might not optimally distinguish between normal and faulty samples, potentially reducing prediction accuracy. In this study, we introduce an end-to-end approach using the Deep Support Vector Data Description model for fault detection in 3D printers. This design inherently facilitates automatic feature learning, where the features are synergistically optimized for fault detection. Our experiments leverage magnetic field signals for fault detection in 3D printers, using 1D convolutional layers to discern temporal signal patterns and wide kernels in the initial layer to mitigate high-frequency noise. Furthermore, our model can be easily adapted to integrate multi-channel signals for enhanced accuracy. Evaluations on real-world data from a delta 3D printer underscore the superiority of our method compared to existing alternatives.

Failure Severity Prediction for Protective-Coating Disbondment via the Classification of Acoustic Emission Signals.

Structural health monitoring is a popular inspection method that utilizes acoustic emission (AE) signals for fault detection in engineering infrastructures. Diagnosis based on the propagation of AE signals along any surface material offers an attractive solution for fault identification. However, the classification of AE signals originating from failure events, especially coating failure (coating disbondment), is a challenging task given the AE signature of each material. Thus, different experimental settings and analyses of AE signals are required to classify the various types of coating failures, and they are time-consuming and expensive. Hence, to address these issues, we utilized machine learning (ML) classification models in this work to evaluate epoxy-based-protective-coating disbondment based on the AE principle. A coating disbondment experiment consisting of coated carbon steel test panels for the collection of AE signals was implemented. The obtained AE signals were then processed to construct the final dataset to train various state-of-the-art ML classification models to divide the failure severity of coating disbondment into three classes. Consequently, methods for the extraction of useful features, the handling of data imbalance, and a reduction in the bias of ML models were also effectively utilized in this study. Evaluations of state-of-the-art ML classification models on the AE signal dataset in terms of standard metrics revealed that the decision forest classification model outperformed the other state-of-the-art models, with accuracy, precision, recall, and F1 score values of 99.48%, 98.76%, 97.58%, and 98.17%, respectively. These results demonstrate the effectiveness of utilizing ML classification models for the failure severity prediction of protective-coating defects via AE signals.

Weak Fault Diagnosis Method of Rolling Bearings Based on Variational Mode Decomposition and a Double-Coupled Duffing Oscillator

Aiming at the problems of the low detection accuracy and difficult identification of the early weak fault signals of rolling bearings, this paper proposes a method for detecting the early weak fault signals of rolling bearings based on a double-coupled Duffing system and VMD. The influence rule of system initial value on the response characteristics of a double-coupled Duffing system is studied, and the basis for its determination is given. The frequency of the built-in power of the system is normalized, and a variance evaluation standard for the output value of the double-coupled Duffing system for weak fault signals detection is established. In order to solve the interference problem of fault monitoring signals, VMD is proposed to pre-process the fault monitoring signals. The weak fault signal detection method proposed in this paper is tested and verified by simulation signals and rolling bearing fault signals. The results show that the method proposed in this paper can detect the weak fault signal with the lowest signal-to-noise ratio reduced by 2.96 dB compared with the traditional Duffing detection system, and it can accurately detect the early weak fault signal of rolling bearings.

A generalized proportional‐integral observer for fault detection: An approximate input disturbance decoupling approach

SummaryThis article proposes a generalized PI observer with approximate disturbance decoupling (ADD‐GPIO) for detecting incipient actuator faults of a system subject to periodic input disturbances. Robustness to disturbances and sensitivity to faults is achieved through dynamic configuration of the disturbance transmission zeros and pole‐optimization respectively. By incorporating the ‐gap metric with index, a novel interpretable fault sensitivity optimization objective function is proposed. It is the first time in the fault detection observer design that the difference between the transfer function matrices (TFMs) relating fault detection residual to the disturbances and faults is quantified by the proposed ‐gap metric, which allows a more differentiated treatment of the disturbance and fault signals for better fault detection. Then, the optimal design of the ADD‐GPIO is modeled as a mixed‐integer optimization problem and the Lagrangian relaxation is adopted to find the near‐optimal parameters of the ADD‐GPIO at less computation costs in real application. Finally, both simulation and lab experiments of a two‐wheeled self‐balancing robot are carried out to validate the improved performance of the proposed method.

Preface

The 2023 6th International Conference on Mechanical, Electrical, and Material Applications (MEMA 2023) was successfully held in Changsha, China from February 24th to 26th, 2023 (virtual event). This Seminar was the sixth in a series of topical meetings, and the MEMA series of conferences have come to all successful conclusions in Xi’an, Chongqing, and Chengdu from 2018 to 2022. MEMA 2023 was attended by about 150 participants from different countries.For this fourth meeting we chose Changsha to be our Conference Venue and met with our old and new friends again. While the location of the Conference has been changed sometimes, what remained invariant is the aim of these meetings, which is to discuss recent advances and key challenges and explore new perspectives and research directions facing the development of mechanical, electrical, and material applications in a pleasant and friendly atmosphere. At this meeting we had a comprehensive overview of this fascinating field and of future scenarios thanks to the participation of leaders of the most important projects.The Conference presented an outstanding program of papers covering the most recent advances in mechanical, electrical, and material applications, including Mechanical Dynamics, Precision Machinery, Electromagnetic Compatibility, High Voltage and Insulation Technology, Circuits and Systems, Functional Materials, etc.. The papers in this Proceedings published by Journal of Physics: Conference Series-IOP Publishing represent a collection of the invited talks and academic contributions.The Conference Program consisted of four invited speeches presented in the plenary sessions, including four hot topic speeches highlighting the most recent advances in the field, and various oral presentations. The program included a speech by Dejie Yu who is Member of the Standing Committee of the Hunan Provincial CPPCC and Professor in the College of Mechanical & Vehicle Engineering of Hunan University, a speech title with “Research on Weak Fault Signal Detection Method Based on Gradient Acoustic Metamaterials”. Aiming at the problem that weak signal is difficult to detect, an enhanced detection method based on gradient index acoustic metamaterial was proposed. And still a fault signal enhancement detection method based on gradient index acoustic metamaterial was proposed.We would like to thank the participants, especially those who contributed speeches, posters and manuscripts, for making MEMA 2023 such an exciting and memorable conference. We thank the Technical Program Committee for putting together an outstanding Program. Finally, we thank the Local Organizing Committee for their tireless and expert efforts in the organization of MEMA 2023, and all of our colleagues whose friendly and efficient service contributed much to the success of the Conference.The Committee of MEMA 2023List of Committee Member is available in the pdf

Two combination methods of piecewise unsaturated tri-stable stochastic resonance system and bearing fault detection under different noise

In this paper, a piecewise unsaturated tri-stable stochastic resonance (PUTSR) system is proposed to address the issue of output saturation. Firstly, the unsaturated characteristics of the PUTSR system are verified, followed by a discussion on the system performance of PUTSR under two different combinations of coupled and cascaded systems. The two-dimensional coupled piecewise unsaturated tri-stable stochastic resonance (TCPUTSR) system and cascaded piecewise unsaturated tri-stable stochastic resonance (CPUTSR) system are proposed. By implementing the adiabatic approximation theory, the steady-state probability density (SPD) of TCPUTSR system and spectral amplification (SA) coefficient of TCPUTSR and CPUTSR systems are derived respectively. The impact of different system parameters on the SPD and SA are also investigated. Finally, PUTSR, TCPUTSR and CPUTSR systems are applied to detection on the fault signal of bearing. Gaussian white noise and color noise are used to simulate actual noise environments in the experiments, while the adaptive genetic algorithm (AGA) is used to optimize the parameters and measure the system performance via signal-to-noise ratio improvement (SNRI). Results indicate that both coupled and cascaded systems demonstrate better detection capabilities than individual systems, with the CPUTSR system offering better enhancement and detection of bearing fault signals. Under Gaussian white noise, the SNRI of the CPUTSR system is 1.449 dB ~ 3.198 dB higher than that of the PUTSR and TCPUTSR systems, while under color noise it is 1.566 dB ~ 2.849 dB higher. This paper mainly compares the spectral amplification capability and fault signal detection capability of the same system under two different combinations of coupled and cascaded. The theoretical and numerical simulations further verify that the designed cascaded system outperforms the coupled system and proves the great superiority of CPUTSR system. These findings provide crucial theoretical support and practical application prospects for engineering purposes.

From Online Systems Modeling to Fault Detection for a Class of Unknown High-Dimensional Distributed Parameter Systems

Fault detection for distributed parameter systems reported so far is model-based in general and the performance heavily relies on the prior known model information. This restricts the usability of these methods in industrial applications. In this paper, we make the first attempt to establish a brand-new framework that contains both on-line systems modeling and fault detection of unknown high-dimensional DPSs. These two parts interact with each other in the sense that the systems modeling error is transformed into the residual signal for fault detection while the on-line modeling switches to off-line mode depending on the fault detection results. The high-dimensional DPSs are first decomposed into spatial features and temporal sequences. Then a receding-horizon scheme is applied for the temporal dynamics learning and the residual signal is converted by the temporal validation error. Experiments on sensor faults diagnosis for the thermal process of a 2-D battery cell are provided for method validation.