Early Fault Research Articles

Active Adaptive Composite Fault Tolerant Controller Design For Nonlinear Systems

Abstract It can be seen from the public opinion monitoring that there are many cases of death and injury caused by quality problems of mechanical products, which poses a serious threat to people’s lives. Therefore, it is particularly important to analyze the reliability of mechanical products. This study focuses on active adaptive composite fault tolerant controller (ACFTC) design for nonlinear system with actuator fault. Firstly, a novel iterative learning observer (ILO) is proposed to estimate the early potential fault. And then, the ACFTC approach is proposed in order to obtain desired performance in the faulty case based on the fault estimation information from ILO. Finally, simulation of the flexible joint robot system verifies the validity and applicability of the algorithm.

An extraction method for early fault features of rolling bearings based on resonance sparse signal decomposition and non-convex second-order total variation denoising

A primary challenge in the field of fault diagnosis is extracting weak fault characteristics of bearings under large background noise and non-stationary conditions. Due to significant noise interference in the signals of rolling bearings, resonance sparse signal decomposition (RSSD) cannot efficiently extract the transient impact components in the early failure stage and the total variation denoising (TVD) method distorts signal waveforms. In this study, a combined extraction method for early fault features of rolling bearings based on RSSD and non-convex second-order total variation denoising (NCSOTVD) is proposed. Firstly, a non-convex function is introduced to define the regularisation term in the second-order TVD method, and the regularisation parameter and the convexity parameter in the NCSOTVD method are respectively screened using the noise standard deviation and the permutation entropy value to enhance the impact characteristics of signals and induce signal sparsity. The NCSOTVD model is solved using the optimisation-minimisation algorithm, so as to achieve noise reduction and feature enhancement of the vibration signals. Then, the low-resonance components of RSSD are denoised using the NCSOTVD method to highlight periodic pulse signals and extract the fault features of the rolling bearings. The simulation results and experimental data show that the method largely suppresses the noise interference, highlights the fault characteristics and reduces the problems of waveform distortion and poor sparsity of the TVD method in the denoising process.

Early fault detection via combining multilinear PCA with retrospective monitoring using weighted features

Early fault detection via combining multilinear PCA with retrospective monitoring using weighted features

Lock-in spectrum: a tool for representing long-term evolution of bearing fault in the time–frequency domain using vibration signal

PurposeThis study aims to propose a method for monitoring bearing health in the time–frequency domain, termed the Lock-in spectrum, to track the evolution of bearing faults over time and frequency.Design/methodology/approachThe Lock-in spectrum uses vibration signals captured by vibration sensors and uses a lock-in process to analyze specified frequency bands. It calculates the distribution of signal amplitudes around fault characteristic frequencies over short time intervals.FindingsExperimental results demonstrate that the Lock-in spectrum effectively captures the degradation process of bearings from fault inception to complete failure. It provides time-varying information on fault frequencies and amplitudes, enabling early detection of fault growth, even in the initial stages when fault signals are weak. Compared to the benchmark short-time Fourier transform method, the Lock-in spectrum exhibits superior expressive ability, allowing for higher-resolution, long-term monitoring of bearing condition.Originality/valueThe proposed Lock-in spectrum offers a novel approach to bearing health monitoring by capturing the dynamic evolution of fault frequencies over time. It surpasses traditional methods by providing enhanced frequency resolution and early fault detection capabilities.

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.

An Optimal Spatio-Temporal Hybrid Model Based on Wavelet Transform for Early Fault Detection.

An optimal spatio-temporal hybrid model (STHM) based on wavelet transform (WT) is proposed to improve the sensitivity and accuracy of detecting slowly evolving faults that occur in the early stage and easily submerge with noise in complex industrial production systems. Specifically, a WT is performed to denoise the original data, thus reducing the influence of background noise. Then, a principal component analysis (PCA) and the sliding window algorithm are used to acquire the nearest neighbors in both spatial and time dimensions. Subsequently, the cumulative sum (CUSUM) and the mahalanobis distance (MD) are used to reconstruct the hybrid statistic with spatial and temporal sequences. It helps to enhance the correlation between high-frequency temporal dynamics and space and improves fault detection precision. Moreover, the kernel density estimation (KDE) method is used to estimate the upper threshold of the hybrid statistic so as to optimize the fault detection process. Finally, simulations are conducted by applying the WT-based optimal STHM in the early fault detection of the Tennessee Eastman (TE) process, with the aim of proving that the fault detection method proposed has a high fault detection rate (FDR) and a low false alarm rate (FAR), and it can improve both production safety and product quality.

Bearing fault diagnosis based on POA-VMD with GADF-Swin Transformer transfer learning network

To address the challenges posed by early weak fault signals hindering fault feature extraction and leading to diminished recognition accuracy in deep learning models, we present a method for diagnosing bearing faults. This method integrates the Pelican Optimization Algorithm (POA), Variational Mode Decomposition (VMD), Gramian Angular Difference Fields (GADF), and the Swin Transformer network. Initially, the VMD’s key parameter are optimized through POA to dynamically yield the optimal parameter combination. Subsequently, the refined VMD is employed to decompose the original signal. The intrinsic modal function (IMF) is subsequently filtered, and the signal is reconstructed using the weighted composite kurtosis(WCK) index. Following this step, the reconstructed 1D signal is converted into a 2D image using GADF and is then input into the constructed Swin Transformer transfer learning network model for the purpose of training. In conclusion, a fault diagnosis experiment was conducted using the measured signal, which showed the successful extraction of the signal’s characteristics and octave frequencies through the method presented in this paper. Moreover, concerning fault identification, an identification accuracy exceeding 95% was achieved.

BC-GAN: A threshold-free framework for unsupervised early fault detection in rotating machinery

Early fault detection (EFD) is a crucial component of proactive maintenance that can prevent expensive downtime, enhance safety, and optimize equipment performance and longevity. Existing limitations of the contemporary EFD approaches frequently include: (1) manually designed features relying on expert skills and knowledge, (2) the vaguely determined pre-set thresholds to distinguish between the faulty and healthy state of the testing object (however, the threshold value can vary notably from task to task), and (3) most methods, which have been originally designed for vibration data, cannot be generalised to other techniques, for example acoustic emission (AE) signals. To address these issues, a novel binary-classification generative adversarial network (BC-GAN) is designed for general EFD problems and applied to several specific datasets acquired from different run-to-failure tests of rotating components. Compared with conventional methods, unsupervised BC-GAN directly outputs the probability that an input belongs to either the “health” or “fault” state of the rotating machine without a priory threshold setting. Experimental results demonstrate the high versatility of the proposed network, which can be applied in various laboratory and industrial settings to both vibration and AE signals.

Early micro-short circuit fault diagnosis of lithium battery pack based on Pearson correlation coefficient and KPCA

Though lithium batteries have been extensively applied in electric vehicles as the power sources due to the excellent advantages in recent years, the safety risk of them is always existed inarguably. For the effect of early micro-short circuit faults on the electrical characteristics of the batteries is minor, it is hard to be detected and diagnosed timely, as a result it may evolve into direct short circuit and cause severe safety accidents, such as thermal runaway, explosion and so on. This paper proposes a method for diagnosing micro-short circuit fault in battery pack based on Pearson correlation coefficients (PCCs) and kernel principal component analysis (KPCA). Firstly, the voltage values of each battery in various operation states are measured and denoised using a moving filter method, then PCCs between each battery's voltage of the same series branch are calculated to form a dataset. Secondly, the dataset of PCCs is taken to train KPCA algorithm to obtain the control threshold by calculating the squared prediction error (SPE) statistic. After the training process finished, the PCCs of real-time voltage values of the batteries are calculated, then the related SPE statistic is calculated to determine whether the threshold is exceeded or not, meanwhile the contribution graph will be drawn if the threshold is exceeded. Finally, the faulty cell can be cross localized according to the feature of contribution rate in the contribution graph. Experiments are carried out under the condition of Dynamic Stress Test (DST), and comparisons are performed with principal component analysis (PCA) algorithm by using the different input features, such as raw voltage data, Kendall and Spearman correlation coefficient, respectively. The experimental results show that, the proposed method can diagnose the fault as soon as it occurred, and the feature of contribution rate is more obvious than other methods, which is beneficial to the fault localization. Moreover, for the fault judgment only depends on the correlation of the battery's voltages rather than the absolute values of them, which always vary obviously in different operation states, the proposed method can be applied in various engineering scenarios expediently.

Model-based diversity-driven learn-to-rank test case prioritization

Model-based Test Case Prioritization utilizing similarity metrics has proved effective in software testing. However, the utility of similarity metrics in it varies with test scenarios, hindering its universal effectiveness and performance optimization. To tackle this problem, we propose a Diversity-driven Learn-to-rank model-based TCP approach, named DLTCP, for optimizing early fault detection performance. Our method first employs the whale optimization algorithm to search for a suitable set of similarity metrics from a pool of existing candidates. This search process determines which metrics should be used. According to each selected metric, test cases are then prioritized. The resulting test case rankings are used as the training data for DLTCP. Finally, the proposed method incorporates random forest to train a ranking model for test case prioritization. As such, it can fuse multiple similarity metrics to improve the TCP performance. We conduct extensive experiments to evaluate our method’s performance using the average percentage fault detected (APFD) as metric. The experimental results show that DLTCP achieve an average APFD value of 0.953 for seven classic benchmark models, which is 11.37% higher than that of the state-of-the-art algorithms. It can well select a set of similarity metrics for effective fusion, demonstrating competitive performance in early fault detection.

Canonical variate residual analysis for industrial processes fault detection

AbstractWith the rapid development of intelligent integration in industrial processes, a challenge emerges. Early failures cannot be detected in a timely manner, potentially leading to significant financial losses. While traditional canonical variate analysis (CVA) methods are effective for dynamic process monitoring, they may lack the flexibility required for early fault detection. To address this challenge, a fault detection method based on canonical variate residual analysis (CVRA) is proposed. CVRA introduces a distinctive residual statistic that preserves critical information about the data. It places heightened focus on the primary components of the data, capturing core features of system changes and enhancing sensitivity to early anomalies. Additionally, by incorporating the geometric properties of the Manhattan distance, it mitigates statistical data errors, thereby improving detection accuracy. Simulation results validate the method's effectiveness in the Tennessee Eastman (TE) process. Furthermore, the successful application of the three‐phase flow facility provides a benchmark for evaluation using real process data.

Wind turbine gearbox condition monitoring using AI-enabled virtual indicators*

Abstract At present, the condition monitoring of wind turbine gearbox mostly involves selecting monitoring indicators in advance and establishing normal behavior models based on deep learning. However, single physical monitoring indicator cannot fully characterize the operating status of the wind turbine gearbox. To address the above issues, a wind turbine gearbox condition monitoring method using convolutional neural network (CNN)-long and short term memory network (LSTM)-autoencoder (AE) enabled virtual indicators is proposed in this paper. This method first establishes a cleaning principle to preprocess the data of supervisory control and data acquisition (SCADA) system and screen out effective SCADA data further. A CNN-LSTM-AE monitoring model was trained using SCADA data during normal operating process, various characteristic parameters of the gearbox are integrated to construct the AI-enabled virtual indicators, and meanwhile warning thresholds was determined based on the probability density distribution of virtual indicators to analyze the operating status of the gearbox. Finally, the proposed method was validated using real SCADA data from two wind turbines in a cooperated wind farm with my group. Compared with a single physical indicator, the virtual indicator enables to detect gearbox early faults 5 d in advance, indicating that the proposed method can effectively alert wind turbine gearbox failures.

Bearing race fault detection using an optomechanical micro-resonator

Bearing fault detection plays a crucial role in ensuring machinery reliability and safety. However, the existing bearing-fault-detection sensors are commonly too large to be embedded in narrow areas of bearings and too vulnerable to work in complex environment. Here, we demonstrate an approach to distinguish the presence of race faults in bearings and their types by using an optomechanical micro-resonator. The principle of the amplitude-frequency modulation model mixing fault frequency with mechanical frequency is raised to explain the asymmetrical sideband phenomena detected by the optical microtoroidal sensor. Kurtosis estimation used in this work can distinguish normal and faulty bearings in the time domain with the maximum accuracy rate of 91.72% exceeding the industry standard rate of 90%, while the amplitude-frequency modulation of the fault signal and mechanical mode is introduced to identify the types of the bearing faults, including, e.g., outer race fault and inner race fault. The fault-detection methods have been applied to the bearing on a mimic unmanned aerial vehicle (UAV), and correctly confirmed the presence of fault and the type of outer or inner race fault. Our study gives new perspectives for precise measurements on early fault warning of bearings, and may find applications in other fields such as vibration sensing.

Fault root cause analysis using degree of change and mean variable threshold limit in non-linear dynamic distillation column

The chemical industrial processes are both dynamic and complex. The presence of instability and danger in the production process poses significant challenges to safety management. Early and accurate fault diagnosis is essential to ensure a sustainable and stable chemical process performance. Most studies in literature do not provide detailed information about diagnosing the root cause of faults in distillation columns using contribution plots. Using principal component analysis (PCA) in conventional contribution plots leads to a large number of contributing variables, making it difficult to identify the root cause of a specific fault. In this study, the authors suggest employing the Degree of Change of Contribution Values (DCC) and Mean Variable Threshold Limit (LMVT) techniques alongside the Wavelet Transform-Principal Component Analysis (WT-PCA) method to decrease the quantity of fault identification variables in a non-linear system (distillation column). The Aspen Plus software is utilized to perform a dynamic simulation of a distillation column, generating data for both normal and faulty operations. Two distinct types of faults are considered, which include loss of feed flow and feed temperature changes. This study aims to analyze the results obtained from the Hotelling T2 and SPE contribution plots by calculating the average difference between the normal and faulty conditions using the Degree of Change in Contribution Values. This procedure is performed to determine the extent of deviation from the standard state. Subsequently, the variables that have surpassed the threshold limit for means variables (LMVT) are designated as the variables that serve as the primary underlying cause of the fault. The technique was employed in a case study involving a nonlinear distillation column, and the results indicate that only one "dominant" variable intersects the LMVT by Hotelling T2, which represents the true underlying cause of the corresponding fault.

Real-time multivariate statistical monitoring of biopharmaceutical processes with no prior product-specific history

Biologics drug substance manufacturing normally comprises several processing steps including cell culture, purification, etc. Real-time Multivariate Statistical Process Monitoring (RT-MSPM) is an integral need in order to achieve early fault detection and prevention to guarantee robust and efficient process performance. As a part of RT-MSPM framework, Batch Evolution Models (BEMs), which take into account the transient phase of a batch prior to reaching full maturity (steady state), are the standard methods for real-time early fault detection in batch processes. Prior product-specific knowledge and training dataset are critical in order to model time (batch maturity) dependencies. Unlike traditional settings, modern biopharmaceutical manufacturing and clinical facilities use modular designs to enable simultaneous production of multiple medicines and quickly pivot from producing one medicine to another where no prior product-specific historical data might be available. In this article, first, a framework is proposed to detect the steady state operation of a manufacturing scale cell culture bioreactor. This is critical to achieve the ultimate goal to demonstrate feasibility of developing a continuous statistical process monitoring framework to monitor the steady state operation of a batch with no prior product specific history. Steady state time series data from previous step are processed following a systematic approach. The requirements for statistical properties of the processed time series in order to leverage data from different products to monitor a new product are outlined. The new framework establishes a guideline to develop models using datasets from other products with different recipes to monitor new products with no prior product-specific history. A novel software product is developed to test the framework. The framework is successfully applied for real-time monitoring of fast-rate sensors of a manufacturing cell culture bioreactor.

A Time Series Prediction-Based Method for Rotating Machinery Detection and Severity Assessment

Monitoring the condition of rotating machinery is critical in aerospace applications like aircraft engines and helicopter rotors. Faults in these components can lead to catastrophic outcomes, making early detection essential. This paper proposes a novel approach using vibration signals and time series prediction methods for fault detection in rotating aerospace machinery. By extracting relevant features from vibration signals and using prediction models, fault severity can be effectively quantified. Our experimental results show that the proposed method has potential in early fault detection and is applicable to various types of bearing faults and the different statuses of these faults under complex running conditions, achieving very good generalization ability.

The Uncertainty Evaluation of Determining the Trace H2S in SF6/N2 Insulating Gas Mixture by Cavity Ring-Down Spectroscopy

Abstract H2S is one of the most important characteristic components of sulfur hexafluoride gas insulated electrical equipment. The detection of trace H2S is of great significance for early fault diagnosis of such equipment. Based on the 1578 nm wavelength distributed feedback diode laser (DFB-DL), cavity ring-down spectroscopy (CRDS) can effectively measure the concentration of trace H2S in SF6/N2 gas mixtures. Starting from the principle of methodology, this article establishes a mathematical model for evaluating the measurement uncertainty of CRDS and analyzes its sources of uncertainty: gas constant R1 , temperature T, Avogadro constant NA , gas pressure p in the optical cavity, volume V of the optical cavity, speed c of light, the absorption cross-section parameter σ(ν) of H2S molecules in the laser frequency ν, the ring-down time τ with absorption sample H2S and the ring-down time τ0 without absorption sample. After evaluating the uncertainty components, it was found that the main component was σ(ν) and the secondary components were τ and τ0. The H2S content in the 80% SF6-20% N2 mixed gas measured is (7.64 ± 0.12) × 10−6 mol/mol.

Enhancing Predictive Maintenance in Contour Cutting Machines: A Similarity-Based Approach for Band Blade Remaining Useful Life Estimation and Early Fault Detection

Anticipating the Remaining Useful Life (RUL) of cutting tools is crucial for optimising operational efficiency, ensuring safety, and minimising maintenance costs. This paper addresses the unresolved challenge of unexpected band blade failures in contour cutting machines within the foam and plastic industry, where such failures disrupt production, lead to material wastage, and pose operational hazards. Band blades circulate continuously at very high speeds during operation, and no classic sensor technology can be applied to them. Any information required to estimate the condition of the band blades must be acquired externally. Using similarity-based prediction models, a strategy for estimating band blades' effective RUL is proposed. Historical failure data is systematically collected from a contour-cutting machine operating under various load conditions using multiple contact and non-contact sensors mounted on the machine. Features are extracted and processed from the mounted sensors in both time and frequency domains using classical condition monitoring techniques. The classification of damaged and undamaged states of the blade is performed using bagged decision trees, which consider predefined health levels of the band blade during test runs. Degradation trends are generated for a test set of blade failures, and a similarity model is trained on this data to determine the remaining life. Different features are selected based on their prognostic capabilities to optimise the proposed algorithm's performance. The developed model is tested on new data, demonstrating efficacy in predicting band blades' health status and RUL with good accuracy. This research contributes to cutting tool condition monitoring and predictive maintenance by offering a novel and reliable approach for early fault detection and estimation of the RUL of band blades in contour cutting machines, mitigating disruptions, reducing material wastage, and enhancing overall operational efficiency. The procedures are validated in situ with a latest generation's real contour-cutting machine.

An early-fault diagnostic method based on phase plane for lithium-ion batteries under complex operation conditions

Timely and accurate diagnosis of lithium-ion battery faults is crucial for ensuring the safety of electric vehicles. While incremental capacity (IC)-based diagnostic methods are effective, they can only be employed under charging conditions. To address this issue, a fault diagnostic method based on phase plane analysis is proposed to extend the application to various operating conditions. In a phase plane, the battery voltage is plotted on the x-axis, while the differential in voltage is plotted on the y-axis. During charging, diagnostic vectors indicating the occurrence and type of faults are extracted from the trajectories in the phase plane. Under complex operating conditions, early faults can be detected based on the morphological and scale deviation of the trajectories. Experimental results have shown that the proposed method can effectively detect minor faults. The fault detection rate and detection accuracy rate under charging conditions are 96.25 % and 97.73 %, respectively, which are 17.5 % and 8.54 % higher than those of the IC-based diagnostic method. Furthermore, the fault detection rate and accuracy rate under UDDS (Urban Dynamometer Driving Schedule) are 91.76 % and 97.23 %, respectively. Additionally, the diagnostic speed of the proposed method is twice as fast as that of the IC-based method.

Diagnosis of Rotor Component Shedding in Rotating Machinery: A Data-Driven Approach.

The potential for rotor component shedding in rotating machinery poses significant risks, necessitating the development of an early and precise fault diagnosis technique to prevent catastrophic failures and reduce maintenance costs. This study introduces a data-driven approach to detect rotor component shedding at its inception, thereby enhancing operational safety and minimizing downtime. Utilizing frequency analysis, this research identifies harmonic amplitudes within rotor vibration data as key indicators of impending faults. The methodology employs principal component analysis (PCA) to orthogonalize and reduce the dimensionality of vibration data from rotor sensors, followed by k-fold cross-validation to select a subset of significant features, ensuring the detection algorithm's robustness and generalizability. These features are then integrated into a linear discriminant analysis (LDA) model, which serves as the diagnostic engine to predict the probability of rotor component shedding. The efficacy of the approach is demonstrated through its application to 16 industrial compressors and turbines, proving its value in providing timely fault warnings and enhancing operational reliability.