Component Faults Research Articles

Weak Compound Fault Identification of Gearboxes Based on Improved Symplectic Geometric Mode Decomposition and Optimized Cyclic Kurtosis Deconvolution

Abstract Given the complex and harsh operating conditions of gear transmission systems, gearboxes are prone to compound faults. These faults, involving multiple types, often couple together, causing the weak fault pulse characteristics to be entirely masked by strong environmental noise. This significantly complicates the extraction of relevant fault information from the gearbox. To address these issues, this paper proposes a method for extracting compound fault features based on improved symplectic geometric mode decomposition (SGMD) and optimized cyclic bispectrum deconvolution (CYCBD). Firstly, considering the periodic impact characteristics of different fault types, morphological envelope cyclic bispectrum is proposed to cluster the initial components obtained from SGMD decomposition, thereby adaptively separating different fault features contained in the compound fault signals. An adaptive filter length search strategy is subsequently introduced to optimize the CYCBD by deconvolving each initial fault component, thereby eliminating the interference caused by complex transmission paths and substantial environmental noise, which, in turn, enhances weak periodic fault pulses. Following this, the enhanced signals are subjected to envelope demodulation to extract fault characteristic frequencies, enabling the identification of various types of faults. The effectiveness and feasibility of the proposed method are demonstrated through both simulation signals and actual experimental data related to gearbox compound faults. Compared with existing methods, the proposed method demonstrates superior performance in identifying weak compound faults under strong environmental noise.

Research on noise reduction method of centrifugal pump coupling fault signal based on LMD-FE-IWT

Abstract Aiming at the problem that the coupling fault signal of centrifugal pump presents the complexity of mutual coupling due to the mutual influence of various fault components, and it is easy to be affected by the surrounding environmental noise, which leads to the difficulty of noise reduction, the LMD-FE-IWT noise reduction method is proposed. This method first utilizes local mean decomposition (LMD) to adaptively decompose the vibration signal, and calculates the fuzzy entropy of each component. According to fuzzy entropy, the components are divided into two categories: disordered and ordered. After the improved wavelet threshold denoising of the disordered component, it is reconstructed with the ordered component to achieve the denoising effect. By analying the simulation signal and experimental data, the results show that, the proposed method outperforms other methods, with improvements in signal-to-noise ratio by 55.95%, 48.86%, and 31.71% for the simulation signal noise reduction. The effect is significant, enabling the effective extraction of characteristic frequencies associated with different faults for the experimental signal noise reduction.

Order-difference of normalized square envelope spectrum and its applications in early chatter detection of roll grinder

Roll grinder is widely demanded in grinding the surface of rolls that will be used to mill steel strips for high-quality automobile outer panels. The grinding chatter generally leads to poor machining accuracy and massive economic losses. The significance of roll grinder vibration monitoring is to detect the early grinding chatter. However, in harsh working conditions, some chatter detection methods inevitably confuse the fault components and interference components in vibration signals and the chatter feature information cannot be extracted exactly. The dynamical model of roll grinder system reveals that the spectrums of vibration signals contain intrinsic frequency components and chatter frequency components under health and chatter conditions. Based on the analytical modelling, a new health index order-difference of normalized square envelope spectrum (ODNSES) is proposed to detect early chatter and evaluate the health degradation of the roll grinder. The normalized square envelope spectrum (SES) is used as the pretreatment of ODNSES to compare the frequency components in vibration signals under health and early chatter conditions. Furthermore, order-difference of normalized SES is proposed to suppress the noise interference and to enable ODNSES to characterize the grinding chatter process. The detailed simulation research is performed to verify three important properties of ODNSES. The experimental results show that ODNSES would not be interfered by background noise significantly and it is on average 29.12% more sensitivity to impulse amplitudes than classical health indexes. The testing results on actual roll grinder exhibit that ODNSES can detect the early chatter and quantify the abnormal vibration in the grinding process.

Calibration of a hybrid model for HVAC systems for fault data generation

The application of automated fault detection and diagnosis algorithms has proven to be an effective way to increase the energy efficiency of buildings. While data-driven strategies have demonstrated their potential in developing such algorithms, they require a set of historical data that represents both healthy and faulty equipment operation, which is not a common scenario in real facilities. This article presents a methodology for the generation of synthetic data on both healthy and faulty operation for building heating and air conditioning equipment, which is especially useful for supervision and failure detection in the case of replication and expansion of buildings in tertiary or residential building planning programmes. This work investigates the automatic calibration of a typical air-handling unit hybrid model, composed of the detailed parametric representation of the system components and its control sequence coupled with a simplified thermal load. The model is then extended with fault models that resemble commonly encountered component faults to generate operation data in faulty scenarios. The proposed framework is validated in a real use case with the calibration of an air-handling unit system and its control sequence using 15 days of data gathered from the building management system. The results obtained from the injection of seven typical faults are then compared with the fault-free simulations to highlight and validate their impact on key operating variables. The results prove the capabilities of this methodology to support database generation in the fields of fault detection and advanced maintenance of buildings’ air conditioning systems for building replicas.

Influence of velocity pulse directivity on seismic response of cross-fault bridges

Pulse-type ground motions have special destructive effects on structures, and directivity is one of the fundamental characteristics of velocity pulses. In this paper, the impact of the velocity pulse directivity of seismic motions on both sides of the fault on the seismic response of fault-crossing bridges was quantified using the original records from the Chi-Chi earthquake in Taiwan. First, an automatic baseline correction method was applied to restore the permanent ground displacement, and the direction corresponding to the strongest pulse energy on both sides of the fault was identified based on continuous wavelet transformation. On this basis, the variability of the peak intensity of ground motions on the hanging wall and footwall in different directions, as well as the differences in pulse characteristics between the strongest pulse component and the two initial horizontal components, were analysed. Finally, a typical 5 × 30 m continuous girder bridge was considered as the research object to reveal the influence of the velocity pulse directivity on the seismic response of key parts on both sides of the fault. The results showed that the variability in the peak ground-motion intensity on the hanging wall of the fault was higher than that on the footwall. The displacement variability was up to 863 %, velocity was 262 %, and acceleration was 124 %. The pulse characteristics of the strongest pulse component were stronger than those of the parallel and vertical fault components, and its acceleration, velocity, and displacement response spectra were larger. The amplification effects of the velocity pulse directivity on the transverse bending moment, longitudinal bending moment, and torque of the pier bottom reached 1.3, 1.1, and 1.6, respectively. However, the amplification effect of the velocity pulse directivity on the relative displacement of the pier top, displacement of the main beam, and displacement of the bearing was more than 1.6 times, which was more significant than the internal force of the pier bottom.

Multi-Source Information-Based Bearing Fault Diagnosis Using Multi-Branch Selective Fusion Deep Residual Network.

Rolling bearing is the core component of industrial machines, but it is difficult for common single signal source-based fault diagnosis methods to ensure reliable results since sensor signals are vulnerable to the pollution of background noises and the attenuation of transmitted information. Recently, multi-source information-based fault diagnosis methods have become popular, but the information redundancy between multiple signals is a tough problem that will negatively impact the representational capacity of deep learning algorithms and the precision of fault diagnosis methods. Besides that, the characteristics of various signals are actually different, but this problem was usually omitted by researchers, and it has potential to further improve the diagnosing performance by adaptively adjusting the feature extraction process for every input signal source. Aimed at solving the above problems, a novel model for bearing fault diagnosis called multi-branch selective fusion deep residual network is proposed in this paper. The model adopts a multi-branch structure design to enable every input signal source to have a unique feature processing channel, avoiding the information of multiple signal sources blindly coupled by convolution kernels. And in each branch, different convolution kernel sizes are assigned according to the characteristics of every input signal, fully digging the precious fault components on respective information sources. Lastly, the dropout technique is used to randomly throw out some activated neurons, alleviating the redundancy and enhancing the quality of the multiscale features extracted from different signals. The proposed method was experimentally compared with other intelligent methods on two authoritative public bearing datasets, and the experimental results prove the feasibility and superiority of the proposed model.

Application of PCA-LSTM algorithm in predicting component faults in CNC machining centers

Abstract In order to further explore the relationship between component failures and CNC machining center failures, a method of predicting component failures in advance was proposed to reduce the likelihood of machining center failures and improve CNC machining efficiency. In this paper, the principal component analysis method is used to optimize the Long short-term memory neural network to build a network model to study and predict the fault status of NC machining center components in work. The use of Principal Component Analysis (PCA) to extract the main features of machine tool faults can improve the speed of iterative training networks during the machining process and reduce the input dimension and prediction difficulty of LSTM. The extracted data is used as input for the LSTM network. The fault type is output. The comparison of diagnostic results between PCA-LSTM, LSTM, and BP neural networks shows that PCA-LSTM is a high-precision prediction model. The root mean square difference is reduced to 1.572. The predicted error results can effectively reflect the changes that occur in the machining center components with the occurrence of faults. It can be seen that it is feasible to use PCA-LSTM as a tool for predicting the faults of CNC machining center components.

Physics-informed unsupervised domain adaptation framework for cross-machine bearing fault diagnosis

Varying components and operating conditions in industrial machines lead to different distribution characteristics and fault states of monitoring data for critical rotating machinery. Adequate and accurate labelling of monitoring data is challenging to achieve. Existing data-driven unsupervised domain adaptation methods exhibit poor interpretability and low confidence in the target domain’s pseudo-labelling. Therefore, a physics-informed unsupervised domain adaptation framework is proposed. Data and physical information are combined to enhance the reliability and interpretability of the model while ensuring its generalization capability. First, physical information is extracted by merging the knowledge of the mechanical component fault characteristics with indicators like the signal spectrum’s energy value. Subsequently, the physical label and loss are created. The physical loss is then embedded in the loss function of the source domain model. Next, by aligning the physical labels and the clustering results of the spectral clustering, the target domain samples’ hard pseudo-labels are obtained. The probability values of the sample belonging to each category as determined by the Wasserstein criterion comprise the soft pseudo-label of the sample. Furthermore, the confidence of hard pseudo-labels is continually increased by iteratively updating the probability values of soft pseudo-labels using the multi-label as a guide and the inverse improved sigmoid function as a gradient. Finally, unsupervised cross-machine diagnostic models with high robustness can be obtained. Three datasets are employed in the experimental section, and five sub-datasets are created and crossed for cross-machine experiments to confirm the suggested approach’s efficacy and superiority.

SF6 Decomposition Components Fault Diagnosis Based on Gaussian Process Classification and Decision Fusion

SF₆ Decomposition Components Fault Diagnosis Based on Gaussian Process Classification and Decision Fusion

Enhancing efficiency of large cold store refrigeration systems through automated fault identification and intelligent energy optimization

Refrigeration systems in large cold stores frequently operate suboptimally due to component faults, leading to significant energy wastage and high carbon emissions. This study introduces a novel procedure that leverages data mining to automatically analyze and identify faults, thereby enhancing the intelligence of refrigeration equipment. The research focused on abnormal suction temperatures of compressors during the defrosting of air coolers in a large cold store. Through theoretical analysis and key data acquisition, the root cause of defrosting issues was traced to the abnormal operation of gas-powered suction stop valves, causing leakage of high-pressure hot gas. Clustering methods, Self-Organizing Maps (SOM), were utilized to classify system states and achieved high accuracy rates of 88.6 % to 93.8 % for the three fault modes during the defrosting process, respectively. The resolution of defrosting faults resulted in an energy consumption reduction of up to 18.3 %, aligning with global sustainability initiatives. The study also evaluated the carbon emission reduction, providing a comprehensive approach to improving the efficiency and environmental impact of cold store operations.

Physical model and Bayesian theory based hydraulic component fault diagnosis method

Hydraulic components are integral parts of hydraulic systems, and their failures directly impact the normal operation of hydraulic systems. Due to the dynamic variation of working pressure in hydraulic components with load, it is challenging to diagnose faults of hydraulic components under dynamic pressure conditions using existing methods. This paper focuses on the research of internal leakage faults in hydraulic directional control valves and proposes a fault diagnosis method based on physical model and Bayesian theory for hydraulic components. Firstly, this method investigates the working fault mechanism of hydraulic directional control valves and constructs an internal leakage model. Then, correlation analysis is introduced to select fault feature signals, and principal component analysis is adopted to construct internal leakage features. Finally, based on Bayesian model, Markov chain Monte Carlo sampling, and internal leakage features, the parameters of the internal leakage model are estimated to achieve fault diagnosis of internal leakage in hydraulic directional control valves. Experimental results demonstrate that compared to several traditional fault diagnosis methods, the proposed method exhibits higher adaptability and accuracy under dynamic pressure conditions. This method, based on the internal leakage model and Bayesian theory, realizes fault diagnosis of hydraulic components under dynamic pressure conditions, avoiding the shortcomings of deep learning methods that rely on a large amount of fault data to train fault models.

Research on Classification Maintenance Strategy for More Electric Aircraft Actuation Systems Based on Importance Measure

In this paper, a practical maintenance algorithm is proposed to improve the reliability of actuation systems and their components, specifically addressing the consistency degradation caused by faults in the symmetric actuation system components of more electric aircraft (MEA). By integrating important measures with traditional genetic algorithms, the accuracy of the algorithm is improved. Prior to maintenance, a reasonable classification of components is built to mitigate the adverse effects of extreme fault conditions on the algorithm. This approach improves both the effectiveness and efficiency of the algorithm, rendering the overall maintenance strategy better suited for real-world needs. Finally, comparative simulations confirm the algorithm’s superior performance in reliability improvement, demonstrating its substantial contribution to the field of MEA maintenance and reliability.

A fault diagnosis method for hydraulic system based on multi-branch neural networks

As a key part of construction machinery, the hydraulic system is widely used in industrial fields. Due to its complexity and high integration, the fault diagnosis of hydraulic systems has always been a challenging problem. However, existing methods or models mainly focus on individual hydraulic system components while overlooking the interactions between different components, which are limited to specific application scenarios. Therefore, this research aims to develop a multi-task network model to diagnose faults in multiple components of hydraulic systems. Firstly, the initial data was collected from the hydraulic system test bench, in which the extreme gradient boosting (XGBoost) was introduced to evaluate the importance of all features under different fault types. Then, reduction dimensionality is achieved by setting a threshold for feature selection. Subsequently, a novel multi-branch deep neural network (MBDNN), which utilizes multiple branches to extract different information and correlations in the input data, is proposed and established. The multi-level combination of residual block and multi-branch connections enables MBDNN to achieve multiple types of fault diagnosis simultaneously and compensate for the problem of insufficient information representation in single-branch neural networks. The results of multiple rounds of experimental indicate that the MBDNN has higher robustness and accuracy in hydraulic system fault diagnosis than the existing general methods, and the diagnostic accuracy of multi-type faults is improved to 98.5%.

Security constrained optimal power shutoff for wildfire risk mitigation

AbstractElectric grid faults are increasingly the source of ignition for major wildfires. To reduce the likelihood of such ignitions in high risk situations, utilities use preemptive de‐energization of power lines, commonly referred to as Public Safety Power Shutoffs (PSPS). Besides raising challenging trade‐offs between power outages and wildfire safety, PSPS removes redundancy from the network at a time when component faults are likely to happen. This may leave the network particularly vulnerable to unexpected line faults that may occur while the PSPS is in place. Previous works have not explicitly considered the impacts of these outages. To address this gap, the Security Constrained Optimal Power Shutoff problem is proposed which uses post‐contingency security constraints to model the impact of unexpected line faults when planning a PSPS. This model enables, for the first time, the exploration of a wide range of trade‐offs between both wildfire risk and pre‐ and post‐contingency load shedding when designing PSPS plans, providing useful insights for utilities and policy makers considering different approaches to PSPS. The efficacy of the model is demonstrated using the EPRI 39‐bus system as a case study. The results highlight the potential risks of not considering security constraints when planning PSPS and show that incorporating security constraints into the PSPS design process improves the resilience of current PSPS plans.

Local fusion generative adversarial network with dual-discriminator and parallel multipath and its application in machinery fault diagnosis with imbalanced data

Abstract Diagnosing faults in critical machinery components is imperative for effective condition monitoring and real-world datasets often suffer from data imbalance. To address this issue, numerous data generation methods have been developed, such as improved local fusion generative adversarial network (ILoFGAN), variational autoencoding GAN (VAEGAN), etc. However, the existing data generation methods primarily concentrate on global and single-scale features and often ignore local or multi-scale features, which leads to the omission of key features or nuances in the generated data. Therefore, a novel approach called the Local Fusion Generative Adversarial Network with Dual-discriminator and Parallel multipath (LoFGAN-DP) is designed to enhance the fault diagnosis performance in the context of imbalanced data. The LoFGAN-DP features a Parallel Multi-Path (PMP) module along with a dual-discriminator scheme, in which the multipath module facilitates feature extraction at various scales through convolution across paths of diverse sizes, and the dual-discriminator scheme can better improve the quality and diversity of the samples generated by the generator. The PMP module and dual-discriminator scheme enhance the proposed method's robustness against variations in input data. After generating data by LoFGAN-DP, a two-dimensional capsule network is further used to achieve the efficient recognition of fault features. To validate the proposed LoFGAN-DP in the machinery fault diagnosis with imbalanced data, the gear dataset and the self-constructed bearing dataset were utilized. Experimental results show that LoFGAN-DP significantly improves Structural Similarity Index (SSIM), Fréchet Inception Distance (FID), and fault classification accuracy compared to several advanced methods.

Digital twin-enabled autonomous fault mitigation in diesel engines: An experimental validation

Due to the growing demand for robust autonomous systems, automating maintenance and fault mitigation activities has become essential. If an unexpected fault occurs during the travel, the system should be able to manage that fault autonomously and continue its mission. Thus, a robust fault mitigation system is needed that can quickly reconfigure itself in an optimal way. This paper presents a novel digital twin-based fault mitigation strategy that uses hierarchical control architecture. Here, a computationally efficient high-fidelity hybrid engine model is developed to simulate actual engine behavior. This hybrid engine model includes a neural network model representing the cylinder combustion process and well-studied physics-based analytical equations describing the remaining subsystems. This architecture uses a feedback controller on top of the control calibration map, generated offline using the hybrid model, to mitigate faults and modeling errors. The fault mitigation strategies are calibrated and validated through model-in-loop (MIL) and hardware-in-loop (HIL) simulations for various operating points using the Navistar 7.6 liters six-cylinder engine. The effectiveness of the proposed architecture in handling injector nozzle clogging, intake manifold leaks, and pressure shift faults is illustrated. The results demonstrate that the proposed architecture can completely overcome faults and maintain the desired torque in a few seconds. Moreover, the average accuracy of 96% is observed for the engine model compared to experimental data. It is anticipated that the proposed end-to-end architecture will be easily deployable on unmanned marine vessels and can be extended to accommodate other component faults.

A multi-period restoration approach for resilience increase of active distribution networks by considering fault rapid recovery and component repair

As the frequency of extreme weather events continues to rise, there is an urgent need to strengthen the safe and stable operation of active distribution networks (ADNs), and it is of great value to establish highly resilient ADNs to withstand multi-faults caused by extreme weather events. This paper proposes a multi-period restoration approach for the resilience increase of ADNs by considering fault rapid recovery and component repair under typhoon disasters. Firstly, based on the structural reliability theory, the failure rate model of the main components is established, and in light of the system information entropy, the typical fault scenario selection strategy is designed to determine the branches with high fault probability. Then, according to the fault islanding division and network reconfiguration, a fault rapid recovery method is suggested for the ADNs, where the impact of typhoon disasters on the output features of distributed generators (DGs) are taken into account, and meanwhile, the network structure and the output power of the DGs are jointly optimized to minimize the operating cost of the ADNs. Further, a fault component repair model is formulated by adopting the adaptive ant colony algorithm, and a multi-period restoration approach is proposed for the ADNs to fulfill a rolling optimization of the network reconfiguration and fault component repair. The improved IEEE 33-node and IEEE 118-node systems are used for the approach verification, and the results show that the proposed approach can effectively improve the overall load restoration level and increase the component repair efficiency. Following a multi-criteria resilience evaluation system, the proposed approach enables the ADNs to more effectively withstand typhoon disasters, offering a resilience increase of 6.93 % and 32.24 % regarding the 33-node and 118-node systems.

Period enhanced feature mode decomposition and its application for bearing weak fault feature extraction

Abstract Decomposition methods which can separate the fault components into different modes have been widely applied in bearing fault diagnosis. However, early fault diagnosis is always a challenge for the signal processing methods as well as the traditional decomposition methods due to the heavy noise. Therefore, how to extract the weak fault information from the complicated signal with low SNR is of significance. To overcome this issue, a period-enhanced feature mode decomposition (PEFMD) method is proposed in this paper. Firstly, the initialized filters used for the mode decomposition are adaptively designed according to the spectrum of the original vibration signal. Secondly, time synchronized averaging is used in the iterative process to excavate and identify accurately the weak period components and determine the period of the iterative signal. Finally, the period information can promote the proposed method to decompose the fault component into the hopeful modes by setting correlation kurtosis as the optimation objective and the mode selection. Relative to FMD, the proposed PEFMD achieves further improvement in extracting weak fault information. The practicability and superiority of the proposed PEFMD are verified by the simulated and experimented data. Compared with the feature mode decomposition method and variational mode decomposition, the proposed decomposition method shows an obvious performance advantage under low SNR situations.

Robust optimized weights spectrum: Enhanced interpretable fault feature extraction method by solving frequency fluctuation problem

Machine condition monitoring (MCM) plays a pivotal role in ensuring the reliability, safety, and efficiency of a production and operation system. Fault feature extraction (FFE), as an important step within MCM, aims to filter out interference components (ICs) and extract fault components (FCs) from raw signals. Consequently, it facilitates incipient fault detection and performance degradation assessment. A recently proposed optimized weights spectrum (OWS) provided a data-driven FFE methodology with a strong theoretical foundation, but it was found that the OWS is highly sensitive to a frequency fluctuation problem caused by rotational speed fluctuations and sensor errors, which may result in fake fault signatures. Therefore, a robust optimized weights spectrum (ROWS) is proposed in this paper to solve the frequency fluctuation problem. The ROWS is inspired by an intuitive idea that employs functions with adaptive frequency bandwidths instead of isolated spectral lines to represent frequency components, thus mitigating the impact of the frequency fluctuation problem. To adaptively determine the optimal parameters for these functions and estimate the corresponding ROWS, an alternative optimization strategy is adopted. Then, the proposed ROWS can be obtained when convergence conditions of this strategy are satisfied. Finally, the effectiveness and superiority of the proposed ROWS are verified by three real-world cases, i.e., the proposed ROWS can solve the frequency fluctuation problem and provide robust results for interpretable FFE.

HTG transformation: an amplitude modulation method and its application in bearing fault diagnosis

Abstract Rolling bearings are critical components in modern mechanical equipment, and the health monitoring and predictive maintenance of bearings are crucial for the normal operation of machinery. Hence, there is a compelling need to delve into advanced methodologies for enhancing the detection of fault characteristics in bearings. Faulty bearings produce periodic impulses during constant-speed rotation, which can typically be detected through envelope analysis. However, in some complex conditions, the relevant fault frequencies may be hidden within interfering components. This paper presents an amplitude modulation technique called the hyperbolic tangent Gaussian (HTG) transformation, designed to extract weak fault components from signals. Firstly, a family of amplitude modulation functions, known as the HTG functions, is constructed. These functions modulate signals with normalized amplitudes to obtain a series of modulated signals. Simultaneously, a frequency domain amplitude ratio metric is used for the automatic selection of the optimal components. Finally, the HTGgram is introduced, a spectral decomposition method based on trend components, aiming to identify the best combination of filtering and modulation components. Simulations with multi-component bearing fault signals and experimental signals with composite bearing faults demonstrate that this method not only highlights fault features and suppresses noise interference but also adaptively selects frequency bands related to faults, enhancing fault information. This approach exhibits excellent adaptability and effectiveness in complex operating conditions with multiple interference components.