Degradation Model Research Articles

Advanced Prognostic Models for Bearing Health: A Comparative Analysis of BiLSTM and ANFIS

Bearings play a critical role in the operation of rotary machines, serving as essential components. Their failure often leads to unexpected shutdowns, posing a significant risk to the entire system. To mitigate these risks, it is imperative to implement proactive maintenance measures and strategic planning to prevent system breakdowns. This article introduces a comparative analysis between two predictive modelling approaches: Bidirectional Long Short-Term Memory (Bi-LSTM) and Adaptive Neuro Fuzzy Inference System (ANFIS) networks, aiming to enhance bearing prognostics. The proposed methodology involves a two-step process. Firstly, data undergoes pre-processing through wavelet packet decomposition (WPD). Subsequently, a degradation model is employed for predicting the remaining useful life (RUL). To validate the accuracy of the proposed approach, extensive testing is conducted using a bearing's life dataset obtained from a run-to-failure experiment. The results demonstrate that the ANFIS model exhibits remarkable capabilities in learning and accurately estimating the system's RUL, achieving this with minimal computation time compared to alternative methods, thus presenting a more efficient and precise solution.

A random-effect Wiener process degradation model with transmuted normal distribution and ABC-Gibbs algorithm for parameter estimation

Degradation modeling is a widely used technique for evaluating the reliability of high-quality products. However, unit-to-unit variability, stemming from material fluctuations during manufacturing and environmental factors, can significantly impact the accuracy of this assessment. To tackle this issue, we propose a novel time-transformed Wiener process with a transmuted normal distribution to represent unit-to-unit variability. This distribution extends the normal distribution, offering greater flexibility by capturing a wide range of non-normal, asymmetric behaviors in unit-to-unit variability. We derive closed-form expressions for the probability density function and reliability function for the model in two scenarios: (i) assuming the degradation process observations remain unaffected by measurement errors, and (ii) assuming the degradation process observations influenced by measurement errors. Due to the complexity of the likelihood functions, we employ the Gibbs version of approximate Bayesian computation (ABC-Gibbs) for parameter estimation. The effectiveness and application of the proposed method were demonstrated through numerical examples and practical application with light-emitting diode degradation data. Moreover, we use approximate Bayesian computation model choice (ABC-MC) for model comparison studies. The results indicated that our model offers improved approximations to observed degradation results compared to existing models, showcasing its superiority in generating data under the smallest tolerance threshold.

Hierarchical control for collaborative electric vehicle charging to alleviate network congestion and enhance EV hosting in constrained distribution networks

This paper introduces a novel hierarchical architecture aimed at enhancing coordination between distribution system operators and electric vehicle aggregators in order to minimize Electric Vehicle (EV) charging costs for users while optimizing EV hosting capacity to alleviate network congestion. Real-world distribution networks are employed to evaluate EV charging strategies and their impact on medium and low-voltage networks. Two distinct EV charging optimization strategies are proposed to ensure fair power allocation among EV Aggregators (EVAs), alleviating congestion while managing EV charging power efficiently. Results demonstrate that the proposed collaborative EV charging effectively flattens the load curve, reducing peak power and avoiding grid congestion. The main findings underscore the importance of incentivizing EV flexibility to support Distribution System Operator (DSO) objectives beyond static tariffs. Furthermore, a battery degradation model is introduced into the optimization problem, reducing high currents and capacity decay. Despite capturing a higher mean electricity price, the total cost of EV charging is reduced.

Bearing degradation prediction based on deep latent variable state space model with differential transformation

Rolling bearings are a critical component of mechanical transmission equipment. Predicting their degradation trend is crucial for ensuring safe and stable equipment operation. Most existing bearing degradation prediction methods based on state space models (SSMs) use either linear functions or limited nonlinear functions (e.g., exponential/power laws) to construct the state and measurement equations. As such, these models fail to adapt to the complex and varied nonlinear degradation processes that occur in real-world environments. To address this limitation, we developed a deep latent variable-driven state space degradation model and employed it for bearing degradation prediction. Owing to the powerful nonlinear modeling ability of deep learning models, the proposed method extends the applicability of state space equations. In addition, it inherits the advantages of SSMs and can model uncertainties in a structured manner. Furthermore, the model was integrated with differential pre-transformation to improve its long-term prediction performance. Finally, to validate the effectiveness of the proposed model in predicting bearing degradation, experiments were conducted using a bearing dataset from the PRONOSTIA platform and real wind turbine bearing data. Results showed that the proposed method yielded higher bearing degradation prediction accuracy than existing methods, thus demonstrating the superior performance of the proposed model in predicting bearing degradation.

Strength degradation and damage mechanism of TA1 titanium alloy clinched joints under fatigue loading

A digital model for the strength degradation of titanium alloy clinched joints was established using strength degradation tests and a fatigue cumulative damage model. This model aims to investigate the strength degradation law and fatigue damage failure mechanism of titanium alloy clinched joints under fatigue loading. Fractured test specimens were scanned to analyse the fatigue damage failure mechanism by examining the evolution of fracture morphology under varying fatigue cyclic loading times. The results demonstrate that the power index degradation model accurately predicts the strength degradation of titanium alloy clinched joints. As the number of fatigue loading cycles increases, cleavage features emerge alongside fatigue cracks, leading to a gradual reduction in joint strength. Ultimately, the strength degradation power index model for titanium alloy clinched joints is verified by the test to have high accuracy in predicting residual strength.

Towards real world stereo image super-resolution via hybrid degradation model and discriminator for implied stereo image information

Real-world stereo image super-resolution has a significant influence on enhancing the performance of computer vision systems. Although existing methods for single-image super-resolution can be applied to enhance stereo images, these methods often introduce notable modifications to the inherent disparity, resulting in a loss in the consistency of disparity between the original and the enhanced stereo images. To overcome this limitation, this paper proposes a novel approach that integrates an implicit stereo information discriminator and a hybrid degradation model. This combination ensures effective enhancement while preserving disparity consistency. The proposed method bridges the gap between the complex degradations in real-world stereo domain and the simpler degradations in real-world single-image super-resolution domain. Our results demonstrate impressive performance on synthetic and real datasets, enhancing visual perception while maintaining disparity consistency.

Simulation of fuel cell membrane durability under vehicle operation

In this work, a statistical fuel cell chemo-mechanical membrane degradation model is developed based on the ionomer fibrillar morphology as a framework for use-level membrane durability prediction for fuel cell electric vehicles. The mechanical and chemical degradation modes are separately calibrated with pressure differential-accelerated mechanical stress tests and accelerated membrane durability tests, respectively. Finite element simulations are used to estimate the initial stress distribution across the membrane, while the genetic algorithm with the least squares method is employed to calibrate the model parameters with experimental results, thus reaching a good agreement. Next, the validated model is utilized for a case study of fuel cell electric transit bus operation in the city of Victoria, B.C., Canada. The initial cell voltage profile is obtained using a dynamic fuel cell power system model applied to the transit bus drive cycle recorded during real-world operation. According to the model predictions, reducing the stack nominal power from 396 to 132 kW results in a 148% membrane lifetime enhancement, whereas decreasing the cell temperature from 90 to 70°C results in an 11-fold increase in the membrane lifetime under simulated transit bus operation, thereby exceeding the 25,000-h lifetime target for this application.

The Influence of the Aggressive Medium upon the Degradation of Concrete Structures: Numerical Model of Research

This article discusses the impact of the aggressive environment on the pattern of pore distribution, strength, and mass absorption of investigated samples. For this purpose, a physical and numerical research model has been developed based on Fick’s second law and Zhurcov’s theory. Consequently, computer tomography research revealed that pore redistribution was revealed in test samples due to exposure. The degradation model is proposed assuming that in the first stage of interaction between concrete constructions and aggressive medium, the product of interaction is accumulated in the surface of structures and pores. Interaction products in the form of needle-shaped crystals grow in time and create additional stress in the body of the structure, resulting in partial distribution of the surface of the structure due to the growth. In this state, the excretion of dissolved substances (in the form of citrate and calcium acetate), leaching of Ca(OH)2, and decalcination of CSH lead to a decrease in the strength of cement stone. Based on the developed numerical models, the dependences of aggressive environment impact on the on the parameters of the structure of cement composites at different exposure times were obtained. For the samples obtained during the activation of Portland cement in the electromagnetic mill, energy parameters of the destruction process are 1.85–2.2 times heavier than the control compositions. The samples obtained by activating Portland cement in the electromagnetic mill have a higher susceptibility to an aggressive environment (they absorb 1.8 times more energy per unit of time for structure transformation). However, the higher U-energy barrier (1.85 times greater than the control composition) provides both a longer term of exploitation and a lower kinetics of the change in the strength of the material.

Novel Prognostic Methodology of Bootstrap Forest and Hyperbolic Tangent Boosted Neural Network for Aircraft System

Complex aviation systems’ integrity deteriorates over time due to operational factors; hence, the ability to forecast component remaining useful life (RUL) is vital to their optimal operation. Data-driven prognostic models are essential for system RUL prediction. These models benefit run-to-failure datasets the most. Thus, significant factors that could affect systematic integrity must be examined to quantify the operational component of RUL. To expand predictive approaches, the authors of this research developed a novel method for calculating the RUL of a group of aircraft engines using the N-CMAPSS dataset, which provides simulated degradation trajectories under real flight conditions. They offered bootstrap trees and hyperbolic tangent NtanH(3)Boost(20) neural networks as prognostic alternatives. The hyperbolic tangent boosted neural network uses damage propagation modelling based on earlier research and adds two accuracy levels. The suggested neural network architecture activates with the hyperbolic tangent function. This extension links the deterioration process to its operating history, improving degradation modelling. During validation, models accurately predicted observed flight cycles with 95–97% accuracy. We can use this work to combine prognostic approaches to extend the lifespan of critical aircraft systems and assist maintenance approaches in reducing operational and environmental hazards, all while maintaining normal operation. The proposed methodology yields promising results, making it suitable for adoption due to its relevance to prognostic difficulties.

A novel normalized fatigue progressive damage model for complete stress levels based on artificial neural network

The fatigue life model and fatigue stiffness degradation model are most crucial components in establishment of fatigue progressive damage model (FPDM). Based on numerous static and fatigue experiments of glass fiber reinforced polymer-matrix composites (GFRP) 3232A/Glass, a novel normalized FPDM for complete stress level based on artificial neural network (ANN) has been built: (1) By analyzing fatigue experimental data, the construction method of fatigue life model is deeply investigated. Furthermore, a normalized fatigue life model (NFLM) predicting fatigue life considering simultaneously tension–tension (T-T) fatigue and compression-compression (C–C) fatigue is developed, which has been validated by experimental data. It is expected to reduce experimental time and costs by nearly half; (2) To fully consider the influence of stress level and remove the constraint of the shape of stiffness degradation function, the traditional models are no longer suitable. Thus, a fatigue stiffness degradation model based on ANN (FSDM-ANN) has been constructed, which overcomes drawbacks of the traditional models. The results predicted by FSDM-ANN are consistent with fatigue data in different stress levels; (3) Due to distortion of the fatigue life prediction of extreme high-cycle and low-cycle, an empirical data extrapolation method is proposed here to construct a modified FSDM-ANN, which greatly improves prediction accuracy of stiffness degradation for complete stress levels.

Lifetime Prediction of Permanent Magnet Synchronous Motor in Selective Compliance Assembly Robot Arm Considering Insulation Thermal Aging.

The direct-drive selective compliance assembly robot arm (SCARA) is widely used in high-end manufacturing fields, as it omits the mechanical transmission structures and has the advantages of high positioning accuracy and fast movement speed. However, due to the intensifying dynamic coupling problem of structures in the direct-drive SCARA, the permanent magnet synchronous motors (PMSMs) located at the joints will take on nonstationary loads, which causes excessive internal temperature and reduces the lifetime of PMSMs. To address these issues, the lifetime prediction of PMSMs is studied. The kinematic and dynamic models of the SCARA are established to calculate the torque curve required by the PMSM in specific typical motion tasks. Additionally, considering thermal stress as the main factor affecting lifetime, accelerated degradation tests are conducted on insulation material. Then, the reliability function of the PMSM is formulated based on the accelerated degradation model. Based on the parameters and working conditions of the PMSM, the temperature field distribution is obtained through simulation. The maximum temperature is used as the reference temperature to conduct reliability evaluation and lifetime prediction of the PMSM. The research results show that for a typical point-to-point task, the PMSM can run for 102,623 h while achieving the reliability requirement of 0.99.

A reliability analysis method for electromagnet performance degradation based on FMEA and fuzzy inference system

AbstractElectromagnets are often used in indirect control for industrial applications. The ability of an electromagnet to control objects should decrease with performance degradation. And electromagnets product poses a danger to people and objects in the working environment. So, it is very difficult to analyze the reliability of electromagnetic performance degradation because of the complicated working condition. Failure Mode and Effect Analysis (FMEA) is the most commonly used tool for product reliability analysis. The new version of FMEA uses integer as evaluation value, which cannot represent the hesitation psychology of the evaluator. The Action Priority (AP) table of the FMEA describes the relationship between the evaluation of influencing factors and the risk level of the failure mode, which provides rules for determining the risk level of the failure mode. However, the AP table may result in multiple failure modes having the same ranking, which does not align with the intention of FMEA to prevent failures. Therefore, this paper proposes a reliability analysis method for electromagnetic performance degradation based on FMEA and FIS. Firstly, the Double Hierarchy Hesitant Fuzzy Linguistic Term Set (DHHFLTS) is used as the evaluation language to describe the hesitation psychology of evaluators. Secondly, the AP table of FMEA is used as FIS fuzzy inference rule. In this way, the idea of FMEA to determine the risk level of failure mode is retained and the problem of FIS fuzzy rule making is overcome. Then, FIS defuzzification AP table inference results to determine the risk ranking of failure modes. This avoids situations where the order of failure modes is equal. Finally, a performance degradation model of the electromagnet is constructed based on the Wiener process, and the calculation results of the new method are verified.

A hybrid residual correction method with auxiliary particle filter and conditional kernel density estimation for remaining useful life prediction

Predicting the remaining useful life (RUL) is crucial for prognosis and health management and provides an essential foundation for maintenance decisions. This study constructed a hybrid RUL prediction method based on residual correction to enhance prediction accuracy, minimize uncertainty, and mitigate errors caused by local fluctuations in the degeneration state within complex environments. This approach combined an auxiliary particle filter (APF), complementary ensemble empirical mode decomposition (CEEMD), and conditional kernel density estimation (CKDE). First, a Wiener degradation model was established, and the APF was used to acquire the initial state estimate of the equipment and residual difference between actual observations. Second, CEEMD was used to reconstruct the residual sequence and reduce interference. Subsequently, the nonparametric CKDE predicted the residual to correct the filter estimation. The corrected degeneration state value elucidated the local details of the system degradation process, and the point prediction of the RUL at the current time was obtained. The probability density distribution of the remaining life was estimated by substituting the modified degeneration state values into the kernel density estimation (KDE) model. Finally, the method was tested using an aircraft engine dataset. The results demonstrated the efficacy of the proposed method and its superiority over alternative approaches.

A method of degradation mechanism-based unsupervised remote sensing image super-resolution

Remote sensing image (RSI) super-resolution (SR) is an efficient and low-cost technique to achieve high-resolution and high-quality reconstruction images. The quality of RSI SR reconstruction is affected by the prior information contained in the degradation model. Therefore, studying how to incorporate more RSI degradation prior into the degradation model is crucial. This article presents an approach to design the degradation model by extracting degradation factors from the perspective of remote sensing imaging mechanisms. It includes two aspects: simulating the atmospheric scattering effect through RGB channel weights downsampling and the comprehensive degradation effect of the remote sensing imaging platform through combined blurring. Furthermore, we proposed a high-performance RSI SR network based on degradation mechanism (RSN-DM), which includes a degrader D and a generator G, to employ remote sensing prior fully. We conducted experiments on the UC Merced Land-Use and WPU-RESIS45 datasets, demonstrating that our proposed method is effective. Our method achieves state-of-the-art (SOTA) performance in quantitative evaluation and visual quality. Finally, we apply the proposed degradation model to other networks to further validate the model's effectiveness. Therefore, the degradation model proposed in this paper can enhance the performance of remote sensing image super-resolution techniques in practical applications.

Dynamic model of the functional parameter degradation changes in radio-electronic systems with two non-stationary random components corresponding to two types of noise

Problem statement. The processes of aging and degradation caused by the influence of environmental conditions, leading to changes in the functional parameters of radio-electronic systems, negatively affect the output characteristics and reduce the period of operation. The currently existing model of changes in radio-electronic system parameters, used for individual forecasting by extrapolation, includes only one random component representing various types of noise. At the same time, practical studies shows that the maximum amplitudes of different types of noise change at different rates. Therefore, for a more complete representation of the process of electromagnetic parameter changes over time, it is necessary to develop a model that takes into account this effect. The article discusses this problem using the example of the linear stabilizer output voltage. Goal. The main goal of the research presented in this article is to develop a model of functional parameter degradation that takes into account changes in maximum amplitudes of various types of noise in order to increase the accuracy of individual forecasting and the potential period of the device operation. Results. A generalized model of the electromagnetic parameter changes of the radio-electronic systems with two nonstationary random components characterizing various types of noise is presented. A software implementation of the presented model successfully verified on experimental data. Practical significance. The extended model of the functional parameter changes in radio-electronic systems can be used both in individual forecasting by extrapolation, and in the development of systems with a long period of operation, as well as devices intended for autonomous use. The prospects of using the presented model to simulate changes in functional parameters and determine the possibilities of compensating these changes are shown on the example of a frequency synthesizer with an automatic output power control system.

Compression and Splitting Tensile Strength Model of Recycled Seawater and Sea Sand Concrete after Seawater Freeze–Thaw Cycles

Using seawater, sea sand, and recycled bricks to make concrete for nearshore and marine engineering can save resources and protect the environment. Therefore, this article studies the mechanical degradation law and failure mechanism of recycled seawater and sea sand concrete (SSC) after seawater freeze–thaw (SFT) cycles. Using the replacement rate of recycled brick coarse aggregate as a variable, the mass loss rate, relative dynamic elastic modulus, compression and splitting tensile strength, and microstructure changes of specimens under different SFT cycles were tested, and a mechanical performance degradation model was established. The results indicate that the SFT failure of recycled brick coarse aggregate SSC results from the action of physical SFT and chemical crystallization. Friedel’s salts without cementitious properties and ettringite with expansive properties are generated inside the concrete due to the chloride and sulfate ions in the internal concrete and external seawater reacting with cement hydration products. The formation of harmful crystals leads to the loosening of the concrete, especially in the interface area between brick aggregates and cement. The calculated results of the mechanical model established in this article agree with the test results. The compression and splitting tensile strength decrease linearly with the increase in SFT cycles.

Multiscale reweighted smoothing regularization in curvelet domain for hyperspectral image denoising

ABSTRACT Hyperspectral images are easily contaminated by multi-modal noise in the process of data acquisition. Generally, hyperspectral signatures and noise appear unexpectedly scattered in the spatial-spectral domain. Conversely, in the transform domain, the principle components of an image are gathered in the low-frequency bands, while the details and noise often occur in high-frequency parts. The existing denoising methods usually divide the whole frequency domain into two parts, that is, high frequency and low frequency, which can not make the most of the knowledge contained at different frequencies or scales, especially in the multiscale transform domain. Furthermore, aiming to restore a clean image from the noise-corrupted data, hyperspectral image denoising often amounts to an ill-posed problem, in which reshaping cubic data into matrix form results in the loss of structure information. To address the aforementioned issues, this paper incorporates the reweighted smoothing regularization in the transform domain into the noise-perturbed degradation model to reformulate a novel optimization problem. First, the multiscale curvelet is leveraged to transform the spatial matrix into frequency domain, where the coefficients are carefully designed to weight the components at different scales and orientations. Second, l 1 -norm is imposed on the abundance term to promote sparsity in the transform domain for performance enhancement. Finally, using proximal alternating optimization, an efficient algorithm is well developed to obtain the closed-form solutions to the proposed denoising problem. The experimental results on several synthetic and real datasets, illustrate that the proposed method improves PSNR by at least 1.5 dB and reduces ERGAS error by more than 35% than the state-of-the-art approaches under the multi-modal noise mixed environments, which verifies the validity of regularization terms in hyperspectral images denoising.

Predicting the Remaining Useful Life of Solid Oxide Fuel Cell Systems Using Adaptive Trend Models of Health Indicators

Degradation is an inevitable companion in the operation of solid oxide fuel cell (SOFC) systems since it directly deteriorates the reliability of the system’s operation and the system’s durability. Both are seen as barriers that limit the extensive commercial use of SOFC systems. Therefore, diagnosis and prognosis are valuable tools that can contribute to raising the reliability of the system operation, efficient health management, increased durability and implementation of predictive maintenance techniques. Remaining useful life (RUL) prediction has been extensively studied in many areas like batteries and proton-exchange membrane fuel cell (PEM) systems, and a range of different approaches has been proposed. On the other hand, results available in the domain of SOFC systems are still relatively limited. Moreover, methods relying on detailed process models and models of degradation turned out to have limited applicability for in-field applications. Therefore, in this paper, we propose an effective, data-driven approach to predicting RUL where the trend of the health index is modeled by an adaptive linear model, which is updated at all times during the system operation. This allows for a closed-form solution of the probability distribution of the RUL, which is the main novelty of this paper. Such a solution requires no computational load and is as such very convenient for the application in ordinary low-cost control systems. The performance of the approach is demonstrated first on the simulated case studies and then on the data obtained from a long-term experiment on a laboratory SOFC system. From the tests conducted so far, it turns out that the quality of the RUL prediction is usually rather low at the beginning of the system operation, but then gradually improves while the system is approaching the end-of-life (EOL), making it a viable tool for prognosis.

A remaining useful life prediction framework with adaptive dynamic feedback

Remaining useful life (RUL) prediction of components is a crucial aspect of mechanical systems prognostic and health management. However, during the online RUL prediction of components, the existing method cannot use the prediction results for feedback and optimize the prediction model. To address this issue, this paper proposes a framework for RUL prediction with adaptive dynamic feedback. First, a feedback multi-feature fusion (FMFF) method is designed. It introduces a series of non-exceeding threshold positive constants, that is fraction thresholds (FT), to perform division of the degradation state dimension. Besides, the first hitting time (FHT) from the current moment to FT is the fraction remaining useful life (FRUL). It is used to construct and update the fusion factors. Then, the feedback multi-model selection (FMMS) method is proposed for adaptive feedback and to select the degradation model based on the FRUL prediction results in different stages. The probability density function of RUL based on the FHT is calculated based on the FMMS method to realize the RUL prediction of the component. Finally, the effectiveness and superiority of the proposed framework are validated based on XJTU-SY dataset and run-to-failure test.

Degradation Modeling and RUL Prediction in Dynamic Environments Using a Wiener Process With an Autoregressive Rate

Degradation Modeling and RUL Prediction in Dynamic Environments Using a Wiener Process With an Autoregressive Rate