Reliability Of Mechanical Systems Research Articles

Data-Driven Prediction of COF in Wet Friction Components: A Model Development and Interpretability Analysis

Abstract Predicting the coefficient of friction (COF) is essential for enhancing the efficiency and reliability of mechanical systems. Nevertheless, traditional mechanistic models relying on fixed values or fitted curves fail to accurately capture this complexity. To address this issue, this paper proposes a model for predicting the COF of wet friction components using an extreme gradient boosting (XGBoost) algorithm optimized by the sparrow search algorithm (SSA). This model effectively captures the nonlinear relationships among relative speed, pressure, temperature, and COF. As a result, the proposed SSA-XGBoost model exhibits excellent predictive performance with an RMSE of only 0.063, and 88.3% of the COF predictions have a relative error of less than 1%, significantly outperforming other deep learning algorithms. Additionally, to enhance the understanding of the COF prediction results for wet friction components, SHAP interpretability analysis is used to explore the influence of relative speed, pressure, and temperature on the predicted COF values.

Introducing Copula Functions to Estimate the Reliability of Dependent Mechanical Systems

This paper addresses the challenge of assessing the reliability of complex mechanical systems where components are inherently correlated in their failure modes. Traditionally, the assumption of independence among these components has been employed, but it often fails to capture the real-world complexities. To overcome this limitation, copula functions are introduced as a robust methodology for modeling the dependent relationships between correlated variables within mechanical systems. This paper aims to demonstrate the utility of copulas in estimating system reliability while accounting for these dependencies. The results reveal that the Clayton copula emerges as the most suitable model for representing dependence in such systems. Importantly, the reliability estimates obtained through copula-based methods not only reflect the complex interdependencies accurately but also align with the principles of the boundary theory of reliability. This research underscores the potential of copula-based reliability estimation as a valuable alternative, offering a more comprehensive and precise assessment of reliability in complex mechanical systems and holding significant promise for practical engineering applications. This framework allows the consideration of dependence among the observed variables that is usually overlooked in engineering practice.

Asymmetric-Based Residual Shrinkage Encoder Bearing Health Index Construction and Remaining Life Prediction.

Predicting the remaining useful life (RUL) of bearings is crucial for maintaining the reliability and availability of mechanical systems. Constructing health indicators (HIs) is a fundamental step in the methodology for predicting the RUL of rolling bearings. Traditional HI construction often involves determining the degradation stage of the bearing by extracting time-frequency domain features from raw data using a priori knowledge and setting artificial thresholds; this approach does not fully utilize the vibration information in the bearing data. In order to address the above problems, this paper proposes an Asymmetric Residual Shrinkage Convolutional Autoencoder (ARSCAE) model. The asymmetric structure of the ARSCAE model is characterized by the soft thresholding of signal features in the encoder part to achieve noise reduction. The decoder part consists of convolutional and pooling layers for data reconstruction. This model can directly construct HIs from the original vibration signals collected, and comparisons with other models show that it constructs better HIs from the original vibration signals. Finally, experiments on the FEMTO dataset show that the results indicate that the HIS constructed by the ARSCAE model has better lifetime prediction capability compared to other methods.

A closed-form continuous-depth neural-based hybrid difference features re-representation network for RUL prediction

Remaining Useful Life (RUL) prediction contributes to ensuring the reliability of mechanical systems and improving their maintenance plans. Recently, prediction methods based on deep learning have undergone rapid development. However, there are significant differences between multivariate monitoring sequences and utilizing a single model for feature extraction, which leads to reaching suboptimization. Additionally, focusing solely on a specific feature dimension usually imposes notable limitations on the model. This paper proposes a Closed-form Continuous-depth neural (CfC)-based hybrid difference Features Re-representation Network (CfC-F2RN) for RUL prediction. This method comprehensively utilizes hybrid difference features through two stages: initial feature representation and feature re-representation. In the initial feature representation stage, a Long Short-Term Memory (LSTM) is employed to capture the hidden state information of each time step in sequence data. Next, a novel attention mechanism is utilized to extract the hidden states and obtain a deep feature map. In the feature re-representation stage, the encoded features are re-represented using a decoder composed of the CfC model. Finally, the hidden state of the last LSTM unit in the encoder, serving as supplementary information, is combined with the decoded features to form a dual-latent feature representation of the mixed differential features. The prediction subnetwork is then adopted to accomplish RUL prediction. The superiority of CfC-F2RN is substantiated through benchmarking against established methods using the C-MAPSS dataset.

Knowledge embedding synchronous surrogate modeling for multi-objective operational reliability evaluation of complex mechanical systems

To effectively assess the multi-objective operational reliability of complex mechanical system, the concept of Knowledge Embedding Surrogate Modeling (KeSM) is proposed by integrating Knowledge-based Decomposition-Coordination (K-DC) strategy, Knowledge-based Parameter Decomposition (K-PD) strategy, and the surrogate model. In this concept, the K-DC strategy is used to decompose a complex problem into several smaller sub problems, coordinating outcomes from the bottom-up; the K-PD is applied to decompose complex parameters into two parts: associated trends and local fluctuations; the surrogate model is adopted to establish the mapping relationship between input and output. Under this concept, the Knowledge Embedding Synchronous Surrogate Modeling (S-KeSM) multi-objective operational reliability evaluation method is developed by combining linkage important sampling technique and synchronous modeling thought with KeSM concept. In addition, an engineering case (civil aircraft braking system temperature with multi-failures) is employed to validate the proposed method. Through comparison and validation with multiple methods, the results show that the proposed method has significant advantages in analysis accuracy and efficiency. This study can provide theoretical references for the multi-objective operational reliability evaluation of complex mechanical systems.

Study on the tribological behavior of TiN-VN/PAO composite lubricant system: ZIF-8 as a lubricating additive

Safety and reliability of mechanical systems are compromised by the lubricant degradation and excessive wear on contact surfaces. In response, a TiN-VN/PAO lubrication system was developed, and zeolitic imidazolate frameworks-8 (ZIF-8) nanoparticles with highly ordered pore structures were introduced to improve friction performance. The findings indicate that the addition of ZIF-8 significantly reduces the friction coefficient and wear rate in the composite system. The outstanding anti-friction performance is attributed to the heterogeneous TiN-VN nanolaminates material, which provides exceptional deformation tolerance and interface friction products. XPS analysis reveals the formation of a low shear strength Magnéli phases (V2O5) on the wear track surface, while TEM observations demonstrate that a ∼18 nm Zn-rich layer was developed at the interface, acting as a lubricating barrier layer.

A Markov method for a mechanical system reliability assessment using discrete degradation data

Abstract A homogenous continuous-time Markov model (HCTMM) has the advantage of high accuracy and is usually used in reliability analysis. However, the transition intensities (rates) between any two states cannot be accurately obtained due to the discrete data obtained from a mechanical system and little expert knowledge. This paper proposes a method in which the transition intensity matrix of an HCTMM can be obtained indirectly using the actual discrete degradation data of a mechanical system. Firstly, the one-step transition probability matrix can be calculated by a hidden Markov model using the discrete degradation data. Secondly, the unit-time transition intensity matrix can be calculated from the one-step transition probability matrix. At last, an HCTMM is established to assess the reliability of a mechanical system based on the unit-time transition intensity matrix. Moreover, considering the maintenance activities cannot restore a mechanical system as a fire-new one, the random transition of a mechanical system after maintenance is expressed by a quasi-renewal process in this paper. Finally, three cases are studied to validate the proposed method.

Digital twin-driven attention-guided convolutional networks for intelligent fault diagnosis across different domains

Fault diagnosis of rolling bearings is crucial in industries to ensure the reliability, safety, and economic feasibility of mechanical systems. Conventional data-driven methods for fault diagnosis depend on pre-existing datasets containing various failure modes for training. However, obtaining such datasets can be challenging, especially in critical industrial environments, hindering the applicability of these methods across different scenarios. To address this challenge, this research introduces a novel approach called a digital twin-driven attention-guided convolutional network (DTACN) for bearing fault diagnostics with limited data. This study offers two significant enhancements: (1) Development of an intricate digital twin model for bearings, which includes multi-scale Kinetic simulations of the bearing’s operational parameters. This model utilizes the architectural characteristics of the bearing and the severity of the failure to predict the vibratory system’s response accurately; and (2) Establishment of a domain adaptation-based framework employing deep convolutional models and attention mechanism to transfer knowledge from simulated signals to real signals. This framework facilitates efficient fault recognition even in scenarios with limited prior knowledge. The effectiveness of the proposed approach has been rigorously validated through comprehensive experiments.

Fault diagnosis of high-speed motorized spindles based on lumped parameter model and enhanced transfer learning

Condition monitoring of rotating components is crucial for ensuring the reliability and safety of mechanical systems, and artificial intelligence (AI) plays a significant role in achieving the goal. However, the high costs and complexity associated with components like high-speed motorized spindles present significant challenges in collecting complete fault samples. Therefore, we propose a new approach to tackle the challenges. The process commences with establishing a lumped parameter dynamic model for the high-speed motorized spindle. Then, the parameters such as stiffness, eccentricity, and damping in the lumped parameter model were optimized using genetic algorithm. Subsequently, simulated fault samples are acquired by introducing excitation to normal simulated signals. Finally, transfer learning techniques are utilized for intelligent fault diagnosis. The training set consists of simulated fault samples, while the testing set comprises experimental fault samples. Our approach aims to enhance the efficiency and accuracy of fault diagnosis for high-speed motorized spindles while also addressing the challenge of high cost.

ReF-DDPM: A novel DDPM-based data augmentation method for imbalanced rolling bearing fault diagnosis

Effective bearing fault diagnosis is crucial to ensure the safety and reliability of mechanical systems. Due to the complex and harsh working environment, mechanical data often comes from imbalanced datasets, which is a pressing problem in diagnosis applications. However, currently proposed data augmentation methods mainly based on generative adversarial networks, remain challenging in balancing the quality and diversity of the generation samples. To solve it, this paper proposes a new data enhancement method called the reparameterized residual denoising diffusion probability model (ReF-DDPM) and applies it to fault diagnosis. The proposed architecture includes a forward diffusion process and a reverse denoising process, where Gaussian noise and original samples are transformed by Markov chains. To improve the quality of generation samples, the noise prediction network is modified for better feature representation by enhancing intra-level and inter-level features. Furthermore, signal labels are added to the model as conditional information to direct the generation of relevant category samples during the sampling process. The study provides a new data augmentation method for bearing imbalanced data, and generation data can be further used for fault diagnosis tasks. Verification experiments demonstrate the effectiveness and good generalization of the method, and improve the accuracy of imbalance fault diagnosis.

Digital twin-driven discriminative graph learning networks for cross-domain bearing fault recognition

Rolling bearing fault diagnosis holds paramount significance in industrial field, as it is pivotal for ensuring the reliability, safety, and economic viability of mechanical systems. Most of traditional data-driven fault diagnosis methods rely on the availability of pre-collected data sets (containing various failure modes) as training data. Regrettably, such datasets may not always be easy to collect, particularly in critical industrial settings. Consequently, the applicability of data-driven fault diagnostic methods across diverse applications is impeded. In response to this challenge, this research introduces a digital twin-empowered discriminative graph learning network (DT-DGLN) for bearing fault diagnostics with unlabeled industrial data. The primary improvements of this study are twofold: (1) The creation of an elaborate and meticulous digital twin model for bearings. This model encompasses multi-scale Kinetic simulations of the operational parameters of the bearing and relies exclusively on the architectural attributes of the bearing and magnitude of the failure to deduce the vibratory system’s reaction. (2) The establishment of a domain adaption-based framework based on discriminative graph learning strategy that facilitates the transfer of known intelligence from simulated signals to real signals. This framework enables efficient fault recognition in cases where knowledge is limited. Rigorous experiments have been conducted to validate the effectiveness of the proposed approach.

Investigation of pad radius effects on multiaxial fretting fatigue behavior of al2024 alloy

Fretting fatigue, a critical phenomenon prevalent in engineering applications, occurs at the interface of contacting surfaces under cyclic loading, presenting significant challenges. The advent of Finite Element Analysis (FEA) has transformed the investigation of fretting fatigue by offering detailed insights into stress distributions and fatigue damage mechanisms. This study delves into the impact of pad radius on the fretting fatigue behavior of Al2024 alloy using FEA, with a focus on hot spot analysis and the Smith-Watson-Topper (SWT) criterion. The analysis aims to validate numerical results against analytical findings and explore the role of pad radius in determining contact behavior, fatigue life, and hot spot locations. By incorporating "fe-safe" software, computations are streamlined, facilitating efficient comparison of different fatigue initiation criteria. The results demonstrate that variations in pad radius significantly influence fretting fatigue behavior. Larger pad radii tend to distribute stresses more uniformly across the contact interface, resulting in reduced fatigue damage and longer fatigue life compared to smaller pad radii. Hot spot analysis reveals that smaller pad radii concentrate stresses at specific regions, accelerating fatigue damage initiation. The findings contribute to a deeper understanding of fretting fatigue mechanisms, shedding light on the importance of pad radius in designing more durable engineering components. Through professional scientific methodology, this study provides valuable insights into optimizing pad design to mitigate fretting fatigue and enhance the reliability of mechanical systems.

Multimodal imbalanced‐data fault diagnosis method based on a dual‐branch interactive fusion network

AbstractBearing‐fault diagnosis in rotating machinery is essential for ensuring the safety and reliability of mechanical systems. However, under complicated working conditions, the number of normal mechanical equipment samples can far exceed the number of faulty ones. When the data are so imbalanced, data fault diagnosis cannot be easily conducted using conventional deep learning methods. This study proposes a fault diagnosis method based on a dual‐branch interactive fusion network, which improves the accuracy and stability of bearing‐fault diagnosis. First, a dual‐branch feature representation network comprising an iterative attention‐feature fusion residual neural network and a long short‐term memory network is designed for extracting different modal features. Meanwhile, intermodal fusion of the extracted features is performed through multilayer perception. Based on the cost‐sensitive regularization loss, a new joint loss function is then designed for network training. Finally, the effectiveness of the proposed method is verified through comparative experiments, visualization analyses, ablation experiments, and generalization performance experiments.

Review of Vibration Analysis and Structural Optimization Research for Rotating Blades

AbstractBlades are important parts of rotating machinery such as marine gas turbines and wind turbines, which are exposed to harsh environments during mechanical operations, including centrifugal loads, aerodynamic forces, or high temperatures. These demanding working conditions considerably influence the dynamic performance of blades. Therefore, because of the challenges posed by blades in complex working environments, in-depth research and optimization are necessary to ensure that blades can operate safely and efficiently, thus guaranteeing the reliability and performance of mechanical systems. Focusing on the vibration analysis of blades in rotating machinery, this paper conducts a comprehensive literature review on the research advancements in vibration modeling and structural optimization of blades under complex operational conditions. First, the paper outlines the development of several modeling theories for rotating blades, including one-dimensional beam theory, two-dimensional plate–shell theory, and three-dimensional solid theory. Second, the research progress in the vibrational analysis of blades under aerodynamic loads, thermal environments, and crack factors is separately discussed. Finally, the developments in rotating blade structural optimization are presented from material optimization and shape optimization perspectives. The methodology and theory of analyzing and optimizing blade vibration characteristics under multifactorial operating conditions are comprehensively outlined, aiming to assist future researchers in proposing more effective and practical approaches for the vibration analysis and optimization of blades.

Cyclic Wear Reliability of 2D Monolayers.

Understanding wear, a critical factor impacting the reliability of mechanical systems, is vital for nano-, meso-, and macroscale applications. Due to the complex nature of nanoscale wear, the behavior of nanomaterials such as two-dimensional materials under cyclic wear and their surface damage mechanism is yet unexplored. In this study, we used atomic force microscopy coupled with molecular dynamic simulations to statistically examine the cyclic wear behavior of monolayer graphene, MoS2, and WSe2. We show that graphene displays exceptional durability and lasts over 3000 cycles at 85% of the applied critical normal load before failure, while MoS2 and WSe2 last only 500 cycles on average. Moreover, graphene undergoes catastrophic failure as a result of stress concentration induced by local out-of-plane deformation. In contrast, MoS2 and WSe2 exhibit intermittent failure, characterized by damage initiation at the edge of the wear track and subsequent propagation throughout the entire contact area. In addition to direct implications for MEMS and NEMS industries, this work can also enable the optimization of the use of 2D materials as lubricant additives on a macroscopic level.

ВЫБОР ПАРАМЕТРОВ ТЕХНИЧЕСКОГО СОСТОЯНИЯ ЭЛЕМЕНТОВ ПОГЛОЩАЮЩЕГО АППАРАТА, ОПРЕДЕЛЯЮЩИХ ЕГО БЕЗОТКАЗНОСТЬ

The problems to plan and ensure a given level of reliability of mechanical systems at all stages of their design and operation occupy an important place in the problem of ensuring the quality of machine-building products. With a significant number of scientific methods and approaches to solving theoretical and applied issues of reliability theory, one of the key directions is to determine the reliability indicators of technical systems and their elements, in particular a wide range of products including sliding friction pairs with periodic impacts. The study of failure origins, from the point of view of physical-mechanical processes occurring in surface layers of elements, under the influence of external factors, allows selecting parameters characterizing the functional state of the pair, and, as a result, its reliability. For example, for sliding friction pairs with periodic impacts, such a parameter is the geometric dimensions of the conjugate elements. The decrease in the geometric dimensions of conjugate elements, due to wear, characterizes the rate of change of the initial parameter values to the maximum permissible ones determining the failure, and can be approximated by linear, power, exponential and other dependencies obtained from actual measurements. According to the obtained functional dependencies of parameter changes over operating time, it makes possible to determine the norm for the parameter regulating their pre-failure state, beyond which failure prediction is possible with varying probability, and, as a result, the reliability of the system as a whole. The use of this method to reliability forecasting through the determination of the pre-failure state of the system can be projected onto technical objects, which performance indicators are geometric parameters that ensure the performance, first of all, of the functions of the elements themselves and the entire technical system, and worn out during operation.

An Integrated Multitasking Intelligent Bearing Fault Diagnosis Scheme Based on Representation Learning Under Imbalanced Sample Condition.

Accurate bearing fault diagnosis is of great significance of the safety and reliability of rotary mechanical system. In practice, the sample proportion between faulty data and healthy data in rotating mechanical system is imbalanced. Furthermore, there are commonalities between the bearing fault detection, classification, and identification tasks. Based on these observations, this article proposes a novel integrated multitasking intelligent bearing fault diagnosis scheme with the aid of representation learning under imbalanced sample condition, which realizes bearing fault detection, classification, and unknown fault identification. Specifically, in the unsupervised condition, a bearing fault detection approach based on modified denoising autoencoder (DAE) with self-attention mechanism for bottleneck layer (MDAE-SAMB) is proposed in the integrated scheme, which only uses the healthy data for training. The self-attention mechanism is introduced into the neurons in the bottleneck layer, which can assign different weights to the neurons in the bottleneck layer. Moreover, the transfer learning based on representation learning is proposed for few-shot fault classification. Only a few fault samples are used for offline training, and high-accuracy online bearing fault classification is achieved. Finally, according to the known fault data, the unknown bearing faults can be effectively identified. A bearing dataset generated by rotor dynamics experiment rig (RDER) and a public bearing dataset demonstrates the applicability of the proposed integrated fault diagnosis scheme.

Machine learning Based Bearing Fault Classification Using Higher Order Spectral Analysis

In the defense sector, where mission success often hinges on the reliability of complex mechanical systems, the health of bearings within aircraft, naval vessels, ground vehicles, missile systems, drones, and robotic platforms is paramount. Different signal processing techniques along with Higher Order Spectral Analysis (HOSA) have been used in literature for the fault diagnosis of bearings. Bispectral analysis offers a valuable means of finding higher-order statistical associations within signals, thus proving to detect the nonlinearities among Gaussian and non-Gaussian data. Their resilience to noise and capacity to unveil concealed information render them advantageous across a range of applications. Therefore, this research proposesa novel approach of utilizing the features extracted directly from the Bispectrum for classifying the bearing faults, departing from the common practice in other literature where the Bispectrum is treated as an image for fault classification. In this work vibration signalsare used to detect the bearing faults. The features from the non-redundant region and diagonal slice of the Bispectrum are used to capture the statistical and higher-order spectral characteristics of the vibration signal. A set of sixteen machine learning models, viz., Decision Trees, K-Nearest Neighbors, Naive Bayes, and Support Vector Machine, is employed to classify the bearing faults. The evaluation process involves a robust 10-fold cross-validation technique. The results reveal that the Decision Tree algorithm outperformed all others, achieving a remarkable accuracy rate of 100 %. The naive Bayes algorithm also demonstrated the least performance, with an accuracy score of 99.68 %. The results obtained from these algorithms have been compared with those achieved using Convolutional Neural Network (CNN), revealing that the training time of these algorithms is significantly shorter in comparison to CNN.

Fault diagnosis of rotating machinery using novel self-attention mechanism TCN with soft thresholding method

Rotating machinery (e.g. rolling bearings and gearboxes) is usually operated in high-risk and vulnerable environments such as time-varying loads and poor lubrication. Timely assessment of the operational status of rotating machinery is crucial to prevent damage caused by potential failure and shutdown, which significantly enhances the reliability of mechanical systems, prolongs the service life of critical components in rotating machinery, and minimizes unnecessary maintenance costs. In this regard, in this paper, a novel approach named self-attention mechanism combining time convolutional network with soft thresholding algorithm (SAM-TCN-ST) is proposed for fault intelligent recognition of rotating machinery. Specifically, the vibration signals are transformed into time-frequency graphs with distinct features utilizing the continuous wavelet transform, and then the proposed SAM-TCN-ST algorithm is employed for capturing essential data characteristics and classification performance. Eventually, datasets from rolling bearings and gearboxes are used to verify the accuracy and effectiveness of the proposed method compared with state-of-the-art benchmark networks such as pure TCN, convolutional neural networks and long short-term memory models. Experimental results demonstrate that the recognition accuracy rate of the proposed SAM-TCN-ST is higher than that obtained from the benchmark methods. This research presents an intelligent and viable solution for achieving real-time monitoring of the status and detecting faults in rotating machinery, thereby expectedly enhancing the reliability of mechanical systems. Consequently, the proposed SAM-TCN-ST algorithm holds significant potential for applications in prognostic and health management practices related to rotating machinery.

Investigation on the health evaluation of mechanical system in powertrain based on subjective and objective fusion method

The powertrain is a core component of military heavy tracked vehicles, and the accurate evaluation of its reliability and health is gradually becoming a key technology to improve our military combat effectiveness. However, the powertrain is a complex system integrating mechanical, electrical, and hydraulic components, which is difficult to achieve its accurate assessment and comprehensive characterization. Therefore, using data-driven and expert opinion fusion method to evaluate the mechanical system health is gradually becoming a research trend. This paper points out the composition of evaluation system, and puts forward how to calculate the index. Then using subjective and objective fusion method to analyze these indexes of mechanical system health and calculate the weights of each index. Based on the weights, the fuzzy comprehensive evaluation method is used to score and summarize the change law of mechanical system health. In conclusion, this study enriches the method of effectively evaluating the mechanical system health, and verifies the accuracy of this evaluation method. It will provide an evaluation basis for improving the mechanical system reliability.