Bolt Loosening Research Articles

Simulation data-driven attention fusion network with multi-similarity metric: A single-domain generalization diagnostic method for tie rod bolt loosening of a rod-fastening rotor system

The rod-fastening rotor system is the core rotating component of gas turbines and aero engines. The rod-disk joint structure of the rod-fastening rotor system is subjected to tie rod bolt loosening under complex operating conditions. Because of the uncertainty of fault occurrence, the model must possess diagnostic capability under unseen working conditions. Domain generalization methods are commonly employed to address such problems. They typically utilize multi-condition data or generate data from a single condition to train the model, enabling it to generalize to unknown operating conditions. However, difficulties in collecting complete multi-condition data and limitations in generating data, such as conflicting attributes and limited categories, make it challenging to ensure high-quality data for model training. To address these issues, this paper establishes a dynamic model of the rod-fastening rotor system to obtain high-fidelity simulation fault data, ensuring the physical accuracy, richness, and diversity of the source domain data. Meanwhile, a novel signal-domain generalization method called simulation data-driven attention fusion network with multi-similarity metric is proposed for tie rod bolt loosening in the rod-fastening rotor system. The attention feature fusion strategy is utilized to achieve the comprehensive representation of local and global features efficiently. Moreover, a multi-similarity loss based on deep metric learning is introduced to comprehensively consider the self-similarity and relative similarities between features, enabling class-level optimization of features. The proposed method is validated to have superior diagnostic performance in two cross-domain tasks compared with other methods. The proposed method can provide valuable insights into fault diagnosis in the rod-fastening rotor system.

Early Bolt Loosening Detection Method Based on Digital Image Correlation.

Bolt loosening can significantly impact the accuracy, stability, and safety of equipment. The detection of bolt loosening in a timely manner is crucial for ensuring the safety, reliability, performance, and service life of equipment, structures, and systems. Various methods exist for detecting bolt loosening, such as strain gauges and ultrasonic waves. However, these technologies have some limitations that impede their widespread application. In this paper, for the high-pressure pipe manifolds that may experience leakage accidents due to the loosening of bolts, an early bolt loosening detection method based on digital image correlation is proposed. Initially, a model is established through tensile tests to relate the average strain on the side of the bolt head to the axial force. Subsequently, an industrial camera captures images of bolts with random speckles under operational conditions. Using digital image correlation technology, the average strain in a specific region on the side of the bolt head is calculated. By integrating the average strain into the established relationship model between the average strain and axial force, the axial force of the bolt under operational conditions can be predicted, enabling the early assessment of bolt loosening. The findings show that the average strain on the side of the bolt head increases proportionally with the axial force, indicating a strong linear relationship. This method enables accurate prediction of the bolt's axial force, offering a new approach for identifying the early loosening of bolts in high-pressure manifolds and monitoring structural health.

Bolt looseness detection in lap joint based on phase change of Lamb waves

Bolts are widely applied to lap joints in many industrial fields. Due to harsh environment and low quality of operation, bolt looseness may appear during service. For lack of an understanding of the Lamb wave propagation process across bolted joints, most of the existing methods exploit some basic characteristics such as the transmitted energy as the looseness index, which is insensitive to bolt looseness at the early stage. To take full advantage of the information in the Lamb wave propagation and improve the detection performance, this study proposes a method for bolt looseness detection based on the phase change of Lamb waves during the propagation process. Firstly, the contact status is investigated based on the distribution of contact press, and the change of contact area along with bolt torque is analyzed. Subsequently, the propagation process of Lamb waves across bolted joints is revealed, based on which the monotonic relationship between the phase delay of Lamb waves and the extent of bolt looseness is derived. Thus, a looseness index based on phase change can be established to detect bolt looseness. Finally, the experiment is carried out in a bolted joint composed of two aluminum plates. The phase change in received signals conforms to the analyzed propagation mechanism of Lamb waves in bolted joints and verifies the effectiveness of the established bolt looseness index. Compared to the traditional methods based on the transmitted energy of Lamb waves, the proposed method is more sensitive to the change of bolt torque, especially at the early stage of bolt looseness.

Bolt looseness localization with connection-stiffness-varying flange

Electromechanical impedance analysis is a traditional method to identify the occurrence of bolt looseness, but accurate localization of blot looseness is hard to realize on the flange. In this study, a flange model with bolt connection stiffness varying with position is proposed. The location of bolt looseness can be then determined from the impedance spectrum of the model since the uniformity and symmetry of the flange are broken. The analytic model is established to reveal the distinguishability of the eigenfrequency shifting characteristics when the connection stiffness at different positions changes. The frequency shifting sequence is extracted from the coupling impedance spectrum as a feature, and the correlation between the sequences corresponding to bolt looseness at different positions is low. The relationship between the sequence and the degree of looseness is highly related so that the unknown degree of looseness can be matched with the calibrated sequence to realize the localization of the looseness. Based on the distinguishability of the frequency shifting sequence, the connection-stiffness-varying model shows great potential in the field of flanges or other connecting structures for structural health monitoring and damage localization.

Identification of Bolt Loosening Damage of Steel Truss Structure Based on MFCC-WPES and Optimized Random Forest

In the field of bolt loosening detection, although some progress has been made, there are still challenges such as high operational complexity, single feature extraction methods, and insufficient analysis model performance, especially in large steel truss structures, where there is a lack of efficient and accurate bolt loosening identification solutions. In response to these shortcomings, this article proposes an innovative bolt loosening damage recognition method based on sound signals. This method integrates feature extraction techniques of Mel frequency cepstral coefficients (MFCCs) and wavelet packet energy spectra (WPES), and comprehensively characterizes sound signals by constructing MFCC-WPES combined features. Subsequently, the random forest (RF) algorithm optimized by genetic algorithm was used for feature selection and model training, aiming to improve recognition accuracy and robustness. The experimental results show that this method can not only accurately identify bolt loosening signals in steel truss structure bolt loosening detection, but also has strong identification ability for environmental noise. Compared with traditional methods, the proposed solution in this article shows significant improvements in both performance and practicality, providing a new perspective and solution for the technological advancement of bolt loosening detection in steel truss structures.

Addressing data scarcity using audio signal augmentation and deep learning for bolt looseness prediction

Deep learning models such as convolutional neural networks (CNNs) encounter challenges, including instability and overfitting, while predicting bolt looseness in data-scarce scenarios. In this study, we proposed a novel audio signal augmentation approach to classify bolt looseness in the event of data deficiency using CNN models. Audio signals at varied bolt torque conditions were extracted using the percussion method. Audio signal augmentation was performed using signal shifting and scaling strategies after segmenting the extracted audio signals. The unaugmented and augmented audio signals were transformed into scalograms using the continuous wavelet transform approach to train the CNN models. Upon training with augmented datasets, a promising improvement in the loss and accuracy of the CNN models in recognizing bolt looseness was noticed. One of the significant observations from the current study is that the implementation of audio signal augmentation improved the extrinsic generalization ability of the CNN models to classify bolt looseness. A maximum increase of 73.5% to identify bolt looseness in novel data was exhibited as compared to without augmentation. Overall, a maximum accuracy of 94.5% to classify bolt looseness in unseen data was demonstrated upon audio signal augmentation. In summary, the results affirm that the audio signal augmentation approach empowered the CNN models to predict bolt looseness in data-deficient scenarios accurately.

Guided wave based SHM for loosening detection in bolted lap joints with the application of Neural Networks

Bolted and riveted connections are a mainstay in many aerospace, mechanical, and civil engineering applications. Early detection of bolt loosening is essential for ensuring structural integrity and preventing catastrophic failures. Guided wave-based structural health monitoring (SHM) systems are well-suited for damage detection in plate-like structures. The present study aims at an experimental investigation of Lamb wave propagation in an aluminum lap joint with two bolts using piezoelectric transducers and compares the effectiveness of different damage indices based on wave energy transmission between plates in looseness detection. Torque values ranging from 5 Nm to 12 Nm at 1 Nm intervals are applied, along with a hand-tightened condition as well as free plates without bolts. Torquing conditions are evaluated for both bolted joints individually as well as simultaneously. The experiment is currently in progress, and the preliminary results are being examined. Further to this, the experimental findings will be compared with the finite element (FE) modelling results. Relatively few studies have explored the use of deep learning algorithms to enhance the performance of guided wave-based SHM systems for bolt loosening detection. The central goal of this study is to develop a neural network architecture for a Lamb wave propagation-based SHM system for bolted connections. This network will be trained using damage indices from the FE modelling results and later validated with the experimental data.

Bolt looseness monitoring using dynamic mode decomposition with piezoelectric active sensing

Bolt joints are widely used in multiple industries due to its ease of operation and low-cost. Under the influence of multiple external factors, bolt joint will loosen, which poses risks to structural safety. In this paper, a bolt loosening monitoring approach is proposed based on piezoelectric active sensing and dynamic mode decomposition (DMD). To the best of the author’s knowledge, this research represents the first attempt to detect bolt looseness using DMD method. A high-frequency dynamic response signal of the bolt joint is obtained based on piezoelectric active sensing. DMD is used to decompose the high-frequency dynamic response signal into a series of dynamic mode components. The bolt looseness mainly affects the localized high-frequency and high-order dynamic characteristics of the bolted structure. This paper innovatively proposes that the high frequency component signal constructed by the higher order dynamic component more directly reflect the localized dynamic characteristics of the bolted joint. Then, the signal energy of the constructed high frequency component signal is developed into a health index (HI) to characterize the bolt loosening degree. The experiments were conducted to verify the effectiveness of the proposed method. The experiment results shows that the proposed HI monotonically increases as the tightening of the bolt over the whole range of bolt-preload. Furthermore, the research incorporates different sensor mounting positions and loosening of bolts with various diameters, demonstrating the applicability of the proposed method. The proposed method is significant in detecting loosening of bolt joints, especially in bolt early loosening, and enhances the performance of the piezoelectric active sensing method.

An oversampling method based on Gaussian Mixture Model for multi-bolt looseness monitoring using Lamb waves`

The imbalance in the number of healthy and faulty samples poses a significant hindrance to the successful implementation of multi-bolt looseness monitoring and fault classification in engineering applications. The Synthetic Minority Oversampling Technique (SMOTE) is widely used in addressing data imbalance issues. However, traditional SMOTE methods and their improvements have not taken into account the problem of sensor network signals with multiple paths. In this paper, an improved oversampling technique, namely Gaussian Mixture Model (GMM)-SMOTE, is introduced. The proposed SMOTE method is based on GMM and aims to solve the sample imbalance problem under different bolt states and different sensor paths in sensor networks. The GMM is utilized to cluster the minority classes in multi-bolt looseness data. The assignment of weights to different clusters is based on the clustering density function, which is subsequently followed by oversampling. The KL distance is utilized to screen the SMOTE sample data, which improves the quality of the data by achieving inter-class balance and intra-class balance. To verify the effectiveness of the method, a multi-bolt looseness monitoring procedure is implemented. The experimental results demonstrate that the proposed method can improve the accuracy of diagnosing early-stage bolt looseness.

Experimental and numerical study on the effect of load direction on the bolt loosening failure

The loosening is one of the main failure modes of bolted joints. Currently, researchers only focused on bolt loosening behavior under simple axial or transverse loads. Understanding the loosening failure mechanism of bolted joints under complex load is important for improving reliability. A multi-directional loading test device was designed, and bolt loosening experiments were conducted. The effect of load direction and amplitude on bolt loosening behavior were investigated. The results indicate that bolt loosening can be divided into two stages. Load direction and load amplitude are critical factors determining the loosening trend in the later stage. In addition, a refined finite element model of bolted joints was established to verify and explain the experimental results. The FEA results show that the relative sliding between internal and external threads and the stress redistribution on the threads are the main reasons for the bolt loosening. The smaller the angle between the load direction and the tangential direction of the contact surface, the relative sliding more likely to occur.

Load-equivalent model and loosening life prediction method of bolts under transverse loading

To establish a method for predicting the loosening life of bolts under random transverse vibration, this study first obtains the transverse displacement–loosening life (D–NL) curves of bolts under three loosening states (90 %, 80 %, and 70 % of the residual preload) through bolt-loosening tests under different transverse displacement loads. Based on the mechanical analysis model of bolt loosening with strict physical definitions, load-equivalent models of the bolt external load, screw load, and screw-tooth root stress are established by considering the transverse displacement load as the input excitation and the screw-tooth root stress as the output response; these achieve the transfer and conversion of the bolt external load and screw root stress with the screw load as the bridge. Subsequently, two types of finite element models of bolted connections are established and verification tests are performed. The equivalent relationships between the bolt external load, screw load, and screw-tooth root stress are simulated and tested, and the accuracies of the bolt-load equivalent models are verified. Finally, based on the bolt-load equivalent models, the D–NL curves for evaluating loosening using the directional macroscopic displacement load are converted to stress–loosening life (S–NL) curves to evaluate loosening using the undirected local stress. A calculation flow of the bolt-loosening life under random transverse vibrations is established, and a method of predicting bolt-loosening life based on the bolt-load equivalent relationship is developed. These findings provide a useful reference for optimizing bolted connection designs and preventing bolt loosening.

Analysis of Bolt Loosening due to Transvers Vibration

Bolt loosening is a critical issue in engineering applications where vibration-induced failures pose significant risks to the structural integrity and functionality of mechanical systems. This project aims to investigate the phenomenon of bolt loosening resulting from the transfer of vibrations and develop effective strategies to mitigate this problem. The study employs a comprehensive approach, combining experimental analysis, numerical simulations, and theoretical modeling to gain insights into the underlying mechanisms of bolt loosening. Furthermore, a theoretical model is developed to predict the susceptibility of different bolted joints to loosening based on factors such as material properties, bolt size, and tightening torque. The model is validated using experimental data, ensuring its accuracy and reliability in practical applications.

Prediction of Pre-Loading Relaxation of Bolt Structure of Complex Equipment under Tangential Cyclic Load.

Bolts have the advantages of simple installation and easy removal. They are widely applied in aerospace and high-speed railway traffic. However, the loosening of bolts under mixed loads can lead to nonlinear decreases in pre-loading. This affects the safety performance of the structure and may lead to catastrophic consequences. Existing techniques cannot be used to monitor the bolt performance status in time. This has caused significant problems with the safety and reliability of equipment. In order to study the relaxation law of bolt pre-loading, this paper carries out an experimental analysis for 8.8-grade hexagonal bolts and calibrates the torque coefficient. We also studied different loading waveforms, nickel steel plate surface roughnesses, tangential displacement frequencies, four different strengths and bolt head contact areas of the bolt, the initial pre-loading, and the effects of tangential cyclic displacement on pre-loading relaxation. This was done in order to accurately predict the degree of bolt pre-loading loosening under external loads. The laws are described using the allometric model function and the nine-stage polynomial function. The least squares method is used to identify the parameters in the function. The results show that bolts with a smooth surface of the connected structure nickel steel flat plate, high-frequency working conditions, half-sine wave, and a high-strength have better anti-loosening properties. Taking 5-10 cycles of cyclic loading as a boundary, the pre-loading relaxation is divided into two stages. The first stage is a stage of rapid decrease in bolt pre-loading, and the second stage is the slow decrease process. The performance prediction study shows that the allometric model function is the worst fitted, at 71.7% for the small displacement condition. Other than that, the allometric model function and the nine-stage polynomial function can predict more than 85.5% and 90.4%, which require the use of least squares to identify two and ten unknown parameters, respectively. The complexity of the two is different, but both can by better indicators than the pre-loading relaxation law under specific conditions. It helps to improve the monitoring of bolt loosening and the system use cycle, and it can provide theoretical support for complex equipment working for a long time.

A Vision-Based Bolt Looseness Detection Method for a Multi-Bolt Connection

Many vision-based bolt looseness detection methods that directly observe the bolts have been developed. However, these methods have many limitations in terms of the conditions and processes of their implementation. To address these problems, this paper proposed a fully automated vision-based bolt looseness detection method for a rigid multi-bolt connection. The proposed method combines digital shearing speckle pattern interferometry (DSSPI) and recurrent neural network (RNN) and involves capturing speckle fringe patterns under various looseness cases using the DSSPI system and classifying these patterns with an RNN model to detect the loose bolts. The proposed method can detect all the bolts within the measured surface at one time, which is efficient. On the other hand, it eliminates the need for prior information such as the initial angle and position of each bolt. It can even detect unseen bolts in multi-bolt connections, making it applicable for connections in complex structures in which occlusion often occurs. Additionally, the method eliminates the complex process of distortion rectification. These features make the method achieve a single-judgment time (four bolts at one detection) of only 4.70 millisecond with a detection accuracy over 99%, which has potential for the real-time detection of loose bolts in multi-bolt connections.

A novel anti-loosening bolt looseness diagnosis of bolt connections using a vision-based technique

Bolt looseness detection is a common problem in engineering. Most vision-based detection techniques focus on diagnosing ordinary bolt looseness, i.e., the methods used for diagnosis are based only on the sidelines of nuts. These methods cannot be used for anti-loosening bolt looseness diagnosis because of the simultaneous rotation of screws and nuts. Therefore, a novel anti-loosening bolt looseness diagnosis method based on a vision-based technique is proposed in this paper. First, a regular hexagonal cap was installed on the screw, which can be used as a reference for the nut. Then, to automatically distinguish the hexagonal borders of the screw cap and nut, a new hexagonal border reconstruction algorithm is proposed. Furthermore, the relative rotation angles of the screw cap and nut hexagons can be determined using the sidelines of the reconstructed hexagonal borders of the screw cap and nut. Finally, a novel anti-loosening bolt looseness diagnosis method is established by using the relative rotation angle of the regular hexagonal borders of the screw cap and nut under initial status and loose status. A prototype flange node of the transmission tower was used for experimental verification. The results show that the proposed method can effectively detect the loosening angle of anti-loosening bolts.

Bolt load looseness detection for slip-critical blind bolt based on wavelet analysis and deep learning

Bolt preload is a crucial factor in high-strength bolt applications, particularly for the Slip-critical blind bolts (SCBBs). This study presents a novel nondestructive approach that leverages ultrasonic echo waves to accurately detect the state of bolt looseness, addressing a significant research gap in the field of blind bolt looseness detection. The proposed technique is uniquely suitable for blind bolted connections as it only necessitates access to a single side of the connection. Nine types of SCBBs were tested and obtained approximately 4000 ultrasonic echo signals with varying degrees of looseness. These signals have been transformed into image-based representations using wavelet analysis, and deep learning techniques were used to classify and predict the looseness level accurately. The performance of various damage assessment criteria, CNN models, and dataset sizes were evaluated and compared. The proposed method was validated by classifying 400 datasets with a validated accuracy of 97.30%.

Adaptive stochastic resonance under Poisson white noise background and its application for bolt looseness detection

Adaptive stochastic resonance under Poisson white noise background and its application for bolt looseness detection

Bolt loosening monitoring with passive wireless-based smart washers

Ensuring sufficient preload of bolted connections is crucial for maintaining the safety of railway operations. Accidents resulting from loose bolts caused by inadequate preload are a recurring concern. Traditional bolt preload detection methods suffer from reliability issues and bulky equipment requirements. To address these challenges, this study proposes a novel solution utilising passive wireless measurement systems. However, the communication effectiveness of these systems can be significantly impacted by the surrounding metal environment. This research introduces an intelligent clover washer design to mitigate the adverse effects of eddy currents induced by the metal environment. The design incorporates a new clover antenna and washer structure, effectively reducing the influence of the metal environment and improving the communication quality. The proposed design has undergone comprehensive prototyping, simulation and experimental verification. The results demonstrate a significant improvement over the traditional circular antenna and washer combination under similar conditions. Specifically, the sensing distance of the new clover washer is enhanced by 60% and the stable communication distance is improved by 75%. The experimental results highlight the ability of the new clover smart washer to generate a stronger spatial magnetic field and exhibit reduced susceptibility to the metal washer, thereby enhancing communication effectiveness.

Bolt loosening angle detection through arrangement shape-independent perspective transformation and corner point extraction based on semantic segmentation results

The identification of loosened bolts is crucial for the early warning of structural damage and maintaining the overall stability of the structure. Most existing two-dimensional computer vision-based bolt loosening detection methods need to rely on the bolt arrangement shape for perspective transformation, to overcome this limitation, this study proposes a bolt loosening angle detection method through arrangement shape-independent perspective transformation and corner point extraction based on semantic segmentation results. First, a dataset of 1748 images containing bolts is collected. Second, a bolt region of interest (RoI) detection is developed to extract the sub-image of the bolt. The results show that the training and validation accuracy of bolt RoI detector are 99.5%, and 99.4%, respectively. Then, the contour corner points are extracted, the automatic and arrangement shape-independent perspective transformation of the image is completed using the planar homography-based image processing algorithm and the regular hexagonal characteristics of the bolt. Finally, automatic estimation of the bolt angle is performed on the corrected bolt image. The proposed method is used to detect bolt images obtained from different shooting distances, perspective angles, and lighting conditions. The results demonstrate that the method can accurately detect the looseness of bolts in bolt connections, and the quantification error is mostly less than 3°, it has the potential for real-time bolt loosening monitoring of multi-type bolted connections.

Multi-bolt looseness positioning using multivariate recurrence analytic active sensing method and MHAMCNN model

The piezoelectric active sensing method has been proven to be an effective, nondestructive approach for bolt looseness monitoring. The conventional damage index relies on the energy index of the wavelet packet. However, the method of wavelet packet could not identify the looseness location of the multi-bolt. Therefore, an innovative multi-bolt intelligent method combined the multivariate recurrence analytic active sensing method with an improved convolutional neural network (CNN) model was proposed for multi-bolt looseness positioning. In this method, the multivariate recurrence plots (RPs) are firstly constructed based on the received stress waves and then it is utilized to extract the recursive attributes presented within the stress wave signals. Secondly, a novel model, the CNN improved by the multi-head attention mechanism (MHAMCNN), is constructed to extract nonlinear features hidden in multivariate RPs. Repeated experiments demonstrate that the proposed method, which combines MHAMCNN and un-thresholded multivariate RPs (i.e., mean detection accuracy: 98.62%), outperformed other methods, including multivariate RPs (i.e., mean detection accuracy: 97.06%) and common RPs. Compared with traditional pattern recognition algorithms, MHAMCNN has higher classification accuracy. In summary, the suggested approach presents a promising opportunity for the real-time monitoring of multi-bolt looseness.