Bolt Loosening Research Articles

Artificial Intelligence (AI)-Based Evaluation of Bolt Loosening Using Vibro-Acoustic Modulation (VAM) Features from a Combination of Simulation and Experiments

The detection of bolt loosening using vibro-acoustic modulation (VAM) has been increasingly investigated in the past decade. However, conventional nonlinear coefficients, derived from theoretical analysis, are usually based on the assumption of ideal wave–surface interactions at the joint interfaces. Such coefficients show a poor correlation with the tightening torque when the joint is under the combined influences of structural and material nonlinearities. A reliable inspection method of residual bolt torque is proposed in this study using support vector regression (SVR) with acoustic features from VAM. By considering the material intrinsic nonlinearity (MIN) and dissipative nonlinearity (DN), the responses of aluminum–aluminum and composite–composite bolted joints during the VAM test were accurately simulated. The SVRs were subsequently established based on the database built by combining simulated and experimental nonlinear spectral features when the joints were inspected at different scenarios. The results show that the evaluation of residual torque using the SVR models driven by the acoustic nonlinear responses had higher accuracy compared to the conventional nonlinear coefficients. Requiring limited experimental data, the proposed method can achieve a reliable inspection of bolt torque by including the simulated data in the machine training.

Bolt loosening angle detection based on binocular vision

Bolt looseness detection is critical in preventing bolt connection failure. Compared to traditional sensor-based bolt looseness detection, image-based methods are low-cost and contactless and have thus become the highlight of research. However, current monocular vision-based detection methods are prone to error scaused by the camera perspective . In this paper, we present a novel bolt loosening angle detection method based on binocular vision. Key points on the bolt are detected and matched by SuperPoint Gauss network for 3D coordinates reconstruction and motion tracking. The bolt loosening angle is solved by fitting the rotation equation using random sample consensus. Experiments verify the proposed method performs well under different perspectives of camera and illumination conditions with an average error of 1.5°. Comparative test shows our method is superior to the monocular vision-based method in terms of accuracy when there is a large perspective angle. The proposed method is mark-free and robust to various working conditions, which makes it of great value for engineering application.

A Multiplexed Fiber Bragg Grating Angle Sensor for Bolt Loosening Monitoring

Bolt joints are widely used in large-span truss and bridge structures. The integrity of bolt joint is paramount to the safety of the structure. For distributed multiple bolt joints in large-span structures, a multiplexed angle sensor based on fiber Bragg grating (FBG) for bolt loosening monitoring is proposed. Two FBGs characterized by different wavelength values are symmetrically arranged inside the specially designed sensor structure for the measurement of the bolt loosening angle in terms of their wavelength shift difference. The detail structure design of the FBG angle sensor with temperature self-compensation, automatic reset, and simple reuse is presented. The theoretical and numerical analyses are adopted to derive the measurement principle and optimize the structure of the sensor. Experimental results show that the measuring sensitivity of the FBG angle sensor prototype is about 109.6 pm/° with excellent linearity in the measuring range from 0° to 20°, and the maximum resolution of the bolt loosening angle obtained is 0.38°. The proposed sensor has stable static characteristics and can be expediently reused and developed into a quasi-distributed sensing network, which offers a new approach to real-time quantitative bolt loosening monitoring for distributed bolt joints.

The impact of initial imperfections on the fatigue assessment of tower flange connections in floating wind turbines: A review

During the massive manufactures and installations of fixed offshore wind turbines in China, initial imperfections were often found in the inspection. As more and more attentions and efforts of the wind energy sector have been devoted to deep waters with fixed and floating wind turbines (FWTs), the impact of such initial imperfections on fatigue assessment is paramount to the reliable design and safe operation, which warrant rigorous study. This paper presents a comprehensive review of three different initial imperfections and their impacts on the fatigue lifetime of FWTs’ tower flange connections. A brief introduction on FWTs and flange connections is provided at first. This is followed by a detailed discussion of the environmental loadings and fatigue assessment on the flange bolted connections. Finally, a comprehensive review of the state-of-art research on three common initial imperfections, including flatness divergence, bolt loosening and tower inclination, are presented. Their impact on fatigue assessment is further discussed.

Current and temperature-rise effect of contact condition for connection terminals in UHVDC converter stations

The heating phenomenon of connector terminals in converter stations has become increasingly common, it has become a serious safety hazared affecting the operation of UHV lines. This paper determined the overlapping model of Al plate-Al plate based on the heating phenomenon of connector terminals in converter stations, conducted the tests which included disassembly and assembly contact surface roughness impact test, pressing force impact test, operation impact test, electric composite grease impact test, anti-loosening measure impact test. Analyzed the main influencing factors of current and temperature-rise for connector terminals heating, and analyzed the influence rule of each factor for current and temperature-rise of connector terminals. Test shows that: bolt tightening torque and electric composite grease was the main influencing factors for current and temperature-rise of connector terminals, and bolt tightening moment was the first main factor, bolt looseness and the performance degradation of electric composite grease directly causes an increase in the contact resistance and temperature rise level of the connector terminals.

Theoretical and experimental investigations of vibration and damping behaviors of carbon fiber-reinforced composite thin shells with partial bolt looseness constraints

In this paper, the vibration and damping behaviors of fiber-reinforced composite thin shells under partial bolt looseness boundary conditions are investigated both theoretically and experimentally. Based on Love's shell theory, the complex modulus approach, and Hooke's law, a theoretical model of fiber-reinforced composite thin shells is constructed. A non-uniform artificial spring technique is proposed to accurately describe the non-uniform looseness in the bolt constraint positions and their interval locations, in which the two kinds of artificial springs, namely the “main spring” and “secondary spring”, are taken into account separately. After the natural characteristics, damping properties, and vibration responses are solved by the Rayleigh-Ritz method, strain energy approach, and Duhamel integral method, detailed measurements are undertaken on a CA 500 carbon/epoxy composite shell specimen to examine vibration and damping characteristics as well as to validate the proposed model. By comparing the theoretical results with the experimental ones, the maximum calculation errors of natural frequencies, resonant responses, and damping ratios are within an acceptable level. In addition, the influences of partial bolt looseness constraints on the vibration characteristics of such shell structures are also investigated here.

Dynamic Response Identification of a Triple-Single Bailey Bridge Based on Vehicle Traffic-Induced Vibration Analysis

Even though prefabricated steel Bailey bridges have been used for more than 80 years, limited studies of their structural features have been conducted, most of which do not consider their response in operational conditions. This study aimed at determining the modal parameters of a 30.48 m length Triple-Single (TS) Bailey bridge based on traffic-induced vibrations and comparing them with numerical results. Low-cost improvised accelerometers recorded and logged the actual response time histories, while a three-dimensional (3D) numerical model was developed to carry out the relevant dynamic analyses. The identification of modal parameters was based on the Operational Modal Analysis (OMA) process and the Frequency Domain Decomposition (FDD) method. Numerical analysis results are in accordance with the operational dynamic response of the Triple -Single Bailey bridge, confirming that the numerical model can effectively be used for extended dynamic analysis. In addition, the analysis of raw time histories through the OMA process indicates that the response is affected by the connections’ condition, in particular, the eventual looseness of bolts and pins. At least five eigenfrequencies were estimated and matched with relevant mode shapes.

Proof-of-concept study of bolt connection status monitoring using fiber Bragg grating curvature sensor

For connection status monitoring of bolted joint groups, a novel method with fiber Bragg grating (FBG)-based curvature sensor is proposed. An FBG curvature sensor with an inextensible elastic matrix and an offset grating is adopted and clamped between a fixed support and the monitored bolt in a plane bending status. Based on the shape deformation of the FBG curvature sensor induced by the bolt loosening, the bending curvature change of the elastic matrix is measured by the FBG. By detecting the wavelength shift of the FBG induced by the matrix curvature variation, the relationship between the bolt loosening angle and the wavelength shift of FBG can be obtained, and hence the bolt connection status can be determined by the wavelength shift of FBG. Details of the proposed method are presented, and a surface-bonded FBG curvature sensor is designed, fabricated, and experimentally studied to verify the proposed method, and the parameters on sensing performance are also investigated. Experimental results show that the proposed method can monitor bolt loosening angle with high sensitivity and linear output by adjusting the parameters of the FBG curvature sensor. The looseness angle resolution of the proposed sensor can reach 0.0767°. This paper presents the first attempt to monitor bolt loosening angle using an FBG curvature sensor. With the advantages of high sensitivity and resolution, strong applicability, convenience and reusability for the maintenance of bolts, and ease of forming quasi-distributed sensor networks, the proposed method is able to provide a general solution for the on-line monitoring of bolt connection status for large-span distributed bolted-joint groups.

Structural nonlinear damage identification based on Bayesian optimization GNAR/GARCH model and its experimental study

Cracks and bolt looseness are common damages in a steel structure. Under the time-history loading, nonlinear characteristics of variable stiffness exist in cracks, and bolt looseness has complex nonlinear characteristics of stiffness and damping. To effectively solve the problem of structural nonlinear damage identification, an output-only damage identification method based on the GNAR/GARCH (general expression for linear and nonlinear autoregressive/general autoregressive conditional heteroskedasticity) model with Bayesian optimization is proposed. First, the stationarity test and continuous difference processing was carried out on the measured acceleration data, and an order determination method based on Bayesian optimization was proposed to automatically select the optimal model order. Then, a model structure optimization method based on Bayesian optimization was proposed to select the optimal model structure of a GNAR/GARCH model, and a GNAR/GARCH model was established based on the measured acceleration data for damage identification. Finally, a new damage indicator PIDI (probabilistic Itakura distance indicator) was proposed to judge the structural healthy status. The nonlinear damage experiment of three-story frame and relay tower was used to verify the effectiveness of the proposed method. In addition, in order to illustrate the efficiency of the proposed method for nonlinear damage identification, a comparative study was carried out using other two damage identification methods. The results show that the nonlinear damage identification method based on the GNAR/GARCH model with Bayesian optimization can easily identify the nonlinear damage of the frame and relay tower structure, and it can effectively identify the structure damage with single or multiple nonlinear damage sources.

Loosening Identification of Multi-Bolt Connections Based on Wavelet Transform and ResNet-50 Convolutional Neural Network.

A high-strength bolt connection is the key component of large-scale steel structures. Bolt loosening and preload loss during operation can reduce the load-carrying capacity, safety, and durability of the structures. In order to detect loosening damage in multi-bolt connections of large-scale civil engineering structures, we proposed a multi-bolt loosening identification method based on time-frequency diagrams and a convolutional neural network (CNN) using vi-bro-acoustic modulation (VAM) signals. Continuous wavelet transform was employed to obtain the time-frequency diagrams of VAM signals as the features. Afterward, the CNN model was trained to identify the multi-bolt loosening conditions from the raw time-frequency diagrams intelligently. It helps to get rid of the dependence on traditional manual selection of simplex and ineffective damage index and to eliminate the influence of operational noise of structures on the identification accuracy. A laboratory test was carried out on bolted connection specimens with four high-strength bolts of different degrees of loosening. The effects of different excitations, CNN models, and dataset sizes were investigated. We found that the ResNet-50 CNN model taking time-frequency diagrams of the hammer excited VAM signals, as the input had better performance in identifying the loosened bolts with various degrees of loosening at different positions. The results indicate that the proposed multi-bolt loosening identification method based on VAM and ResNet-50 CNN can identify bolt loosening with a reasonable accuracy, computational efficiency, and robustness.

UAV-based pipeline inspection system with Swin Transformer for the EAST

The regular inspection of pipelines is not only a requirement to ensure the stable operation of the EAST, but also a strict safety regulation to decrease the probability of accidents caused by gas or liquid leakage. The main issues facing manual inspection are the length of the pipeline, inaccessible areas, and hazardous scenarios, which makes this task extremely difficult and time-consuming. This paper proposes a UAV inspection system for pipeline inspection missions. Loose bolts within a given pipeline are used as detection objects during experimentation to create a dataset and conduct further analysis on the accuracy of the loose-bolt detection with Swin Transformer. The results verify the effectiveness and accuracy of the UAV pipeline inspection system in terms of loose-bolt detection. The UAV inspection system proposed in this study can provide useful reference value and guidance for the regular inspection of the EAST or other pipeline inspection missions.

Deep learning recognition of bolt looseness and axial force compensation of shape memory alloy

Loosening of bolts, which is a common form of failure in bolted connections, causes relative slippage between the connected surfaces. The bolts fail under the action of external shear forces due to fatigue and breakage, thereby affecting the service performance and connection strength of the equipment, potentially resulting in major accidents. At present, condition monitoring, which is used to detect the tightness of bolt connections, has obtained acceptable results; however, most of them are still carried out under laboratory conditions and cannot be applied to engineering. In addition, effective remedial measures should be implemented after detecting bolt looseness. On the basis of such problems, a multi-bolt looseness monitoring method based on machine vision and deep learning is proposed. At the same time, shape memory alloy is used in the design of a structure that actively compensates for loose bolts. This method realises bolt recognition of the bolt connection structure through video monitoring and looseness monitoring of multi-target bolts at the same time. When the system detects that the bolts are loosened, an alarm signal is issued and, at the same time, the control device is activated to compensate, to increase the time available for repair time and to ensure the service performance of major equipment.

Acoustic Emission-based Damage Detection and Classification in Steel Frame Structure Using Wavelet Transform and Random Forest

This research proposes a unique approach for detecting damage locations and identifying damage kinds. This method is beneficial for discovering and categorizing internal structural faults that vision-based approaches cannot locate. Construction-related vibrations in a steel frame structure can be used as a source for acoustic emission. Sensor devices detect the stress waves produced by structure collapse, and spectrum analysis using wavelet transform of such data is valuable in pinpointing the location of the damage. The col-lected characteristics from these signals are input into the most effective RF (Random Forest) classifier, which are used to categories damage types like cracks and bolt loosening. When compared to previous damage localization approaches, the findings show that the proposed strategy is more efficient and has a higher classification accuracy.

The effect of tightening again on bolt loosening under transverse load: Experimental and finite element analysis

Bolt loosening is one of the most common failure modes in bolted joints. Tightening again is often used to compensate for the loss of clamping force in many critical applications. In this study, the effect of load control modes and lubrication conditions on bolt loosening were studied by experiments. Then, a series of experiments were carried out on the tightening again after bolt loosening under transverse load. Finally, in order to study the cause of fatigue fracture, FEA was carried out by using an accurate three-dimensional finite element model. The results show that the bolt loosening is mainly caused by relative motion between the two clamped plates. With oil lubrication, the bolt clamping force was able to reach the magnitude comparable to the initial preload when the nut is released to a specific angle (30° ∼ 60°) before tightening again. Nevertheless, the times of tightening again should be limited to avoid fatigue fracture of the bolt.

Electromechanical coupling modeling and motor current signature analysis of bolt loosening of industrial robot joint

Since loosening of the bolt connection reduce the stability and working accuracy of industrial robot joint, developing and applying new detection methods to provide effective and reliable diagnosis is still a challenging task. In this study, a detection method for bolt loosening of industrial robot joint based on electromechanical modeling and motor current signature analysis (MCSA) is proposed. Firstly, a dynamics model is established based on the electromechanical coupling characteristics of the robot joint servo system, and the bolt loosening factor in the model is equivalent to the variations of support stiffness. The vibration performance of the system due to bolt loosening is analyzed, and the dynamical equations show the coupling relationship between the motor current and bolt loosening. Then according to the traits of motor current variation, this study proposes to utilize the time–frequency features of the motor current to detect loosening. The energy concentrated time–frequency representation (TFR) is obtained by the synchrosqueezing transform (SST) method, and then time–frequency ridges are extracted. The features of the time–frequency ridges are adopted as indicators of the bolt loosening. The support vector machine (SVM) classifier is utilized to identify the loosening of bolts. The simulated motor current signal analysis shows that the SST can highlight the current transients caused by bolt loosening. The bolt loosening experiment is conducted on the single-degree-of-freedom servo joint test bench, and the results prove the effectiveness of the proposed method.

Temperature compensation to guided wave-based monitoring of bolt loosening using an attention-based multi-task network

Online monitoring of bolt torque is critical to ensure the safe operation of bolted structures. Guided waves have been intensively explored for bolt loosening monitoring. Nevertheless, guided waves are excessively sensitive to fluctuation of ambient temperature. As a result of the complexity of wave transmitting across a bolted joint, it is highly challenging to compensate for the effect of temperature. To this end, an attention-based multi-task network is developed towards accurate detection of bolt loosening in multi-bolt connections over a wide range of temperature variation. By integrating improved attention gate modules in a modified U-Net architecture, an attention U-Net is configured for temperature compensation. A two-layer convolutional subnetwork is connected in series behind the attention U-Net to identify bolt loosening. Experimental validation is carried out on a bolt jointed lap plate simulating a real aircraft structure. The results have proved that the developed multi-task network achieves temperature compensation and accurate bolt loosening identification. To further understand the multi-task network, the Integrated Gradients method and a simplified structure of the bolt lap plate are used to interpret the developed network. It is proved that the A0 mode is sensitive to bolt loosening, while the S0 mode is not.

A Deep Learning Model for Small-size Defective Components Detection in Power Transmission Tower

Unmanned Aerial Vehicle (UAV) inspection has gradually replaced manual inspection of transmission tower, which produces many images. While it is laborious and time-consuming to manually analyze these images, there are also challenges in automatically detecting small-size defective components such as bolts in transmission tower images, due to problems including complex background, small size, and many similar objects of bolts. In this paper, by virtue of multi-scale features and context information, we propose a deep neural network named Camp-Net (Context Information and Multi-Scale Pyramid Network) to identify bolts defect in transmission tower images. First, multi-scale feature fusion combines deep features and shallow features in convolutional networks to detect small-size bolts. Second, context information fusion puts the information around bolts into the detection network to remove the disturbance of complex background and similar objects. An image dataset containing defective bolts and normal bolts is constructed for model training and testing. Experimental results show that bolts with loose pins and bolts without pins among fittings in transmission tower can be accurately identified with the proposed model. The Average Precision (AP) of defective bolts detection of this model can be 11.4% higher than that of the commonly used high performance model, Faster R-CNN.

Railway Track Vibration Analysis and Intelligent Recognition of Fastener Defects

AbstractThe rail fastener is an indispensable component used to connect the rail and sleepers in the track structure. Real‐time recognition of the fastener defects plays a vital role in ensuring the safe and stable operation of rail transit. In this paper, an intelligent and innovative method is proposed to detect the fastener defects including the invisible defects appearing as bolt loosening and the visible defects such as the worn or completely missing fasteners by using axle‐box vibration acceleration and deep learning network. First, the dynamical relation between the fastener defects and the axle‐box vibration acceleration is investigated by using the first principle and the vehicle–track dynamical model. Then a defects recognition network is built based on the deep convolution neural network for track fasteners by using the frequency spectrum images of the axle‐box vibration. The results show that the proposed method achieves a classification accuracy of 98.27%. Finally, the track section where the fasteners are most likely to be damaged is investigated, and rail corrugation is found to be a key factor that causes fastener fatigue.

Bolt looseness monitoring based on damping measurement by using a quantitative electro-mechanical impedance method

In-situ bolt looseness monitoring is very important for the stability and safety of engineering structures. The electro-mechanical impedance (EMI) method, which had been intensively studied in structure health monitoring, has offered a feasible solution. However, in traditional EMI method, the lack of modal pre-selection leads to dense resonant peaks which brings difficulty to signal analysis. The commonly used statistical damage indices typically do not have physics meaning and may fail to distinguish the defects from the environmental changes. In this work, a quantitative EMI (Q-EMI) method was proposed to measure the damping of structures for bolt looseness monitoring. The in-plane excitation method based on distributed thickness-shear-mode piezoelectric transducers was used for selective excitation of vibration modes. The modal-related sensitivity variation was theoretically analyzed and then validated by experiments. Three different specimens were tested and the results showed that during bolt loosening, the modal damping increased by 100%–300%, while the resonance frequency of the structure only decreased by several percent. Moreover, it was found that the loosened bolt may be located using the variation of modal-related sensitivity. Due to its good performance and easy mounting, the proposed Q-EMI method is very promising for bolt looseness monitoring and is expected to be widely used in near future.

Latent fault identification method of circuit breaker operating mechanism based on acoustic signals

The information collection and fault diagnosis of the mechanical state is the basis for improving the safe and reliable operation of the high-voltage circuit breaker (HVCB). Based on the LW30-252 SF6 HVCB, the fault simulation platform is built in this paper. It simulates five typical latent faults, including gear pin wear, anchor bolt loosening, closing spring fatigue, oil buffer leakage, spindle stuck. And a fault diagnosis method based on mixed cepstral coefficient convolutional neural network (MCCCNN) is proposed. Taking the sound of the circuit breaker as the detection signal, the Mel-frequency cepstral coefficients (MFCC), Gammatone filter cepstral coefficients (GFCC) and power-normalized cepstral coefficients (PNCC) of the acoustic signal are combined into mixed cepstral coefficients (MCC), and then input into the convolutional neural network (CNN) to identify the fault. And it is verified on the measured HVCB latent fault acoustic data set. The results show that the method proposed in this paper can effectively realize the five latent mechanical fault diagnosis of HVCB.