Development of low-cost non-contact structural health monitoring system for rotating machinery

Vanraj,; Singh, Robin; Dhami, S. S.; Pabla, B. S.

doi:10.1098/rsos.172430

Cited by 11 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison analysis between CEEMDAN and EEMD indicates that CEEMDAN is superior to EEMD in alleviating mode mixing problem and can generate accurate IMFs depicting dynamical properties of vibration signals. CEEMDAN has been successfully applied in audio signal processing in fault diagnosis of rotary machinery [44,45], and here it is applied to percussioncaused audio signal processing of bolt connection. Researches about CEEMDAN indicate that IMFs can reveal dynamic characteristics and underlying properties of decoupling frequency information of signal.…”

Section: The Proposed Percussion-caused Audio Signal Processing-based...mentioning

confidence: 99%

“…The analysis of vibration-induced audio signal is one of the most important ways to conduct fault diagnosis of mechanical system for non-contact and low-cost purpose. Furthermore, CEEMDAN has been applied in vibration-induced audio signal processing in the field of fault diagnosis and structural health monitoring of rotating machinery under invariable and variable operating conditions [43][44][45].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network

Yuan

Kong

2019

Smart Mater. Struct.

View full text Add to dashboard Cite

In this paper, a novel percussion-based bolt looseness monitoring approach using intrinsic multiscale entropy analysis and back propagation (BP) neural network is proposed. The percussion-caused audio signals of bolt connection are decomposed by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to obtain intrinsic mode functions (IMFs). The IMFs are in order of high-to-low instantaneous frequencies and contain underlying dynamical characteristics of audio signals. Multiscale sample entropy (MSE) is improved by smoothed coarse graining process, and the proposed improved multiscale sample entropy (IMSE) values of certain IMFs are adopted as condition indicators in bolt looseness monitoring. The intrinsic multiscale entropy analysis consisting of CEEDMAN and IMSE extracts underlying dynamical characteristics during percussion-caused audio signal processing to identify bolt looseness conditions. The condition indicators, namely IMSE values at smallest scale factors, are employed as input of BP neural network for training and testing, to achieve accurate and stable bolt looseness condition monitoring. The effectiveness and superiority of the proposed approach have been validated by theoretical derivation and practical experimental researches, and the adaptivity and robustness of the proposed approach are also illustrated. The results of the research in this paper demonstrate the proposed approach is promising in practical applications of bolt looseness monitoring.

show abstract

Section: The Proposed Percussion-caused Audio Signal Processing-based...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network

Yuan

Kong

2019

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…A total number of 18 statistical features are extracted from the raw signals and TMI graphs, as listed in Table 1. These time‐domain features are commonly applied in vibration monitoring methods for SHM 21‐24 …”

Section: Methodsmentioning

confidence: 99%

Wind turbine event detection by support vector machine

Albertani

2021

Wind Energy

View full text Add to dashboard Cite

Considering the increase in the deployment of wind energy conversion systems, improving the coexistence between wind turbines and wildlife with an efficient method for blade impact assessment is of primary importance. Automated blade‐impacts on potential wildlife monitoring can support the development and operations of wind farms. A substantial challenge is represented by the typical case of impacts vibrations signature embedded in the operational vibrations of the wind turbine. A heterogeneous multisensor system for automatic eagle detection and deterrent, including an automatic blade‐event detection module, was developed providing the necessary field data. An automated blade event detection system, based on support vector machine, a form of machine learning, was developed and tested. Training of the algorithm was performed using features extracted from vibration signals and energy distribution graphs obtained from numerical simulations of blade impacts. Performance of the method, evaluated using numerical simulations at different levels of signal‐to‐noise ratios, relative to artificial impacts, showed the best results when trained using combined raw vibration signal and time marginal integration graphs, exhibiting an overall accuracy of 93% at SNR=6. The proposed model was tailored for improving specificity (i.e., false negative error), a critical aspect for endangered species events. Performance of the trained algorithm evaluating field data exhibited an improvement in impact detection from a visually identifiable rate of 42% to true positive prediction rate of 75%. The system could perform, with appropriate training, diverse functions as components health monitoring or lighting strike automatic monitoring.

show abstract

“…Once again, the authors point out that natural frequencies and modal parameters, in general, are not very sensitive to structural damages, but the changes in mode shape curvature can nevertheless provide valuable insight to determine the cause of a defect. Other examples for the monitoring of vibrational behaviour are given by Burdzik et al [8], who considered vibroacoustic methods for SHM in manufacturing processes or Varanj et al [9], who introduced a noncontact data acquisition system for condition monitoring of gearboxes in rotating machinery.…”

Section: Introductionmentioning

confidence: 99%

Operational Modal Analysis of an Axial Compressor Rotor and Casing System for the Online Identification of a Digital Twin

2022

View full text Add to dashboard Cite

Modal parameter identification can be a valuable tool in mechanical engineering to predict vibrational behaviour and avoid machine damage during operation. Operational modal analysis is an output-only identification tool motivated by the structural identification of civil engineering structures, which are excited by ambient conditions. This technique is increasingly applied in mechanical engineering in order to characterise the system behaviour during operation as modal parameters can vary under operating conditions. The following study investigates the application of operational modal analysis on an axial compressor under operating conditions. Since the modal parameters of the system change depending on the life history and during the operation of the system, a corresponding data analysis might allow us to identify the present status of the system. Eigenfrequencies and eigenvectors are studied for the use of structural health monitoring approaches. According to the analysis, eigenfrequencies represent robust parameters for the studied purpose. Eigenvectors are sensitive to damages but need further investigation, especially for rotating machinery. This study will help the user to set up a virtual model, which describes the system behaviour for different boundary conditions. This in turn, will provide an accurate prediction of the vibrational behaviour in order to assure a safe operation.

show abstract

Development of low-cost non-contact structural health monitoring system for rotating machinery

Cited by 11 publications

References 32 publications

Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network

Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network

Wind turbine event detection by support vector machine

Operational Modal Analysis of an Axial Compressor Rotor and Casing System for the Online Identification of a Digital Twin

Contact Info

Product

Resources

About