Damage detection of structures based on wavelet analysis using improved AlexNet

Amanollah, Hessam; Asghari, Arghavan; Mashayekhi, Mohammadreza; Zahrai, Seyed Mehdi

doi:10.1016/j.istruc.2023.105019

Cited by 18 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, WSE, derived from wavelet singular values, quantifies signal complexity [26,32]. CWT is mathematically expressed as in Equation ( 2), with coefficients indicating the wavelet's scale and position represented in Equation (3) [35]:…”

Section: Time-frequency Domain Analysismentioning

confidence: 99%

See 1 more Smart Citation

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2024

Machines

View full text Add to dashboard Cite

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classification in Induction Motors (IMs), utilising the Machinery Fault Prevention Technology (MFPT) bearing dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customisation. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset’s unique characteristics. Phase 1 involves exploring load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a Wide Neural Network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in enhancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

show abstract

Section: Time-frequency Domain Analysismentioning

confidence: 99%

“…The function φ reptresents the scaled and translated versions of the mother wavelet. Different mother wavelets yield distinct wavelet coefficients, highlighting varied facets of the signal [35].…”

Section: Time-frequency Domain Analysismentioning

confidence: 99%

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2024

Machines

View full text Add to dashboard Cite

show abstract

“…Here, 𝑊𝑇 𝑓 (𝑎, 𝜏) denotes the wavelet coefficient at a specific scale, 𝑎, and position, τ. The term 𝑎 is the scaling factor that instead stretches or compresses the wavelet, while τ is the translation factor that shifts the wavelet along the signal's time axis [36]. The function 𝜑 reptresents the scaled and translated versions of the mother wavelet.…”

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

“…, acting as foundational waveforms underpinning the wavelet transform. These mother wavelets outline the fundamental shape and attributes of the wavelet that undergoes scaling and translation for signal analysis, as depicted in Equation 4, and CWT is presented in Equation 5 [36]:…”

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilizing MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2023

Preprint

View full text Add to dashboard Cite

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classifica-tion in Induction Motors (IMs), utilizing the Machinery Fault Prevention Technology (MFPT) Bearing Dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customization. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset's unique characteristics. Phase 1 involves the exploration of load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a wide neural network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in en-hancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

show abstract

A convolution neural network-based technique for health monitoring of connections of a multi-story 3D steel frame structure

Naresh,

Kumar,

Pal

2024

Multiscale and Multidiscip. Model. Exp. and Des.

View full text Add to dashboard Cite

Damage detection of structures based on wavelet analysis using improved AlexNet

Cited by 18 publications

References 39 publications

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilizing MFPT Bearing Dataset

A convolution neural network-based technique for health monitoring of connections of a multi-story 3D steel frame structure

Contact Info

Product

Resources

About