Acoustic Emission Monitoring for Film Thickness of Mechanical Seals Based on Feature Dimension Reduction and Cascaded Decision

Zhang, Zhi; Li, Xiaohui

doi:10.1109/icmtma.2014.201

Cited by 8 publications

(3 citation statements)

References 13 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contact seals frequently affect the friction behavior in the whole drive train, and they are exposed to wear. Increasing requirements demand more precise descriptions of the tribological behavior of contact seals in design phases as well as condition monitoring [80,81]. Logozzo and Valigi [82] suggested ANNs as an alternative for analytical models to predict friction instabilities and critical angular speeds of face seals during shaft decelerations.…”

Section: Sealsmentioning

confidence: 99%

Current Trends and Applications of Machine Learning in Tribology—A Review

2021

View full text Add to dashboard Cite

Machine learning (ML) and artificial intelligence (AI) are rising stars in many scientific disciplines and industries, and high hopes are being pinned upon them. Likewise, ML and AI approaches have also found their way into tribology, where they can support sorting through the complexity of patterns and identifying trends within the multiple interacting features and processes. Published research extends across many fields of tribology from composite materials and drive technology to manufacturing, surface engineering, and lubricants. Accordingly, the intended usages and numerical algorithms are manifold, ranging from artificial neural networks (ANN), decision trees over random forest and rule-based learners to support vector machines. Therefore, this review is aimed to introduce and discuss the current trends and applications of ML and AI in tribology. Thus, researchers and R&D engineers shall be inspired and supported in the identification and selection of suitable and promising ML approaches and strategies.

show abstract

Section: Sealsmentioning

confidence: 99%

Current Trends and Applications of Machine Learning in Tribology—A Review

2021

View full text Add to dashboard Cite

show abstract

“…Mitigating undesired face contact requires seal redesign and real-time condition monitoring to detect the onset of face contact. Most previous studies focus on detecting contact experimentally using methods such as vibration monitoring [15,16,18], ultrasonic techniques [19][20][21], acoustic emission [22,23] or a combination of methods [24]. Others have used these same experimental measurement techniques to heuristically identify contact signatures and apply these signatures to an activelycontrolled seal in an attempt to eliminate contact [25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Impact Phenomena in a Noncontacting Mechanical Face Seal

Varney

Green

2016

Journal of Tribology

View full text Add to dashboard Cite

Noncontacting mechanical face seals are often described as unpredictable machine elements, gaining this moniker from numerous instances of premature and unexpected failure. Machine faults such as misalignment or imbalance exacerbate seal vibration, leading to undesirable and unforeseen contact between the seal faces. A hypothesis explaining the high probability of failure in noncontacting mechanical face seals is this undesired seal face contact. However, research supporting this hypothesis is heuristic and experiential and lacks the rigor provided by robust simulation incorporating contact into the seal dynamics. Here, recent developments in modeling rotor–stator rub using rough surface contact are employed to simulate impact phenomena in a flexibly mounted stator (FMS) mechanical face seal designed to operate in a noncontacting regime. Specifically, the elastoplastic Jackson–Green rough surface contact model is used to quantify the contact forces using real and measurable surface and material parameters. This method also ensures that the seal face clearance remains positive, thus allowing one to calculate fluid-film forces. The seal equations of motion are simulated to indicate several modes of contacting operation, where contact is identified using waveforms, frequency spectra, and contact force calculations. Interestingly, and for the first time, certain parameters generating contact are shown to induce aperiodic mechanical face seal vibration, which is a useful machine vibration monitoring symptom. Also for the first time, this work analytically shows a mechanism where severe contact precipitates seal failure, which was previously known only through intuition and/or experience. The utility of seal face contact diagnostics is discussed along with directions for future work.

show abstract

“…A few studies have attempted to apply machine learning to the AE signals generated from mechanical seals. Zhang and Li 10 developed artificial neural networks (ANNs) which distinguished between the intervals wherein the seal face separation lies using AE signals decomposed with wavelet transform. Li et al 11 developed a method based on the genetic particle filters with autoregression and hypersphere support vector machines (SVMs) to distinguish between the contact state categories using AE signals.…”

Section: Introductionmentioning

confidence: 99%

Gas face seal status estimation based on acoustic emission monitoring and support vector machine regression

Yin

Liu

Huang

et al. 2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The difficulty of knowing the real-time status of gas face seals is the main cause of common problems, including sudden failure, ineffective diagnosis, and unpredictability of service life. This study analyzed the acoustic emission signals generated from experiments, uncovering their features in terms of the frequency distribution, periodic fluctuations, and the behaviors during different operation phases. A new vectorization procedure was designed according to the knowledge of informative acoustic emission features. Based on the vectorization procedure, a support vector machine regression method was applied to develop models predicting the eccentric load on the stator of the seal. Cross-validation was conducted to evaluate the regression performance and search for a proper kernel scale. This study found the informative features of acoustic emissions at different timescales and during different seal operation phases, and particularly the great informative potential of certain segments of the starting and stopping phases. The vectorization and support vector machine regression were shown to be effective in estimating the loads in experiments with cross-validation. Thus, a method for estimating the status of gas face seals based on acoustic emission monitoring was established.

show abstract

Acoustic Emission Monitoring for Film Thickness of Mechanical Seals Based on Feature Dimension Reduction and Cascaded Decision

Cited by 8 publications

References 13 publications

Current Trends and Applications of Machine Learning in Tribology—A Review

Current Trends and Applications of Machine Learning in Tribology—A Review

Impact Phenomena in a Noncontacting Mechanical Face Seal

Gas face seal status estimation based on acoustic emission monitoring and support vector machine regression

Contact Info

Product

Resources

About