State of the art on vibration signal processing towards data‐driven gear fault diagnosis

Zhang, Shouhua; Zhou, Jiehan; Wang, Erhua; Zhang, Hong; Gu, Mu; Pirttikangas, Susanna

doi:10.1049/cim2.12064

Cited by 14 publications

(5 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, since gearbox vibration signals contain rich fault information and vibration signals are less expensive to measure and record [5]. Therefore, vibration signal analysis is the mainstream method for gearbox fault diagnosis [6]. However, due to the complex internal structure of the planetary gearbox, the vibrations generated by the Sun wheel and the planetary wheel are coupled with each other, resulting in a vibration signal with non-linear and non-smooth properties, and the early fault characteristics are easily drowned by noise [7].…”

Section: Introductionmentioning

confidence: 99%

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

Tao,

Shi,

Qiu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Although data-driven methods have been widely used in planetary gearbox fault diagnosis, the difficulty and high cost of manual labeling leads to little labeled training data, which limits the classification performance of traditional data-driven methods. Therefore, the semi-supervised fault diagnosis method with few labeled samples becomes one of the main research directions. Graph attention network (GAT) is distinguished from traditional classification network by using graph structure for fault node information aggregation and feature extraction, which is an effective semi-supervised learning algorithm. This paper uses fast Fourier transform to process the original vibration signal of gearbox and use it as graph nodes, and propose a KNN graph construction method using pooling for fuzzy distance calculation. In addition, this paper improves the distribution of attention weights by introducing dynamic graph attention networks to correct the problem that classical static GATs cannot clearly distinguish the weights of different categories of nodes. Experiments show that the method proposed in this paper can better extract fault features in complex gearbox vibration signals with an accuracy of more than 99% with very few labeled samples, and has better diagnostic performance compared with other graph neural network architectures and traditional classification networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

Tao,

Shi,

Qiu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Fundamentally speaking, abrasive and adhesive wear are distinguished modes of tooth wear failures. Adhesive wear is characterized by material transfer between teeth, which leads to propensities for ripping and welding, as opposed to abrasive wear, which includes material removal as a result of inter-tooth contact [25,26]. Scuffing is a key failure mode that is frequently ignored in gear analysis.…”

Section: Introductionmentioning

confidence: 99%

“…This occurrence results from sliding motions interacting with lubricated contacts, which generate high temperatures. These elevated temperatures can consequently cause the surface film that coats the gears to deteriorate, leading to deformations and eventually the melting of the relatively softer gear components [25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Extruder Machine Gear Fault Detection Using Autoencoder LSTM via Sensor Fusion Approach

Lee,

Okwuosa,

Hur

2023

Inventions

View full text Add to dashboard Cite

In industrial settings, gears play a crucial role by assisting various machinery functions such as speed control, torque manipulation, and altering motion direction. The malfunction or failure of these gear components can have serious repercussions, resulting in production halts and financial losses. To address this need, research efforts have focused on early defect detection in gears in order to reduce the impact of possible failures. This study focused on analyzing vibration and thermal datasets from two extruder machine gearboxes using an autoencoder Long Short-Term Memory (AE-LSTM) model, to ensure that all important characteristics of the system are utilized. Fast independent component analysis (FastICA) is employed to fuse the data signals from both sensors while retaining their characteristics. The major goal is to implement an outlier detection approach to detect and classify defects. The results of this study highlighted the extraordinary performance of the AE-LSTM model, which achieved an impressive accuracy rate of 94.42% in recognizing malfunctioning gearboxes within the extruder machine system. The study used robust global metric evaluation techniques, such as accuracy, F1-score, and confusion metrics, to thoroughly evaluate the model’s dependability and efficiency. LSTM was additionally employed for anomaly detection to further emphasize the adaptability and interoperability of the methodology. This modification yielded a remarkable accuracy of 89.67%, offering additional validation of the model’s reliability and competence.

show abstract

“…Vibration signals are often measured and analyzed to extract information about systems, equipment, or structures. This information is utilized for applications such as fault detection [1], equipment performance optimization and preventative maintenance [2], human health monitoring [3], structural health monitoring [4,5], as well as vibration energy harvesting [6]. Due to the extremely weak, primarily low frequency and wide vibration frequency range of the generated vibration signals in earthquake exploration, water pipeline leakage, and bridge structure monitoring industries [7][8][9], vibration sensors with a high sensitivity and wide measurement bandwidth have increasingly significant application potential to ensure the accuracy and reliability of risk assessments and safety monitoring.…”

Section: Introductionmentioning

confidence: 99%

Design and Experimental Evaluation of a Dual-Cantilever Piezoelectric Film Sensor with a Broadband Response and High Sensitivity

Xin,

He,

Zhao

2023

Micromachines

View full text Add to dashboard Cite

Cantilever-beam-type PVDF (Polyvinylidene Fluoride) piezoelectric film sensors are commonly utilized for vibration signal detection due to their simple structures and ease of processing. Traditional cantilevered PVDF piezoelectric film sensors are susceptible to the influence of the second-order vibration mode and have a low lateral stress distribution at the free end, which limit their measurement bandwidth and sensitivity. This study is on the design of a dual-cantilever PVDF piezoelectric film sensor based on the principle of cantilevered piezoelectric film sensors. The results of the experiments indicate that, compared to a typical single-arm piezoelectric cantilever beam vibration sensor, the developed sensor has a longer second-order natural frequency that ranges from 112 Hz to 453 Hz, while the first-order natural frequency is maintained at around 12 Hz. This leads to a better ratio of the second-order natural frequency to the first-order natural frequency and a wider frequency response range. At the same time, the sensitivity is increased by a factor of 3.48.

show abstract

State of the art on vibration signal processing towards data‐driven gear fault diagnosis

Cited by 14 publications

References 91 publications

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

Planetary gearbox fault diagnosis based on FDKNN-DGAT with few labeled data

Extruder Machine Gear Fault Detection Using Autoencoder LSTM via Sensor Fusion Approach

Design and Experimental Evaluation of a Dual-Cantilever Piezoelectric Film Sensor with a Broadband Response and High Sensitivity

Contact Info

Product

Resources

About