A Data-Driven Approach for the Diagnosis of Mechanical Systems Using Trained Subtracted Signal Spectrograms

Huh, Jiung; Van, Huan Pham; Han, Soonyoung; Choi, Hae-Jin; Choi, Seung-Kyum

doi:10.3390/s19051055

Cited by 9 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose is to extract the characteristics of the frequencies in a specific time domain from time-series sensor data composed of signals from various kinds of components, which are used for diagnosis. The short-time Fourier transformation (STFT), wavelet packet decomposition (WPD), and WPD with spectral subtraction are used to convert signals into the time-frequency domain [34]. The parameters are adjusted in detail using a 50% overlap to increase the resolution of the time domain.…”

Section: Data Preprocessing (Time-frequency Domain Imaging)mentioning

confidence: 99%

Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis

et al. 2021

Self Cite

View full text Add to dashboard Cite

Fault diagnosis is a top-priority task for the health management of manufacturing processes. Deep learning-based methods are widely used to secure high fault diagnosis accuracy. Actually, it is difficult and expensive to collect large-scale data in industrial fields. Several prerequisite problems can be solved using transfer learning for fault diagnosis. Data from the source domain that are different but related to the target domain are used to increase the diagnosis performance of the target domain. However, a negative transfer occurs that degrades diagnosis performance due to the transfer when the discrepancy between and within domains is large. A multi-objective instance weighting-based transfer learning network is proposed to solve this problem and successfully applied to fault diagnosis. The proposed method uses a newly devised multi-objective instance weight to deal with practical situations where domain discrepancy is large. It adjusts the influence of the domain data on model training through two theoretically different indicators. Knowledge transfer is performed differentially by sorting instances similar to the target domain in terms of distribution with useful information for the target task. This domain optimization process maximizes the performance of transfer learning. A case study using an industrial robot and spot-welding testbed is conducted to verify the effectiveness of the proposed technique. The performance and applicability of transfer learning in the proposed method are observed in detail through the same case study as the actual industrial field for comparison. The diagnostic accuracy and robustness are high, even when few data are used. Thus, the proposed technique is a promising tool that can be used for successful fault diagnosis.

show abstract

Section: Data Preprocessing (Time-frequency Domain Imaging)mentioning

confidence: 99%

Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kim et al [7] proposed a method to diagnose the severity of control cable wire damage. Huh et al [8] diagnosed soft and hard pitting gears based on a critical information map (CIM). These studies improved diagnoses considering different fault severities, but studied only a single component, not multiple components.…”

Section: Introductionmentioning

confidence: 99%

System-Level Fault Diagnosis for an Industrial Wafer Transfer Robot with Multi-Component Failure Modes

Lee,

Park,

Jang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In the manufacturing industry, robots are constantly operated at high speed, which degrades their performance by the degradation of internal components, eventually reaching failure. To address this issue, a framework for system-level fault diagnosis is proposed, which consists of extracting useful features from the motor control signal acquired during the operation, diagnosing the current health of each component using the features, and estimating the associated degradation in the robot system’s performance. Finally, a maintenance strategy is determined by evaluating how well the system performance is restored by the replacement of each component. The framework is demonstrated using the example of a wafer transfer robot in the semiconductor industry, in which the robot is operated under faults with various severities for two critical components: the harmonic drive and the timing belt. Features are extracted for the motor signal using wavelet packet decomposition, followed by feature selection by considering the trendability and separability of the fault severity. An artificial neural network model and Gaussian process regression are employed for the diagnosis of the components’ health and the system’s performance, respectively.

show abstract

“…Suh [23] proposed a data-driven health segmentation method based on convolutional neural network, which can monitor the wear condition of bearings earlier and more effectively. For the mechanical systems health prediction and management, Huh [5] proposed a data-driven fault diagnosis method which applies critical information map identifying the difference between the signal spectrograms of normal and abnormal status. Morais [16] monitors the the force in the mechanical system, which is more likely to be realized in the monitoring of rotating parts.…”

Section: Introductionmentioning

confidence: 99%

Multi-level health degree analysis of vehicle transmission system based on PSO- Indexed by: BP neural network data fusion

Wu¹,

Cui²,

Shu³

et al. 2023

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

In order to realize the evaluation of the vehicle transmission system health degree, a prediction model by multi-level data fusion method is established in this paper. The prediction model applies PSO(Particle Swarm Optimization)-BP(Back Propagation) neural network algorithm, calculates the whole machine health degree and each module respective weights from the test data. On this basis, it analyzes the error between the model calculated health degree and theoretical health degree. Then the research verifies the validity and prediction model accuracy. The health degree which is obtained by the single module feature parameters fusion, and the vehicle transmission system health degree is investigated, which is less effective compared to the three-level fusions. After that, by analyzing the vehicle transmission system multi-parameter feature weights, it is found that the mechanical module accounted for the largest damage rate, and the three modules influenced the vehicle transmission system health degree in the order of mechanical module, hydraulic module, and electric control module. The study has played a guiding role in the health management of complex equipment.

show abstract

A Data-Driven Approach for the Diagnosis of Mechanical Systems Using Trained Subtracted Signal Spectrograms

Cited by 9 publications

References 35 publications

Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis

Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis

System-Level Fault Diagnosis for an Industrial Wafer Transfer Robot with Multi-Component Failure Modes

Multi-level health degree analysis of vehicle transmission system based on PSO- Indexed by: BP neural network data fusion

Contact Info

Product

Resources

About