A dual path optimization ridge estimation method for condition monitoring of planetary gearbox under varying-speed operation

Measurement ◽  
2016 ◽  
Vol 94 ◽  
pp. 630-644 ◽  
Author(s):  
Xingxing Jiang ◽  
Shunming Li
Keyword(s):  
Condition Monitoring ◽  
Estimation Method ◽  
Path Optimization ◽  
Planetary Gearbox ◽  
Ridge Estimation

scholarly journals A Study on Defect Identification of Planetary Gearbox under Large Speed Oscillation

2016 ◽  
Vol 2016 ◽  
pp. 1-18 ◽  
Author(s):  
Xingxing Jiang ◽  
Shunming Li ◽  
Qian Wang
Keyword(s):  
Condition Monitoring ◽  
Vibration Signal ◽  
Estimation Methods ◽  
Planetary Gearbox ◽  
Time Frequency ◽  
Ridge Estimation ◽  
Practical Engineering ◽  
Conventional Methods ◽  
Tracking Time ◽  
Large Speed

Rotational speed of a reference shaft is the key information for planetary gearbox condition monitoring under nonstationary conditions. As the time-variant speed and load of planetary gearboxes result in time-variant characteristic frequencies as well as vibration magnitudes, the conventional methods tracking time-frequency ridge perform a poor robustness, especially for large speed variations. In this paper, two schemes, time-frequency ridge fusion and logarithm transformation, are proposed to track the targeted ridge curve reliably. Meanwhile, the identified ridge curve by logarithm scheme can be further refined by the time-frequency ridge fusion scheme. Hence, a procedure involving the proposed ridge estimation methods is presented to diagnose the planetary gearbox defects. Two simulation signals and a vibration signal collected from a planetary gearbox in practical engineering (provided by the conference on condition monitoring of machinery in nonstationary operations (CMMNO)) are used to verify the proposed methods. It is validated that the proposed methods can well-track the targeted ridge curve compared with two conventional methods. As a result, the characteristic frequency of each component in the planetary gearbox is clearly demonstrated and the inner race defect of one of the planet bearings is successfully discovered in the order spectrum depending on the derived expression of planet bearing fault frequency.

Pattern recognition approach for acoustic emission burst detection in a gearbox under different operating conditions

2019 ◽  
Vol 25 (17) ◽  
pp. 2295-2304
Author(s):  
Félix Leaman ◽  
Cristián Molina Vicuña ◽  
Ralph Baltes ◽  
Elisabeth Clausen
Keyword(s):  
Pattern Recognition ◽  
Acoustic Emission ◽  
Condition Monitoring ◽  
Rotational Speed ◽  
Operating Conditions ◽  
Burst Detection ◽  
Threshold Method ◽  
Planetary Gearbox ◽  
Industrial Sectors ◽  
Artificial Neural Network Ann

Diverse machines in the mining, energy, and other industrial sectors are subject to variable operating conditions (OCs) such as rotational speed and load. Therefore, the condition monitoring techniques must be adapted to face this scenario. Within these techniques, the acoustic emission (AE) technology has been successfully used as a technique for condition monitoring of components such as gears and bearings. An AE analysis involves the detection of transients within the signals, which are called AE bursts. Traditional methods for AE burst detection are based on the definition of threshold values. When the machine under study works under variable rotational speed and load, threshold-based methods could produce inadequate results due to the influence of these OCs on the AE. This paper presents a novel burst detection method based on pattern recognition using an artificial neural network (ANN) for classification. The results of the method were compared to an adaptive threshold method. Experimental data were measured in a planetary gearbox test rig under different OCs. The results showed that both methods perform similarly when signals measured under constant OCs are considered. However, when signals are measured under different OCs, the ANN method performs better. Thus, the comparative analysis showed the good potential of the approach to improve an AE analysis of variable speed and/or load machines.

Ridge estimation iterative algorithm to ill-posed uncertainty adjustment model

2020 ◽  
Author(s):  
tieding lu
Keyword(s):  
Parameter Estimation ◽  
Iterative Algorithm ◽  
Measurement Data ◽  
Estimation Method ◽  
Coefficient Matrix ◽  
Observation Equation ◽  
Validity And Reliability ◽  
Ridge Estimation ◽  
Adjustment Model ◽  
Ill Posed

<p> Uncertainties usually exist in the process of acquisition of measurement data, which affect the results of the parameter estimation. The solution of the uncertainty adjustment model can effectively improve the validity and reliability of parameter estimation. When the coefficient matrix of the observation equation has a singular value close to zero, i.e., the coefficient matrix is ill-posed, the ridge estimation can effectively suppress the influence of the ill-posed problem of the observation equation on the parameter estimation. When the uncertainty adjustment model is ill-posed, it is more seriously affected by the error of the coefficient matrix and observation vector. In this paper, the ridge estimation method is applied to ill-posed uncertainty adjustment model, deriving an iterative algorithm to improve the stability and reliability of the results. The derived algorithm is verified by two examples, and the results show that the new method is effective and feasible.</p>

Feature-Based Tool Condition Monitoring in a Gear Shaving Application

2008 ◽  
Author(s):  
A. J. Brzezinski ◽  
Y. Wang ◽  
D. K. Choi ◽  
X. Qiao ◽  
J. Ni
Keyword(s):  
Tool Wear ◽  
Condition Monitoring ◽  
Feature Fusion ◽  
Estimation Method ◽  
Principal Component ◽  
Time Frequency ◽  
Tool Condition ◽  
Tool Wear Estimation ◽  
Artificial Neural Network Ann ◽  
Feature Dimension

Condition monitoring (CM) is an effective way to improve the tool life of a cutting tool. However, CM techniques have not been applied to monitor tool wear in an industrial gear shaving application. Therefore, this paper introduces a novel, sensor-based, data-driven, tool wear estimation method for monitoring gear shaver tool condition. The method is applied on an industrial gear shaving machine and used to differentiate between four different tool wear conditions (new, slightly worn, significantly worn, and broken). This research focuses on combining, expanding, and implementing CM techniques in an application where no previous work has been done. In order to realize CM, this paper discusses each aspect of CM, beginning with data collection and pre-processing. Feature extraction (in the time, frequency, and time-frequency domains) is then explained. Furthermore, feature dimension reduction using principal component analysis (PCA) is described. Finally, feature fusion using a multi-layer perceptron (MLP) type of artificial neural network (ANN) is presented.

scholarly journals Improvement in Ridge Coefficient Optimization Criterion for Ridge Estimation-Based Dynamic System Response Curve Method in Flood Forecasting

Water ◽  
2021 ◽  
Vol 13 (24) ◽  
pp. 3483
Author(s):  
Kexin Liu ◽  
Weimin Bao ◽  
Yufeng Hu ◽  
Yiqun Sun ◽  
Dongjing Li ◽  
...  
Keyword(s):  
Dynamic System ◽  
Response Curve ◽  
Estimation Method ◽  
Real Data ◽  
Optimization Criterion ◽  
Sum Of Squares ◽  
System Response ◽  
Ridge Estimation ◽  
Coefficient Optimization ◽  
Curve Method

The ridge estimation-based dynamic system response curve (DSRC-R) method, which is an improvement of the dynamic system response curve (DSRC) method via the ridge estimation method, has illustrated its good robustness. However, the optimization criterion for the ridge coefficient in the DSRC-R method still needs further study. In view of this, a new optimization criterion called the balance and random degree criterion considering the sum of squares of flow errors (BSR) is proposed in this paper according to the properties of model-simulated residuals. In this criterion, two indexes, namely, the random degree of simulated residuals and the balance degree of simulated residuals, are introduced to describe the independence and the zero mean property of simulated residuals, respectively. Therefore, the BSR criterion is constructed by combining the sum of squares of flow errors with the two indexes. The BSR criterion, L-curve criterion and the minimum sum of squares of flow errors (MSSFE) criterion are tested on both synthetic cases and real-data cases. The results show that the BSR criterion is better than the L-curve criterion in minimizing the sum of squares of flow residuals and increasing the ridge coefficient optimization speed. Moreover, the BSR criterion has an advantage over the MSSFE criterion in making the estimated rainfall error more stable.

Wind turbine planetary gearbox feature extraction and fault diagnosis using a deep-learning-based approach

2018 ◽  
Vol 233 (3) ◽  
pp. 303-316 ◽  
Author(s):  
Miao He ◽  
David He ◽  
Jae Yoon ◽  
Thomas J Nostrand ◽  
Junda Zhu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Dictionary Learning ◽  
Memory Storage ◽  
Vibration Monitoring ◽  
Planetary Gearbox ◽  
Storage And Retrieval ◽  
Vibration Data ◽  
Large Memory

Planetary gearboxes are widely used in the drivetrain of wind turbines. Planetary gearbox fault diagnosis is very important for reducing the downtime and maintenance cost and improving the safety, reliability, and life span of the wind turbines. The wind energy industry is currently using condition monitoring systems to collect massive real-time data and conventional vibratory analysis as a standard method for planetary gearbox condition monitoring. As an attractive option to process big data for fault diagnosis, deep learning can automatically learn features that otherwise require much skill, time, and experience. This article presents a new deep-learning-based method for wind turbine planetary gearbox fault diagnosis developed by a large memory storage and retrieval neural network with dictionary learning. The developed approach can automatically extract self-learned fault features from raw vibration monitoring data and perform planetary gearbox fault diagnosis without supervised fine-tuning process. From the raw vibration monitoring data, a dictionary is first learned by a large memory storage and retrieval with dictionary learning network. Based on the learned dictionary, a sparse representation of the raw vibration signals is generated by shift-invariant sparse coding and input to a large memory storage and retrieval network classifier to obtain fault diagnosis results. The structure of the large memory storage and retrieval with dictionary learning is determined by optimal selection of the sliding box size to generate sub-patterns from the vibration data. The effectiveness of the presented method is tested and validated with a set of seeded fault vibration data collected at a planetary gearbox test rig in laboratory. The validation results have shown a promising planetary gearbox fault diagnosis performance with the presented method.

Structural Damage Detection Based on Ridge Estimation Method

2014 ◽  
Vol 578-579 ◽  
pp. 1028-1031
Author(s):  
Hui Yong Guo ◽  
Mao Sheng ◽  
Zheng Liang Li
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Strain Energy ◽  
Good Accuracy ◽  
Detection Method ◽  
Estimation Method ◽  
Structural Damage Detection ◽  
Modal Strain Energy ◽  
Ridge Estimation ◽  
Damage Equation

In order to identify structural damage locations and extent, a method based on ridge estimation and modal strain energy is presented in this paper. First, structural modal strain energy is given and a modal strain energy sensitivity damage equation is obtained. Then, considering the TikhonovTT regularization theoryTT, a ridge estimation method is proposed to solve the damage equation and ridge parameter of the method is optimized. Simulation results demonstrate that the proposed damage detection method based on ridge estimation and modal strain energy can identify structural damage locations and extent with good accuracy.

Sign in / Sign up

Export Citation Format

Share Document