scholarly journals Autoencoder-based anomaly detector for gear tooth bending fatigue cracks

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Nenad Nenadic ◽  
Adrian Hood ◽  
Christopher Valant ◽  
Josiah Martuscello ◽  
Patrick Horney ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Gear Tooth ◽  
Fatigue Cracks ◽  
Detection Performance ◽  
Data Driven ◽  
Bending Fatigue ◽  
Gear Teeth ◽  
Condition Indicators ◽  
Anomaly Detector ◽  
Classical Vibration

The article reports on anomaly detection performance of data-driven models based on a few selected autoencoder topologies and compares them to the performance of a set of popular classical vibration-based condition indicators. The evaluation of these models employed data that consisted of baseline gearbox runs and the associated runs with seeded bending cracks in the root of the gear teeth for eight different gear pairings. The analyses showed that the data-driven models, trained on a subset of baseline data outperformed classical CIs as anomaly detectors.

The Stress Intensity Factor and Stiffness for a Cracked Spur Gear Tooth

1994 ◽  
Vol 116 (3) ◽  
pp. 697-700 ◽  
Author(s):  
S. R. Daniewicz ◽  
J. A. Collins ◽  
D. R. Houser
Keyword(s):  
Stress Intensity ◽  
Gear Tooth ◽  
Fatigue Cracks ◽  
Spur Gear ◽  
Potential Method ◽  
Mapping Technique ◽  
Gear Teeth ◽  
Gear Mesh ◽  
Face Width ◽  
Tooth Pair

The stiffness of a spur gear tooth mesh controls load sharing in an operating gearset as well as vibratory properties which further dictate fatigue resistance and gear noise. A spur gear mesh consisting of a pinion with a single cracked tooth and an uncracked gear is considered. Expressions are presented which allow the determination of stress intensity factors for small through face width fatigue cracks in spur gear teeth. Predictions of tooth pair stiffness for a cracked pinion tooth and uncracked gear tooth pair are made using an analytical model. The model is based on elastic energy methods and fracture mechanics principles. The model employs a conformal mapping technique from elasticity theory, often denoted in spur gear applications as the complex potential method, in which a gear tooth is mapped onto on elastic half-plane.

The Stress Intensity Factor and Stiffness for a Cracked Spur Gear Tooth

1992 ◽  
Author(s):  
S. R. Daniewicz ◽  
J. A. Collins ◽  
Donald R. Houser
Keyword(s):  
Stress Intensity ◽  
Gear Tooth ◽  
Fatigue Cracks ◽  
Spur Gear ◽  
Potential Method ◽  
Mapping Technique ◽  
Gear Teeth ◽  
Gear Mesh ◽  
Face Width ◽  
Tooth Pair

Abstract The stiffness of a spur gear tooth mesh controls load sharing in an operating gearset as well as vibratory properties which further dictate fatigue resistance and gear noise. A spur gear mesh consisting of a pinion with a single cracked tooth and an uncracked gear is considered. Expressions are presented which allow the determination of stress intensity factors for small through face width fatigue cracks in spur gear teeth. Predictions of tooth pair stiffness for a cracked pinion tooth and uncracked gear tooth pair are made using an analytical model. The model is based on elastic energy methods and fracture mechanics principles. The model employs a conformal mapping technique from elasticity theory, often denoted in spur gear applications as the complex potential method, in which a gear tooth is mapped onto an elastic half-plane.

scholarly journals Experimental Analysis of Residual Stress and Bending Strength of Gear Tooth Surface after Shot Peening Treatment

2020 ◽  
Vol 2020 ◽  
pp. 1-10
Author(s):  
Dong Liang ◽  
Sheng Meng ◽  
Yi Chen ◽  
Chengli Hua
Keyword(s):  
Residual Stress ◽  
Fatigue Strength ◽  
Shot Peening ◽  
Bending Strength ◽  
Gear Tooth ◽  
Tooth Surface ◽  
Bending Fatigue ◽  
Gear Teeth ◽  
Tooth Surfaces ◽  
Bending Fatigue Strength

The fatigue strength of a gear tooth surface is affected by various factors, which subsequently impacts the transmission performance of gears. Usually, shot peening treatment is carried out during processing to improve the performance of gears. Most current studies focus on theoretical descriptions and simulation analyses of shot peening treatment. However, in this paper, the relationships among shot peening treatment, residual stress, and bending fatigue strength of a gear tooth surface are discussed, through experimental methods. Based on X-ray stress analysis, at select locations on the test samples, the residual stresses on gear tooth surfaces with and without shot peening treatment are determined and contrasted. The results show that shot peening treatment can effectively increase the residual stress on gear tooth surfaces. In addition, an electromagnetic resonance fatigue tester is used to analyze the bending fatigue strength of gear tooth surfaces. The test results indicate that the bending fatigue strength of the gear teeth with shot peening is higher than that of the gear teeth without shot peening. The obtained conclusions lay the foundation for further practical engineering applications of gears.

scholarly journals Research on the Maximal Bearing Capacity Calculation of a New Double Ring Reducer Based on MATLAB

2015 ◽  
Vol 9 (1) ◽  
pp. 34-39
Author(s):  
Qiang Xu ◽  
Qi-sheng Xu ◽  
Dao-Yi Xu
Keyword(s):  
Bearing Capacity ◽  
Elastic Deformation ◽  
Gear Tooth ◽  
Bending Fatigue ◽  
Gear Teeth ◽  
Double Ring ◽  
Contact Points ◽  
Single Tooth ◽  
Capacity Calculation ◽  
Mathematical Relationships

The bearing capacity of a new double ring reducer increases with the increase of load because of the elastic deformation of the gear tooth. In order to solve the problem of its bearing capacity quantificationally, the concept of the maximal bearing capacity is put forward. Starting with that the single tooth bending stress is up to the bending fatigue strength, a mathematical model to determine the normal backlash of the gear teeth has been established, the maximal deformation of the single tooth has been determined. The mathematical relationships have also been setup between the normal backlashes of the tooth pairs, the maximal deformation and number of contact points, a corresponding MATLAB program is designed. The maximal bearing capacity of the reducer has been estimated through examples and proved by experiment. The results show that the calculation method is more effective and fully considers the factors that the elastic deformation of the gear tooth can increases its bearing capacity, so the structure of the reducer is more compact, which establishes the theory foundation for designing the reducer.

A comparative study of data-driven and physics-based gas turbine fault recognition approaches

2021 ◽  
pp. 1748006X2198964
Author(s):  
Juan Luis Pérez-Ruiz ◽  
Igor Loboda ◽  
Iván González-Castillo ◽  
Víctor Manuel Pineda-Molina ◽  
Karen Anaid Rendón-Cortés ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Gas Turbine ◽  
Recognition Accuracy ◽  
Data Driven ◽  
Fault Identification ◽  
Fault Recognition ◽  
Data Driven Approach ◽  
Diagnostic Approaches ◽  
Artificial Neural Network Ann ◽  
Two Stages

The present paper compares the fault recognition capabilities of two gas turbine diagnostic approaches: data-driven and physics-based (a.k.a. gas path analysis, GPA). The comparison takes into consideration two differences between the approaches, the type of diagnostic space and diagnostic decision rule. To that end, two stages are proposed. In the first one, a data-driven approach with an artificial neural network (ANN) that recognizes faults in the space of measurement deviations is compared with a hybrid GPA approach that employs the same type of ANN to recognize faults in the space of estimated fault parameter. Different case studies for both anomaly detection and fault identification are proposed to evaluate the diagnostic spaces. They are formed by varying the classification, type of diagnostic analysis, and deviation noise scheme. In the second stage, the original GPA is reconstructed replacing the ANN with a tolerance-based rule to make diagnostic decisions. Here, two aspects are under analysis: the comparison of GPA classification rules and whole approaches. The results reveal that for simple classifications both spaces are equally accurate for anomaly detection and fault identification. However, for complex scenarios, the data-driven approach provides on average slightly better results for fault identification. The use of a hybrid GPA with ANN for a full classification instead of an original GPA with tolerance-based rule causes an increase of 12.49% in recognition accuracy for fault identification and up to 54.39% for anomaly detection. As for the whole approach comparison, the application of a data-driven approach instead of the original GPA can lead to an improvement of 12.14% and 53.26% in recognition accuracy for fault identification and anomaly detection, respectively.

A Data-Driven Heart Disease Prediction Model Through K-Means Clustering-Based Anomaly Detection

2021 ◽  
Vol 2 (2) ◽  
Author(s):  
Rony Chowdhury Ripan ◽  
Iqbal H. Sarker ◽  
Syed Md. Minhaz Hossain ◽  
Md. Musfique Anwar ◽  
Raza Nowrozy ◽  
...  
Keyword(s):  
Heart Disease ◽  
Anomaly Detection ◽  
Prediction Model ◽  
Data Driven ◽  
Disease Prediction

Solar farm voltage anomaly detection using high-resolution μPMU data-driven unsupervised machine learning

2021 ◽  
Vol 303 ◽  
pp. 117656
Author(s):  
Maitreyee Dey ◽  
Soumya Prakash Rana ◽  
Clarke V. Simmons ◽  
Sandra Dudley
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Anomaly Detection ◽  
Data Driven ◽  
Unsupervised Machine Learning

On the Direction of Fatigue Cracks in Polycrystalline Ingot Iron

1952 ◽  
Vol 19 (1) ◽  
pp. 54-56
Author(s):  
F. A. McClintock
Keyword(s):  
Statistical Analysis ◽  
Shear Failure ◽  
Fatigue Cracks ◽  
Fatigue Tests ◽  
Tensile Failure ◽  
Bending Fatigue ◽  
Polycrystalline Iron

Abstract A statistical analysis is developed to show how a microscopic shear failure can result in the apparent tensile failure of polycrystalline iron in rotary bending fatigue tests.

Effects of Moving Speeds of Dynamic Loads on the Deflections of Gear Teeth

1981 ◽  
Vol 103 (2) ◽  
pp. 357-363 ◽  
Author(s):  
K. Nagaya ◽  
S. Uematsu
Keyword(s):  
Dynamic Response ◽  
Timoshenko Beam ◽  
Gear Tooth ◽  
Bending Moment ◽  
Dynamic Loads ◽  
Gear Teeth ◽  
Moving Speed

For the dynamic response problems of gear teeth, the dynamic loads which act upon the gear teeth should be considered as a function of both the position and the moving speed. In previous studies, the effects of the moving speed have not been considered. In this paper the effects of the moving speed of dynamic loads on the deflection and the bending moment of the gear tooth are investigated. The results are obtained from the elastodynamic analysis of the tapered Timoshenko beam.

Sign in / Sign up

Export Citation Format

Share Document