Gear dynamics monitoring using discrete wavelet transformation and multi-layer perceptron neural networks

Abstract

This paper presents a multi-stage algorithm for the dynamic condition monitoring of a gear. The algorithm provides information referred to the gear status (fault or normal condition) and estimates the mesh stiffness per shaft revolution in case that any abnormality is detected. In the first stage, the analysis of coefficients generated through discrete wavelet transformation (DWT) is proposed as a fault detection and localization tool. The second stage consists in establishing the mesh stiffness reduction associated with local failures by applying a supervised learning mode and coupled with analytical models. To do this, a multi-layer perceptron neural network has been configured using as input features statistical parameters sensitive to torsional stiffness decrease and derived from wavelet transforms of the response signal. The proposed method is applied to the gear condition monitoring and results show that it can update the mesh dynamic properties of the gear on line.

A long-term prediction approach based on long short-term memory neural networks with automatic parameter optimization by Tree-structured Parzen Estimator and applied to time-series data of NPP steam generators

“…models of fatigue crack growth [6], [7], of capacity degradation in Lithium-ion batteries [8], [9]. Alternatively, data-driven approaches utilize condition monitoring data collected from sensors to learn and predict the component or system behavior and degradation via statistical and artificial intelligent (AI) models, such as autoregressive integrated moving average (ARIMA) [10], artificial neural network (ANN) [11]- [14], neuro-fuzzy (NF) [2] and support vector machine (SVM) [15]- [17]. Due to the data-adaptive nature, data-driven approaches are quite appropriate for prognostic real-world applications where models are not available whereas obtaining condition monitoring data is becoming convenient with smart sensors.…”

Two novel proposed discrete wavelet transform and filter based approaches for short-circuit faults detection in power transmission lines

“…Discrete wavelet transform (DWT) as a soft computing tool has been used in different applications [11][12][13]. In some researches, wavelet transform has been combined with other topics such as ANN and fuzzy systems to form hybrid frameworks [14][15][16][17][18][19]. A fault detection and classification method which uses discrete wavelet transform in combination with ANN was reported in [20].…”

Introduction to Artificial Intelligence based Decision Making

“…This is because it can distinguish data that is not linearly separable, or separable by a hyper-plane. The MLP has been used to model many complex systems in areas such as estimating invasive cerebrospinal fluid pressure (Golzan et al, 2012), monitoring electric load of residential buildings (Rababaah and Tebekaemi, 2012), separating nonlinear source (Elmannai et al, 2012), monitoring gear dynamics (Sanz et al, 2012), engineering sciences (Marwala, 2010), approximating the Vickers hardness of Mn-Ni-Cu-Mo austempered ductile iron (PourAsiabi et al, 2012), estimating wind speed (Culotta et al, 2012), automatically monitoring critical infrastructure (Marwala, 2012), and forecasting odorant chemical class from descriptor values (Bachtiar et al, 2011).…”