scholarly journals An Automated Data Fusion-Based Gear Faults Classification Framework in Rotating Machines

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2957
Author(s):  
Ruifeng Cao ◽  
Akilu Yunusa-Kaltungo
Keyword(s):  
Decision Rules ◽  
Principal Component ◽  
Vibration Monitoring ◽  
Rotating Machines ◽  
Composite Spectrum ◽  
Vibration Sensors ◽  
Rotating Machine ◽  
Classification Framework ◽  
Gear Fault ◽  
Artificial Neural Network Ann

The feasibility and usefulness of frequency domain fusion of data from multiple vibration sensors installed on typical industrial rotating machines, based on coherent composite spectrum (CCS) as well as poly-coherent composite spectrum (pCCS) techniques, have been well-iterated by earlier studies. However, all previous endeavours have been limited to rotor faults, thereby raising questions about the proficiency of the approach for classifying faults related to other critical rotating machine components such as gearboxes. Besides the restriction in scope of the founding CCS and pCCS studies on rotor-related faults, their diagnosis approach was manually implemented, which could be unrealistic when faced with routine condition monitoring of multi-component industrial rotating machines, which often entails high-frequency sampling at multiple locations. In order to alleviate these challenges, this paper introduced an automated framework that encompassed feature generation through CCS, data dimensionality reduction through principal component analysis (PCA), and faults classification using artificial neural network (ANN). The outcomes of the automated approach are a set of visualised decision maps representing individually simulated scenarios, which simplifies and illustrates the decision rules of the faults characterisation framework. Additionally, the proposed approach minimises diagnosis-related downtime by allowing asset operators to easily identify anomalies at their incipient stages without necessarily possessing vibration monitoring expertise. Building upon the encouraging results obtained from the preceding part of this approach that was limited to well-known rotor-related faults, the proposed framework was significantly extended to include experimental and open-source gear fault data. The results show that in addition to early established rotor-related faults classification, the approach described here can also effectively and automatically classify gearbox faults, thereby improving the robustness.

Vibration Analysis on Rotating Machines using Fast Fourier Transform (FFT)

2019 ◽  
Vol 3 (1) ◽  
pp. 67-75
Author(s):  
Iip Muhlisin ◽  
Rusman Rusyadi
Keyword(s):  
System Performance ◽  
Vibration Analysis ◽  
Vibration Monitoring ◽  
Initial Condition ◽  
Rotating Machines ◽  
Experimental Frequency ◽  
Vibration Load ◽  
Time Frequency ◽  
Rotating Machine ◽  
Analytical Approaches

The history has record that heavy industries face major problems that causes by variant types of mechanical failures came from rotating machines. The Vibrations in rotating machine almost fond in everywhere, due to unbalances, misalignments and imperfect part, analytical approaches has shown that vibration monitoring has great capability in detecting and addressing the defect particular part in the machine line .The vibration velocities and vibration load will be measured at different speeds using The Time-frequency analysis at initial condition. The result of vibration readings spectrum analysis and phase analysis can be determining the figure of vibrations character, and the causes of height vibration will be found. By reading the spectrum unbalance will be identified. When the unbalanced part was balanced then we found that the vibration was decrease. The Vibration experimental frequency spectrum test will be conduct for both balanced and unbalanced condition and also in different speed conditions. To full fill the vibration analysis test, in this experimental research a prototype of vibration monitoring system was constructed. The vibration can be generated and the system performance can be monitored. In this prototype the signal from load cell and velocity sensor will be processed in microcontroller and send to computer where FFT will processed the signal to create spectrum in the computer display. The actual final result of Vibration analysis test will be provide after finish the vibrations analysis test that will be done latter, therefore the chart result on this paper is based on theoretical only.

Thermodynamics Energy for Both Supervised and Unsupervised Learning Neural Nets at a Constant Temperature

1999 ◽  
Vol 09 (03) ◽  
pp. 175-186 ◽  
Author(s):  
HAROLD SZU
Keyword(s):  
Free Energy ◽  
Constant Temperature ◽  
Helmholtz Free Energy ◽  
Principal Component ◽  
Neural Nets ◽  
Mixing Condition ◽  
Smart Cameras ◽  
Minimization Principle ◽  
Output Entropy ◽  
Artificial Neural Network Ann

Unified Lyaponov function is given for the first time to prove the learning methodologies convergence of artificial neural network (ANN), both supervised and unsupervised, from the viewpoint of the minimization of the Helmholtz free energy at the constant temperature. Early in 1982, Hopfield has proven the supervised learning by the energy minimization principle. Recently in 1996, Bell & Sejnowski has algorithmically demonstrated. Independent Component Analyses (ICA) generalizing the Principal Component Analyses (PCA) that the continuing reduction of early vision redundancy happens towards the "sparse edge maps" by maximization of the ANN output entropy. We explore the combination of both as Lyaponov function of which the proven convergence gives both learning methodologies. The unification is possible because of the thermodynamics Helmholtz free energy at a constant temperature. The blind de-mixing condition for more than two objects using two sensor measurement. We design two smart cameras with short term working memory to do better image de-mixing of more than two objects. We consider channel communication application that we can efficiently mix four images using matrices [AO] and [Al] to send through two channels.

Effects of the Shaft Normal Modes on the Model-Based Identification of Unbalances in Rotating Machines

2011 ◽  
Author(s):  
A. Vania ◽  
P. Pennacchi ◽  
S. Chatterton
Keyword(s):  
Normal Modes ◽  
Fault Identification ◽  
Diagnostic Strategy ◽  
Rotating Machines ◽  
Large Power ◽  
Identification Methods ◽  
Model Based ◽  
Rotating Machine ◽  
Experimental Response ◽  
Innovative Techniques

Model-based methods can be applied to identify the most likely faults that cause the experimental response of a rotating machine. Sometimes, the objective function, to be minimized in the fault identification method, shows multiple sufficiently low values that are associated with different sets of the equivalent excitations by means of which the fault can be modeled. In these cases, the knowledge of the contribution of each normal mode of interest to the vibration predicted at each measurement point can provide useful information to identify the actual fault. In this paper, the capabilities of an original diagnostic strategy that combines the use of common fault identification methods with innovative techniques based on a modal representation of the dynamic behavior of rotating machines is shown. This investigation approach has been successfully validated by means of the analysis of the abnormal vibrations of a large power unit.

scholarly journals Global Tree Taper Modelling: A Review of Applications, Methods, Functions, and Their Parameters

Forests ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 913
Author(s):  
Serajis Salekin ◽  
Cristian Higuera Catalán ◽  
Daniel Boczniewicz ◽  
Darius Phiri ◽  
Justin Morgenroth ◽  
...  
Keyword(s):  
Measurement Techniques ◽  
Principal Component ◽  
Climatic Conditions ◽  
Modern Times ◽  
Taper Function ◽  
Complex Functions ◽  
Artificial Neural Network Ann ◽  
Species Specific ◽  
Simple Equations ◽  
Taper Equations

Taper functions are important tools for forest description, modelling, assessment, and management. A large number of studies have been conducted to develop and improve taper functions; however, few review studies have been dedicated to addressing their development and parameters. This review summarises the development of taper functions by considering their parameterisation, geographic and species-specific limitations, and applications. This study showed that there has been an increase in the number of studies of taper function and contemporary methods have been developed for the establishment of these functions. The reviewed studies also show that taper functions have been developed from simple equations in the early 1900s to complex functions in modern times. Early taper functions included polynomial, sigmoid, principal component analysis (PCA), and linear mixed functions, while contemporary machine learning (ML) approaches include artificial neural network (ANN) and random forest (RF). Further analysis of the published literature also shows that most of the studies of taper functions have been carried out in Europe and the Americas, meaning most taper equations are not specifically applicable to tropical tree species. Developing well-conditioned taper functions requires reducing the variation due to species, measurement techniques, and climatic conditions, among other factors. The information presented in this study is important for understanding and developing taper functions. Future studies can focus on developing better taper functions by incorporating emerging remote sensing and geospatial datasets, and using contemporary statistical approaches such as ANN and RF.

scholarly journals Centered Kernel Alignment Enhancing Neural Network Pretraining for MRI-Based Dementia Diagnosis

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
David Cárdenas-Peña ◽  
Diego Collazos-Huertas ◽  
German Castellanos-Dominguez
Keyword(s):  
Neural Network ◽  
Characteristic Curve ◽  
Principal Component ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Dementia Diagnosis ◽  
Target Matrix ◽  
Computer Aided ◽  
Artificial Neural Network Ann ◽  
Aided Diagnosis

Dementia is a growing problem that affects elderly people worldwide. More accurate evaluation of dementia diagnosis can help during the medical examination. Several methods for computer-aided dementia diagnosis have been proposed using resonance imaging scans to discriminate between patients with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) and healthy controls (NC). Nonetheless, the computer-aided diagnosis is especially challenging because of the heterogeneous and intermediate nature of MCI. We address the automated dementia diagnosis by introducing a novel supervised pretraining approach that takes advantage of the artificial neural network (ANN) for complex classification tasks. The proposal initializes an ANN based on linear projections to achieve more discriminating spaces. Such projections are estimated by maximizing the centered kernel alignment criterion that assesses the affinity between the resonance imaging data kernel matrix and the label target matrix. As a result, the performed linear embedding allows accounting for features that contribute the most to the MCI class discrimination. We compare the supervised pretraining approach to two unsupervised initialization methods (autoencoders and Principal Component Analysis) and against the best four performing classification methods of the 2014CADDementiachallenge. As a result, our proposal outperforms all the baselines (7% of classification accuracy and area under the receiver-operating-characteristic curve) at the time it reduces the class biasing.

Machine Fault Detection Using Genetic Programming

2005 ◽  
Author(s):  
B. Samanta
Keyword(s):  
Fault Detection ◽  
Genetic Programming ◽  
Vibration Data ◽  
Rotating Machine ◽  
Fault Recognition ◽  
Machine Fault ◽  
Artificial Neural Network Ann ◽  
Monitoring And Diagnostics ◽  
The Time Domain ◽  
Selection Of

Applications of genetic programming (GP) include many areas. However applications of GP in the area of machine condition monitoring and diagnostics is very recent and yet to be fully exploited. In this paper, a study is presented to show the performance of machine fault detection using GP. The time domain vibration signals of a rotating machine with normal and defective gears are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to GP for two class (normal or fault) recognition. The number of features and the features are automatically selected in GP maximizing the classification success. The results of fault detection are compared with genetic algorithm (GA) based artificial neural network (ANN)- termed here as GA-ANN. The number of hidden nodes in the ANN and the selection of input features are optimized using GAs. Two different normalization schemes for the features have been used. For each trial, the GP and GA-ANN are trained with a subset of the experimental data for known machine conditions. The trained GP and GA-ANN are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a gearbox. The results compare the effectiveness of both types of classifiers with GP and GA based selection of features.

scholarly journals Prediction Model of Iron Ore Pellet Ambient Strength and Sensitivity Analysis on the Influence Factors

Metals ◽  
2018 ◽  
Vol 8 (8) ◽  
pp. 593 ◽  
Author(s):  
Qiangjian Gao ◽  
Yingyi Zhang ◽  
Xin Jiang ◽  
Haiyan Zheng ◽  
Fengman Shen
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Prediction Model ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Influence Factors ◽  
Principal Component ◽  
Bp Network ◽  
Input Variables ◽  
Artificial Neural Network Ann

The Ambient Compressive Strength (CS) of pellets, influenced by several factors, is regarded as a criterion to assess pellets during metallurgical processes. A prediction model based on Artificial Neural Network (ANN) was proposed in order to provide a reliable and economic control strategy for CS in pellet production and to forecast and control pellet CS. The dimensionality of 19 influence factors of CS was considered and reduced by Principal Component Analysis (PCA). The PCA variables were then used as the input variables for the Back Propagation (BP) neural network, which was upgraded by Genetic Algorithm (GA), with CS as the output variable. After training and testing with production data, the PCA-GA-BP neural network was established. Additionally, the sensitivity analysis of input variables was calculated to obtain a detailed influence on pellet CS. It has been found that prediction accuracy of the PCA-GA-BP network mentioned here is 96.4%, indicating that the ANN network is effective to predict CS in the pelletizing process.

An Effective Hybrid Semi-Parametric Regression Strategy for Rainfall Forecasting Combining Linear and Nonlinear Regression

2013 ◽  
pp. 273-289
Author(s):  
Jiansheng Wu
Keyword(s):  
Nonlinear Regression ◽  
Regression Models ◽  
Principal Component ◽  
Linear Regression Models ◽  
Rainfall Forecasting ◽  
Forecasting Accuracy ◽  
Parametric Regression ◽  
Nonlinear Regression Models ◽  
Linear And Nonlinear ◽  
Artificial Neural Network Ann

Rainfall forecasting is an important research topic in disaster prevention and reduction. The characteristic of rainfall involves a rather complex systematic dynamics under the influence of different meteorological factors, including linear and nonlinear pattern. Recently, many approaches to improve forecasting accuracy have been introduced. Artificial neural network (ANN), which performs a nonlinear mapping between inputs and outputs, has played a crucial role in forecasting rainfall data. In this paper, an effective hybrid semi-parametric regression ensemble (SRE) model is presented for rainfall forecasting. In this model, three linear regression models are used to capture rainfall linear characteristics and three nonlinear regression models based on ANN are able to capture rainfall nonlinear characteristics. The semi-parametric regression is used for ensemble model based on the principal component analysis technique. Empirical results reveal that the prediction using the SRE model is generally better than those obtained using other models in terms of the same evaluation measurements. The SRE model proposed in this paper can be used as a promising alternative forecasting tool for rainfall to achieve greater forecasting accuracy and improve prediction quality.

Sign in / Sign up

Export Citation Format

Share Document