Fault detection of engine timing belt based on vibration signals using data-mining techniques and a novel data fusion procedure

Khazaee, Meghdad; Banakar, Ahmad; Ghobadian, Barat; Mirsalim, Mojtaba; Minaei, Saeid; Jafari, M; Sharghi, Peyman

doi:10.1177/1475921716652582

Cited by 19 publications

(7 citation statements)

References 54 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When there are many neurons in the hidden layer, a sparsi striction is added, to train the network and extract valuable features. The sparsity l tion is that the processing of the hidden layer neurons is inhibited most of the tim sparsity restriction introduces a cost function [21], denoted by: In Equation (1), y i is the activation value of the hidden layer, W ij is the weight coefficient, b i is the offset vector of the hidden layer, and S(x) represents the activation function. The sigmoid function is employed herein.…”

Section: The Fundamentals Of the Ssaementioning

confidence: 99%

“…The sparsity limitation is that the processing of the hidden layer neurons is inhibited most of the time. The sparsity restriction introduces a cost function [21], denoted by:…”

Section: The Fundamentals Of the Ssaementioning

confidence: 99%

“…Zhang, et al [20], proposed a complete ensemble intrinsic time scale decomposition method, combined with the least squares Support Vector Machine classification method, that was optimized by particle swarm optimization to diagnose and identify faults. Meghdad, et al [21], proposed a data mining technique and a novel data fusion method utilizing an artificial neural network for fault identification. Zhong K, et al [22], proposed a local Fisher discriminant analysis based on the sparse kernel, which effectively improved the accuracy of fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

et al. 2022

View full text Add to dashboard Cite

Due to the relative insufficiencies of conventional time-domain waveform and spectrum analysis in fault diagnosis research, a diesel engine fault diagnosis method based on the Stacked Sparse Autoencoder and the Support Vector Machine is proposed in this study. The method consists of two main steps. The first step is to utilize the Stacked Sparse Autoencoder (SSAE) to reduce the feature dimension of the multi-sensor vibration information; when compared with other dimension reduction methods, this approach can better capture nonlinear features, so as to better cope with dimension reduction. The second step consists of diagnosing faults, implementing the grid search, and K-fold cross-validation to optimize the hyperparameters of the SVM method, which effectively improves the fault classification effect. By conducting a preset failure experiment for the diesel engine, the proposed method achieves an accuracy rate of more than 98%, better engineering application, and promising outcomes.

show abstract

Section: The Fundamentals Of the Ssaementioning

confidence: 99%

“…The sparsity limitation is that the processing of the hidden layer neurons is inhibited most of the time. The sparsity restriction introduces a cost function [21], denoted by:…”

Section: The Fundamentals Of the Ssaementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To this end, with a limited number of measurements at particular nodes of the simulation model (e.g., pressure values at two nodes), the damage scenario should be determined. To solve a classification task with multiple damage scenarios, statistical-and machinelearning-based methods have been developed; for example, Mahalanobis distance (MD), [39][40][41] logistic regression, support vector machine (SVM), 42 artificial neural networks (ANN), 43,44 and convolutional neural networks (CNN). 45,46 In principle, any classifier listed above can be used.…”

Section: Sensor Network Design Analysismentioning

confidence: 99%

Optimal sensor placement to detect ruptures in pipeline systems subject to uncertainty using an Adam-mutated genetic algorithm

Kim

Jung

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

Pipelines in critical engineered facilities, such as petrochemical and power plants, conduct important roles of fire extinguishing, cooling, and related essential tasks. Therefore, failure of a pipeline system can cause catastrophic disaster, which may include economic loss or even human casualty. Optimal sensor placement is required to detect and assess damage so that the optimal amount of resources is deployed and damage is minimized. This paper presents a novel methodology to determine the optimal location of sensors in a pipeline network for real-time monitoring. First, a lumped model of a small-scale pipeline network is built to simulate the behavior of working fluid. By propagating the inherent variability of hydraulic parameters in the simulation model, uncertainty in the behavior of the working fluid is evaluated. Sensor measurement error is also incorporated. Second, predefined damage scenarios are implemented in the simulation model and estimated through a damage classification algorithm using acquired data from the sensor network. Third, probabilistic detectability is measured as a performance metric of the sensor network. Finally, a detectability-based optimization problem is formulated as a mixed integer non-linear programming problem. An Adam-mutated genetic algorithm (AMGA) is proposed to solve the problem. The Adam-optimizer is incorporated as a mutation operator of the genetic algorithm to increase the capacity of the algorithm to escape from the local minimum. The performance of the AMGA is compared with that of the standard genetic algorithm. A case study using a pipeline system is presented to evaluate the performance of the proposed sensor network design methodology.

show abstract

“…Diagnosis techniques for machinery/structural health monitoring based on vibration signals are generally divided into three groups: time domain features, frequency domain features, and time–frequency features. 15 Being simple and interpretable, time domain features have been frequently used for health monitoring in mechanical engineering, 16–20 which are calculated from raw signals without any transformation such as RMS and kurtosis. The main advantage of this group of features is that time domain features are easy and quick in preprocessing without the tasks like filtering, windowing, framing, and transformation.…”

Section: Introductionmentioning

confidence: 99%

Vibration signal–based fault diagnosis in complex structures: A beam-like structure approach

Wang

Jing

2017

Structural Health Monitoring

View full text Add to dashboard Cite

Sensor network–based data-driven fault diagnosis in complex structures using limited prior knowledge is an interesting and hot topic in the literature. In this study, an integrated feature characterization and fuzzy decision method is developed based on a novel beam-like structure approach for fault diagnosis using available limited prior knowledge. Complex structures embedded with vibration sensors can be regarded as some virtual beam-like structures by considering the vibration transmission path from vibration sources to each sensor. The dynamic response of the structures in this vibration transmission path can demonstrate obvious fault features if there is a fault (typically, for example, cracks in connecting rods or around bolts, and bolt-loosening). These fault features can be effectively characterized and efficiently captured and utilized for fault diagnosis with a fuzzy decision method based on the virtual beam-like structure concept. This novel virtual beam-like structure approach needs only limited prior knowledge of the faults and does not require stationary response data. It is also not with respect to a specific structure design and is easy to implement within a sensor network. The effectiveness of the proposed method is well validated in the experiments for fault diagnosis including loosening bolts or cracks around bolts of complex structures such as bolted-base hanging structures in satellites.

show abstract

Fault detection of engine timing belt based on vibration signals using data-mining techniques and a novel data fusion procedure

Cited by 19 publications

References 54 publications

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

Research on Diesel Engine Fault Diagnosis Method Based on Stacked Sparse Autoencoder and Support Vector Machine

Optimal sensor placement to detect ruptures in pipeline systems subject to uncertainty using an Adam-mutated genetic algorithm

Vibration signal–based fault diagnosis in complex structures: A beam-like structure approach

Contact Info

Product

Resources

About