Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration Signal Input

Pipe structures are at the base of the entire industry. In the industry structure, heat and vibration are transmitted in each pipe. The minimum distance between each pipe is significant to the security. The assembly error and the deformation of the pipeline positions after multiple runs are significant problems. The reconstruction of the multi-pipe system is a critical technical difficulty in the complex tube system. In this paper, a new method for the multi-pipes structure inspection is presented. Images of the tube system are acquired from several positions. The photogrammetry technology calculates positions, and the necessary coordination of the structure is reconstructed. A convolution neural network is utilized to detect edges of tube-features. The new algorithm for tube identification and reconstruction is presented to extract the tube feature in the image and reconstruct the 3D parameters of all tubes in a multi-pipes structure. The accuracy of the algorithm is verified by simulation experiments. An actual engine of the aircraft is measured to verify the proposed method.

Section: Methodsmentioning

confidence: 99%

A Novel Method for the Complex Tube System Reconstruction and Measurement

Guo

Yuan

et al. 2021

“…By observing the behavior of training accuracy, and loss function values in several experiments, this value has been decided for avoiding the overfitting problem. Similarly, the number of kernels of the proposed MTL-CNN architecture is optimized utilizing grid search, as preliminary experiments demonstrate that the fluctuating number of kernels affects the final classification performance [ 66 ].…”

Section: Proposed Methodsologymentioning

confidence: 99%

A Multitask-Aided Transfer Learning-Based Diagnostic Framework for Bearings under Inconsistent Working Conditions

Hasan

Sohaib

Kim

2020

Rolling element bearings are a vital part of rotating machines and their sudden failure can result in huge economic losses as well as physical causalities. Popular bearing fault diagnosis techniques include statistical feature analysis of time, frequency, or time-frequency domain data. These engineered features are susceptible to variations under inconsistent machine operation due to the non-stationary, non-linear, and complex nature of the recorded vibration signals. To address these issues, numerous deep learning-based frameworks have been proposed in the literature. However, the logical reasoning behind crack severities and the longer training times needed to identify multiple health characteristics at the same time still pose challenges. Therefore, in this work, a diagnosis framework is proposed that uses higher-order spectral analysis and multitask learning (MTL), while also incorporating transfer learning (TL). The idea is to first preprocess the vibration signals recorded from a bearing to look for distinct patterns for a given fault type under inconsistent working conditions, e.g., variable motor speeds and loads, multiple crack severities, compound faults, and ample noise. Later, these bispectra are provided as an input to the proposed MTL-based convolutional neural network (CNN) to identify the speed and the health conditions, simultaneously. Finally, the TL-based approach is adopted to identify bearing faults in the presence of multiple crack severities. The proposed diagnostic framework is evaluated on several datasets and the experimental results are compared with several state-of-the-art diagnostic techniques to validate the superiority of the proposed model under inconsistent working conditions.

“…Defining the model architecture can be difficult since there are multiple architecture options available and researcher does not know optimal structure or hyper-parameters values. In this research, authors perform additional modifications in input size as well as in MC-DCNN architecture previously presented in [31] to enable intelligent fault diagnosis and optimization of both network structure and hyper-parameters. Machine learning algorithm transforms a problem that needs to be solved into an optimization problem that uses different optimization methods.…”

Section: Related Workmentioning

confidence: 99%

“…1D CNN techniques for induction motors [ 25 , 26 ], pumps [ 27 ] and rolling element bearings [ 28 , 29 ] are developed. Further on, the authors of [ 30 ] presented multi-channels 1D CNN (MC-DCNN) for human activity classification that is modified by [ 31 ] for 3 axis vibration data input with input size of 6400 × 1 × 3. This type of CNN is visualized in Figure 1 .…”

Section: Introductionmentioning

confidence: 99%

Intelligent Fault Diagnosis of Rotary Machinery by Convolutional Neural Network with Automatic Hyper-Parameters Tuning Using Bayesian Optimization

Kolar

Lisjak

Pająk

et al. 2021

Self Cite

Intelligent fault diagnosis can be related to applications of machine learning theories to machine fault diagnosis. Although there is a large number of successful examples, there is a gap in the optimization of the hyper-parameters of the machine learning model, which ultimately has a major impact on the performance of the model. Machine learning experts are required to configure a set of hyper-parameter values manually. This work presents a convolutional neural network based data-driven intelligent fault diagnosis technique for rotary machinery which uses model with optimized hyper-parameters and network structure. The proposed technique input raw three axes accelerometer signal as high definition 1-D data into deep learning layers with optimized hyper-parameters. Input is consisted of wide 12,800 × 1 × 3 vibration signal matrix. Model learning phase includes Bayesian optimization that optimizes hyper-parameters of the convolutional neural network. Finally, by using a Convolutional Neural Network (CNN) model with optimized hyper-parameters, classification in one of the 8 different machine states and 2 rotational speeds can be performed. This study accomplished the effective classification of different rotary machinery states in different rotational speeds using optimized convolutional artificial neural network for classification of raw three axis accelerometer signal input. Overall classification accuracy of 99.94% on evaluation set is obtained with the CNN model based on 19 layers. Additionally, more data are collected on the same machine with altered bearings to test the model for overfitting. Result of classification accuracy of 100% on second evaluation set has been achieved, proving the potential of using the proposed technique.