Deep-Learning Method Based on 1D Convolutional Neural Network for Intelligent Fault Diagnosis of Rotating Machines

Alonso-Valerdi, Luz María; Ibarra-Zárate, David I.

doi:10.3390/app12042158

Cited by 24 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To solve this problem, 1D CNNs were proposed [35,36,37,38,39], and quickly became state-of-the-art in applications such as: biomedical data classification and early diagnosis, structural health monitoring, anomaly detection and identification in power electronics and electrical motor fault detection. In the area of fault detection in rotating machines, some studies involving 1D CNN are [40,41,42,43,44,45].…”

Section: D Convolutional Neural Network (1d Cnn)mentioning

confidence: 99%

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Brito¹,

Brito²,

Duarte³

2022

Preprint

View full text Add to dashboard Cite

Due to the growing interest for increasing productivity and cost reduction in industrial environment, new techniques for monitoring rotating machinery are emerging. Artificial Intelligence (AI) is one of the approaches that has been proposed to analyze the collected data (e.g., vibration signals) providing a diagnosis of the asset's operating condition. It is known that models trained with labeled data (supervised) achieve excellent results, but two main problems make their application in production processes difficult: (i) impossibility or long time to obtain a sample of all operational conditions (since faults seldom happen) and (ii) high cost of experts to label all acquired data. Another limitating factor for the applicability of AI approaches in this context is the lack of interpretability of the models (black-boxes), which reduces the confidence of the diagnosis and trust/adoption from users. To overcome these problems, a new generic and interpretable approach for classifying faults in rotating machinery based on transfer learning from augmented synthetic data to real rotating machinery is here proposed, namelly FaultD-XAI (Fault Diagnosis using eXplainable AI). To provide scalability using transfer learning, synthetic vibration signals are created mimicking the characteristic behavior of failures in operation. The application of Gradient-weighted Class Activation Mapping (Grad-CAM) with 1D Convolutional Neural Network (1D CNN) allows the interpretation of results, supporting the user in decision making and increasing diagnostic confidence. The proposed approach not only obtained promising diagnostic performance, but was also able to learn characteristics used by experts to identify conditions in a source domain and apply them in another target domain. The experimental results obtained on three datasets containing different mechanical faults suggest the method offers a promising approach on exploiting transfer learning, synthetic data and explainable artificial intelligence for fault diagnosis. Lastly, to guarantee reproducibility and foster research in the field, the developed dataset is made publicly available.

show abstract

Section: D Convolutional Neural Network (1d Cnn)mentioning

confidence: 99%

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Brito¹,

Brito²,

Duarte³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It has recently been proposed and has good performance levels in several applications, speci cally for one-dimensional signals. These include fault detection [14] [15] [16] [17], sensor processing [18], personalized biomedical data classi cation and early diagnosis [19] [20], waste sorting at source based on acoustic data [13], structural health monitoring [21], application on near-infrared spectroscopy [22] [22], anomaly detection and identi cation in power electronics [23], and radar signals classi cation [24] [25]. Another signi cant advantage is the possibility of real-time and low-cost hardware implementation due to the simple and compact 1D CNN con guration that only performs multiplication and scalar addition.…”

Section: Introductionmentioning

confidence: 99%

Improving 1d Convolutional Neural Network (1d Cnn) Performance in Processing Tabular Datasets Using Principal Component Analysis

Surendro

Rachmatullah

Santoso

2022

Preprint

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) has been used significantly in various applications to process data that have spatial or temporal relationship, such as image and video recognition, medical image analysis, natural language processing, and speech recognition. This study used CNN to process tabular datasets with unknown spatial and temporal relationship between attributes. It used a principal component analysis (PCA) process to obtain the relationship between the attributes, which are connected based on their variance values and expected to provide a spatial relationship. Therefore, after being transformed with PCA, the dataset remains in the tabular form but between attributes already have a relationship. Because the transformed dataset is still a one-dimensional dataset, the CNN model used is 1D CNN which is more suitable for processing one-dimensional data. To compare the performance of 1D CNN against the original dataset and the dataset that has been transformed with PCA, the Iris and Covertype datasets were used. By using the Wilcoxon difference test, it turns out that two datasets that have been transformed with PCA provide better performance than using the original dataset. Furthermore, the PCA implementation to the NCI-60 dataset using 1D CNN performed better compared to previous research. This research has an accuracy of 83.34%. The previous research transformed the dataset into a two-dimensional image classified using 2D CNN at an accuracy of 75.4%.

show abstract

“…To extract the text extraction using Word2vec and build the prior-knowledge CNN classifier with Cloud Similarity Measurement (CSM) improved the accuracy of aircraft fault diagnosis. J. Chuya-Sumba et al [11] proposed a 1D CNN model that works on raw signals without any need of prerequisite analysis. G. Nassajian and S. Balochian [12] proposed a multi-model estimation and fault detection method using RBF neural network for a nonlinear system of unknown time continuous fractional order.…”

Section: Introductionmentioning

confidence: 99%

A Novel Mechanical Fault Diagnosis Based on Transfer Learning with Probability Confidence Convolutional Neural Network Model

Lin

Wang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

For fault diagnosis, convolutional neural networks (CNN) have been performing as a data-driven method to identify mechanical fault features in forms of vibration signals. However, because of CNN’s ineffective and inaccurate identification of unknown fault categories, we propose a model based on transfer learning with probability confidence CNN (TPCCNN) to model the fault features of rotating machinery for fault diagnosis. TPCCNN includes three major modules: (1) feature engineering to perform a series of data pre-processing and feature extraction; (2) transferring learning features of heterogeneous datasets for different datasets to have better generality in model training and reduce the time for modeling and parameter tuning; and (3) building a PCCNN model to classify known and unknown fault categories. In addition to solving the problem of an imbalanced sample size, TPCCNN self-learns and retrains by iterating with unknown classes to the original model. This model is verified with the use of the open-source datasets CWRU and Ottawa. The experimental results showing the feature transfer of heterogeneous datasets are of average accuracy rates of 99.2% and 93.8% respectively for known and unknown categories, and TPCCNN is then proven effectively in training heterogeneous datasets. Likewise, similar feature sets can also be applied to reduce the training of predicting models by 34% and 68% of the time.

show abstract

Deep-Learning Method Based on 1D Convolutional Neural Network for Intelligent Fault Diagnosis of Rotating Machines

Cited by 24 publications

References 35 publications

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Improving 1d Convolutional Neural Network (1d Cnn) Performance in Processing Tabular Datasets Using Principal Component Analysis

A Novel Mechanical Fault Diagnosis Based on Transfer Learning with Probability Confidence Convolutional Neural Network Model

Contact Info

Product

Resources

About