Two-stage prediction of machinery fault trend based on deep learning for time series analysis

Xu, Hao; Ma, Ruizhe; Li, Yan; Ma, Zongmin

doi:10.1016/j.dsp.2021.103150

Cited by 23 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The IMS dataset does not have a detailed true label of the degradation period and specific failure of the bearing. Therefore, according to the labeling method in [ 17 , 24 ], the threshold of each stage should be set according to actual needs.In this simulation, the root mean square (RMS) features of the 20,480 vibration signals collected per second from each sensor were first extracted. Then, expertise was involved in labeling the degradation period, which is shown in Figure 4 and Table 2 .…”

Section: Validating the Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

Peng

Zhang

et al. 2022

Entropy

View full text Add to dashboard Cite

In order to reduce maintenance costs and avoid safety accidents, it is of great significance to carry out fault prediction to reasonably arrange maintenance plans for rotating mechanical equipment. At present, the relevant research mainly focuses on fault diagnosis and remaining useful life (RUL) predictions, which cannot provide information on the specific health condition and fault types of rotating mechanical equipment in advance. In this paper, a novel three-stage fault prediction method is presented to realize the identification of the degradation period and the type of failure simultaneously. Firstly, based on the vibration signals from multiple sensors, a convolutional neural network (CNN) and long short-term memory (LSTM) network are combined to extract the spatiotemporal features of the degradation period and fault type by means of the cross-entropy loss function. Then, to predict the degradation trend and the type of failure, the attention-bidirectional (Bi)-LSTM network is used as the regression model to predict the future trend of features. Furthermore, the predicted features are given to the support vector classification (SVC) model to identify the specific degradation period and fault type, which can eventually realize a comprehensive fault prediction. Finally, the NSF I/UCR Center for Intelligent Maintenance Systems (IMS) dataset is used to verify the feasibility and efficiency of the proposed fault prediction method.

show abstract

Section: Validating the Proposed Methodsmentioning

confidence: 99%

“…used a neural network model to predict the future state of a rolling bearing [ 16 ]. In [ 17 ], Xu H et al. used two models: a regression model and a classification model, which could not only predict the stage of degradation, but also classify the type of fault that would occur.…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

Peng

Zhang

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…Equations ( 7)- (11) give the required backward pass equations of the whole architecture. The corresponding stochastic gradient update equations are ∆φ…”

Section: The End-to-end Modelmentioning

confidence: 99%

“…Thanks to the feedback connections to preserve the history in memory [10], they are widely used in sequential learning tasks. Nevertheless, a fully connected layer usually employed in the final layer of these hidden layers often hinders their regression ability (e.g., in [11], au-thors use an attention layer for more accurate judgments). An alternative to these deep learning models is the tree-based models that learn hierarchical relations in the data by splitting the input space and then fitting different models to each split [9].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Framework for Sequential Data Prediction with End-to-End Optimization

Aydın¹,

Kozat²

2022

Preprint

View full text Add to dashboard Cite

We investigate nonlinear prediction in an online setting and introduce a hybrid model that effectively mitigates, via an end-to-end architecture, the need for hand-designed features and manual model selection issues of conventional nonlinear prediction/regression methods. In particular, we use recursive structures to extract features from sequential signals, while preserving the state information, i.e., the history, and boosted decision trees to produce the final output. The connection is in an end-to-end fashion and we jointly optimize the whole architecture using stochastic gradient descent, for which we also provide the backward pass update equations. In particular, we employ a recurrent neural network (LSTM) for adaptive feature extraction from sequential data and a gradient boosting machinery (soft GBDT) for effective supervised regression. Our framework is generic so that one can use other deep learning architectures for feature extraction (such as RNNs and GRUs) and machine learning algorithms for decision making as long as they are differentiable. We demonstrate the learning behavior of our algorithm on synthetic data and the significant performance improvements over the conventional methods over various real life datasets. Furthermore, we openly share the source code of the proposed method to facilitate further research.

show abstract

“…The first category is the two-stage predicting category, which aims to improve the performance of the prediction task by decomposing the application task into two sequential tasks. Few studies [6,27,28] have explored the two-stage predicting category. To detect defective rolling element bearings, Yiakopoulos et al [6] presented a two-stage method, where the first task was to detect the existence of a bearing fault while the second stage task classified the type of detected anomaly.…”

Section: Introductionmentioning

confidence: 99%

Efficient Feature Learning Approach for Raw Industrial Vibration Data Using Two-Stage Learning Framework

Tnani

Subarnaduti

Diepold

2022

Sensors

View full text Add to dashboard Cite

In the last decades, data-driven methods have gained great popularity in the industry, supported by state-of-the-art advancements in machine learning. These methods require a large quantity of labeled data, which is difficult to obtain and mostly costly and challenging. To address these challenges, researchers have turned their attention to unsupervised and few-shot learning methods, which produced encouraging results, particularly in the areas of computer vision and natural language processing. With the lack of pretrained models, time series feature learning is still considered as an open area of research. This paper presents an efficient two-stage feature learning approach for anomaly detection in machine processes, based on a prototype few-shot learning technique that requires a limited number of labeled samples. The work is evaluated on a real-world scenario using the publicly available CNC Machining dataset. The proposed method outperforms the conventional prototypical network and the feature analysis shows a high generalization ability achieving an F1-score of 90.3%. The comparison with handcrafted features proves the robustness of the deep features and their invariance to data shifts across machines and time periods, which makes it a reliable method for sensory industrial applications.

show abstract

Two-stage prediction of machinery fault trend based on deep learning for time series analysis

Cited by 23 publications

References 26 publications

Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

A Hybrid Framework for Sequential Data Prediction with End-to-End Optimization

Efficient Feature Learning Approach for Raw Industrial Vibration Data Using Two-Stage Learning Framework

Contact Info

Product

Resources

About