Wavelet based rule for fault detection

Libal, Urszula; Hasiewicz, Zygmunt

doi:10.1016/j.ifacol.2018.09.585

Cited by 6 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the limited size of the public DA dataset, which only contains four types of faults, it is difficult for the fault data to satisfy both the training and testing requirements of the network. Therefore, many current papers use its process simulator to generate the fault data [ 40 , 41 , 42 , 43 ]. However, the selection of fault samples and different sampling methods may lead to unfairness.…”

Section: Resultsmentioning

confidence: 99%

Few-Shot Fault Diagnosis Based on an Attention-Weighted Relation Network

Xue,

Jiang,

Zheng

et al. 2023

Entropy

View full text Add to dashboard Cite

As energy conversion systems continue to grow in complexity, pneumatic control valves may exhibit unexpected anomalies or trigger system shutdowns, leading to a decrease in system reliability. Consequently, the analysis of time-domain signals and the utilization of artificial intelligence, including deep learning methods, have emerged as pivotal approaches for addressing these challenges. Although deep learning is widely used for pneumatic valve fault diagnosis, the success of most deep learning methods depends on a large amount of labeled training data, which is often difficult to obtain. To address this problem, a novel fault diagnosis method based on the attention-weighted relation network (AWRN) is proposed to achieve fault detection and classification with small sample data. In the proposed method, fault diagnosis is performed through the relation network in few-shot learning, and in order to enhance the representativeness of feature extraction, the attention-weighted mechanism is introduced into the relation network. Finally, in order to verify the effectiveness of the method, a DA valve fault dataset is constructed, and experimental validation is performed on this dataset and another benchmark PU rolling bearing fault dataset. The results show that the accuracy of the network on DA is 99.15%, and the average accuracy on PU is 98.37%. Compared with the state-of-the-art diagnosis methods, the proposed method achieves higher accuracy while significantly reducing the amount of training data.

show abstract

Section: Resultsmentioning

confidence: 99%

Few-Shot Fault Diagnosis Based on an Attention-Weighted Relation Network

Xue,

Jiang,

Zheng

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…The algorithm used to construct the add-on model in this study contains a total of three parts: (1) inputting the features of all of the production data obtained from the modified product into the basic model to collect the accuracy rates of the basic model with regard to said data, (2) training and analyzing another RBF-DNN with the production data features of the extended product as the input and the accuracy of the analysis results of the basic model as the output to obtain the key features for add-on model construction, and (3) using the key add-on model features identified in the previous part to construct the add-on model. We next introduce these three parts.…”

Section: Algorithm For Offline Add-on Model Constructionmentioning

confidence: 99%

“…Various product fault detection systems exist. For instance, Koscielny et al [1] and Libal and Hasiewicz [2] performed fault detection in sugar factories using fuzzy neural networks and a binary classification model, respectively. Liu et al [3] developed a fault detection system for textile products based on the Pearson correlation coefficient and neural networks.…”

Section: Introductionmentioning

confidence: 99%

“…The basic model determines the quality of the basic product, whereas the add-on model assesses the quality of the parts where the new product differs. (2) Existing product fault detection systems use all possible features for modeling; we propose identifying key features that can present product faults before establishing the fault detection model. Figure 2a displays a schematic of the first approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Transfer Learning and Radial Basis Function Deep Neural Network Feature Extraction to Upgrade Existing Product Fault Detection Systems for Industry 4.0: A Case Study of a Spring Factory

Loh,

Chen,

2024

Applied Sciences

View full text Add to dashboard Cite

In the era of Industry 3.0, product fault detection systems became important auxiliary systems for factories. These systems efficiently monitor product quality, and as such, substantial amounts of capital were invested in their development. However, with the arrival of Industry 4.0, high-volume low-mix production modes are gradually being replaced by low-volume high-mix production modes, reducing the applicability of existing systems. The extent of investment has prompted factories to seek upgrades to tailor existing systems to suit new production modes. In this paper, we propose an approach to upgrading based on the concept of transfer learning. The key elements are (1) using a framework with a basic model and an add-on model rather than fine-tuning parameters and (2) designing a radial basis function deep neural network (RBF-DNN) to extract important features to construct the basic and add-on models. The effectiveness of the proposed approach is verified using real-world data from a spring factory.

show abstract

“…To extract valuable features, DTCWT is a suitable method for analyzing motor signals to provide features in the timefrequency domain under diferent speed and load conditions. DTCWT's work is to decompose the signal into a set of (detailed and approximate) subcomponents [6,7].…”

Section: Introductionmentioning

confidence: 99%

Aircraft Actuator Performance Analysis Based on Dynamic Neural Network

Abed

2023

Journal of Engineering

View full text Add to dashboard Cite

Monitoring the condition of the aircraft actuators in various operating and environmental circumstances, this paper presents a method for measuring the surface roughness of aircraft actuators. The proposed method starts with the current and vibration signal as failure indicators and a dual-tree complex wavelet transformation (DTCWT) to generate the necessary features. Time-delay neural networks (TDNNs) have been developed for real-time performance monitoring to categorize problems and determine their severity. The simulation results show that the suggested method can accurately identify various faults.

show abstract

Wavelet based rule for fault detection

Cited by 6 publications

References 31 publications

Few-Shot Fault Diagnosis Based on an Attention-Weighted Relation Network

Few-Shot Fault Diagnosis Based on an Attention-Weighted Relation Network

Using Transfer Learning and Radial Basis Function Deep Neural Network Feature Extraction to Upgrade Existing Product Fault Detection Systems for Industry 4.0: A Case Study of a Spring Factory

Aircraft Actuator Performance Analysis Based on Dynamic Neural Network

Contact Info

Product

Resources

About