An Improved Wide-Kernel CNN for Classifying Multivariate Signals in Fault Diagnosis

Hoogen, J.O.D. van den; Bloemheuvel, Stefan; Atzmueller, Martin

doi:10.1109/icdmw51313.2020.00046

Cited by 18 publications

(20 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The design of a CNN and the quality of the data have a significant impact on its classification performance, for instance, sensor signals from industrial machinery regularly contain significant levels of noise. Previous work showed the great performance of using a wide-kernel in the first convolutional layer, followed by smaller kernels in the followup layers, for detecting faults and classifying conditions of rotating equipment [10,11].…”

Section: Methodsmentioning

confidence: 99%

“…Similar to our previous proposed WDTCNN model [11], the adaptive wide-kernel CNN (A-WCNN) contains five convolutional layers followed by two fully connected layers; however, the A-WCNN is able to adapt its first wide-kernel layer based on the dimensionality of the input data. So, this hybrid version can be easily deployed on different datasets with other dimensionalities, without having to manually adjust the architecture of the model.…”

Section: Adaptive Wide-kernel Cnn (A-wcnn)mentioning

confidence: 99%

“…This paper investigates the use of deep learning in the context of fault detection of rolling bearing elements and builds on our earlier research [11], exploring the usage of one-dimensional CNNs for classifying multivariate signals based on data derived from rotating machines. In particular, we propose several architectures that are built on the wide-kernel framework developed by [10].…”

Section: Introductionmentioning

confidence: 99%

“…We propose a method for implementing an adaptive wide-kernel in the first convolutional layer that is able to transform any form of sequential sensor data without any dimensionality reduction; therefore, abiding the principles of a wide-kernel convolutional layer as proposed in [10,11]. We implement this in two models.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Classifying Multivariate Signals in Rolling Bearing Fault Detection Using Adaptive Wide-Kernel CNNs

2021

View full text Add to dashboard Cite

With the developments in improved computation power and the vast amount of (automatic) data collection, industry has become more data-driven. These data-driven approaches for monitoring processes and machinery require different modeling methods focusing on automated learning and deployment. In this context, deep learning provides possibilities for industrial diagnostics to achieve improved performance and efficiency. These deep learning applications can be used to automatically extract features during training, eliminating time-consuming feature engineering and prior understanding of sophisticated (signal) processing techniques. This paper extends on previous work, introducing one-dimensional (1D) CNN architectures that utilize an adaptive wide-kernel layer to improve classification of multivariate signals, e.g., time series classification in fault detection and condition monitoring context. We used multiple prominent benchmark datasets for rolling bearing fault detection to determine the performance of the proposed wide-kernel CNN architectures in different settings. For example, distinctive experimental conditions were tested with deviating amounts of training data. We shed light on the performance of these models compared to traditional machine learning applications and explain different approaches to handle multivariate signals with deep learning. Our proposed models show promising results for classifying different fault conditions of rolling bearing elements and their respective machine condition, while using a fairly straightforward 1D CNN architecture with minimal data preprocessing. Thus, using a 1D CNN with an adaptive wide-kernel layer seems well-suited for fault detection and condition monitoring. In addition, this paper clearly indicates the high potential performance of deep learning compared to traditional machine learning, particularly in complex multivariate and multi-class classification tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Adaptive Wide-kernel Cnn (A-wcnn)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Classifying Multivariate Signals in Rolling Bearing Fault Detection Using Adaptive Wide-Kernel CNNs

2021

View full text Add to dashboard Cite

show abstract

“…According to the classical definition of [32], "an outlier is an observation that differs so much from other observations as to arouse suspicion that it was generated by a different mechanism". Here, there exists a variety of techniques, e.g., using subspace clustering [33,34], tensor factorization [35], community detection [36], adapting deep learning (classification/condition monitoring) techniques [37][38][39], or graph/signal processing methods [40,41]. Identifying anomalies in network data is a prominent novel research area.…”

Section: Anomaly Detectionmentioning

confidence: 99%

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

Maulana

Atzmueller

2021

Applied Sciences

View full text Add to dashboard Cite

Anomaly detection in complex networks is an important and challenging task in many application domains. Examples include analysis and sensemaking in human interactions, e.g., in (social) interaction networks, as well as the analysis of the behavior of complex technical and cyber-physical systems such as suspicious transactions/behavior in financial or routing networks; here, behavior and/or interactions typically also occur on different levels and layers. In this paper, we focus on detecting anomalies in such complex networks. In particular, we focus on multi-layer complex networks, where we consider the problem of finding sets of anomalous nodes for group anomaly detection. Our presented method is based on centrality-based many-objective optimization on multi-layer networks. Starting from the Pareto Front obtained via many-objective optimization, we rank anomaly candidates using the centrality information on all layers. This ranking is formalized via a scoring function, which estimates relative deviations of the node centralities, considering the density of the network and its respective layers. In a human-centered approach, anomalous sets of nodes can then be identified. A key feature of this approach is its interpretability and explainability, since we can directly assess anomalous nodes in the context of the network topology. We evaluate the proposed method using different datasets, including both synthetic as well as real-world network data. Our results demonstrate the efficacy of the presented approach.

show abstract

Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture

Schoenke¹,

Aschenbruck

Interdonato

et al. 2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

We present a position paper about our concept for an artificial intelligence (AI) and data streaming platform for the agricultural sector. The goal of our project is to support agroecology in terms of carbon farming and biodiversity protection by providing an AI and data streaming platform called Gaia-AgStream that accelerates the adoption of AI in agriculture and is directly usable by farmers as well as agricultural companies in general. The technical innovations we propose focus on smart sensor networks, unified uncertainty management, explainable AI, root cause analysis and hybrid AI approaches. Our AI and data streaming platform concept contributes to the European open data infrastructure project Gaia-X in terms of interoperability for data and AI models as well as data sovereignty and AI infrastructure. Our envisioned platform and the developed AI components for carbon farming and biodiversity will enable farmers to adopt sustainable and resilient production methods while establishing new and diverse revenue streams by monetizing carbon sequestration and AI ready data streams. The open and federated platform concept allows to bring together research, industry, agricultural start-ups and farmers in order to form sustainable innovation networks. We describe core concepts and architecture of our proposed approach in these contexts, outline practical use cases for our platform and finally outline challenges and future prospects.

show abstract

An Improved Wide-Kernel CNN for Classifying Multivariate Signals in Fault Diagnosis

Cited by 18 publications

References 35 publications

Classifying Multivariate Signals in Rolling Bearing Fault Detection Using Adaptive Wide-Kernel CNNs

Classifying Multivariate Signals in Rolling Bearing Fault Detection Using Adaptive Wide-Kernel CNNs

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture

Contact Info

Product

Resources

About