Abstract

Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in chemical processes. A deep neural network (DNN) with novel active learning for inducing chemical fault diagnosis is presented in this study. It is a method using large amount of chemical sensor data, which is a combination of deep learning and active learning criterion to target the difficulty of consecutive fault diagnosis. DNN with deep architectures, instead of shallow ones, could be developed through deep learning to learn a suitable feature representation from raw sensor data in an unsupervised manner using stacked denoising auto-encoder (SDAE) and work through a layer-by-layer successive learning process. The features are added to the top Softmax regression layer to construct the discriminative fault characteristics for diagnosis in a supervised manner. Considering the expensive and time consuming labeling of sensor data in chemical applications, in contrast to the available methods, we employ a novel active learning criterion for the particularity of chemical processes, which is a combination of Best vs. Second Best criterion (BvSB) and a Lowest False Positive criterion (LFP), for further fine-tuning of diagnosis model in an active manner rather than passive manner. That is, we allow models to rank the most informative sensor data to be labeled for updating the DNN parameters during the interaction phase. The effectiveness of the proposed method is validated in two well-known industrial datasets. Results indicate that the proposed method can obtain superior diagnosis accuracy and provide significant performance improvement in accuracy and false positive rate with less labeled chemical sensor data by further active learning compared with existing methods.

Highlights

  • Chemical industries have always been concerned about methods for reducing the risk of accidents because they may commonly occur in extreme environments, such as extraordinarily high temperature or pressure, which may result in public damage and large economic losses [1]

  • This study presents an active learning method, which is applied to deep neural network (DNN) based on stacked denoising auto-encoder (SDAE) for further fine-tuning

  • The results above show that the proposed method obtains significantly better diagnosis accuracies and stability than the methods with shallow architectures and back propagation neural network (BPNN)-based method

Read more

Summary

Introduction

Chemical industries have always been concerned about methods for reducing the risk of accidents because they may commonly occur in extreme environments, such as extraordinarily high temperature or pressure, which may result in public damage and large economic losses [1]. Modern chemical processes have become more complex with the development of science and technology, and large amounts of data are being produced. Sensors 2016, 16, 1695 fault diagnosis method to monitor the entire process and detect the fault in time by mining potential information from the large amounts of sensor data collected. Three types of methods are currently used in fault diagnosis from data processing perspective, namely model-based, signal-based and knowledge-based methods [5]. Model-based methods estimate the output of the system by constructing a model and achieving fault diagnosis through the residual between estimates and measurements Methods of this type, such as parameter estimation and parity space methods, provide in-depth analysis for the dynamic of systems [6,7]. The manually extracted feature has a limitation in terms of application, that is, it is only suitable for specific diagnosis issues, limiting the application in complex chemical systems [8]

Methods
Findings
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.