Abstract
This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.
Highlights
The digital transformation is recognised as the most important driver in the era of Industry 4.0
PERFORMANCE EVALUATIONS the proposed cumulative uncertainty reduction network (CURNet) architecture along with the recursive gradient descent (RGD) algorithm is evaluated using a large volume of real-time sensory data collected from the chemical plant, which is equipped with the necessary hardware and software components illustrated in the cyber-physical systems (CPS) in Fig. 1, and integrated with essential functions to perform data measurements and storage
In order to deal with challenging fault prediction problems in wireless sensor network (WSN) embedded industrial CPS, we have developed a novel and effective end-to-end deep learning network named CURNet with its own novel learning algorithm named RGD
Summary
The digital transformation is recognised as the most important driver in the era of Industry 4.0. THE CPS MODEL DESIGN in the CPS system design, there are five modules that constitute this envisioned infrastructure as shown in Fig. 1: the holistic system models and cooperative control, massive connectivity and resilient network communication, machine learning-based fault detection and prediction, an intelligent adaptive decision making framework, and a virtual reality system for visualization This modular infrastructure represents the complexity of industrial processes with a large number of interconnected units operating in extreme environments, which includes hazardous gas diffusion and material leakage, over-pressured tanks, power outage, relating to a paramount health and safety practice. Both predictors are software (Python) defined and take input data streams into computation as soon as they arrive to minimize the processing latency and maintain continuous real-time predictions
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
