Abstract
We looked at the background of fault-detection and fault-tolerant control algorithms to propose a new high efficiency one with a focus on Tennessee Eastman process through fuzzy-based neural network representation. Due to the fact that the open-loop system may not be stabilized, an advanced control strategy to generate proper control signals needs to be designed. At first, to detect and identify the fault, data preprocessing theories have been considered. Based upon the matter disclosed, to provide a reliable decision-maker block, fusion classifier idea has been realized. For this one, raw data, time, and frequency characteristics are divided into various classification tools and finally the obtained knowledge combination regarding each one of them is adopted. It should be noted that the proposed implementation tools are taken into real consideration as the fuzzy-based neural network representation. Subsequently, the fault-tolerant control approach based on local controller regulation in case of each fault occurrence has been researched, which the investigated outcomes emphasize the effectiveness of the approach proposed here.
Highlights
The production and process industries have always been under great pressure due to discussions such as produce high-quality productions, product rejection rates, observe safety strict and precise issues, and environmental rules
Fault-detection and identification structure obtained the base of data, deals with the problem to be used in control structure
A new fault-detection structure is designed in this investigation for extensive Tennessee Eastman process system through fuzzy-neural fusion classifier approach to adjust the process output as studied
Summary
The production and process industries have always been under great pressure due to discussions such as produce high-quality productions, product rejection rates, observe safety strict and precise issues, and environmental rules. View, implement of data preprocessing theories such as extract time and frequency characteristics and the use of conversions to reduce the problem size and study it in a different view are taken into real consideration To do this, it is independent of raw data, time domain conversion includes PDA, LDA, and wavelet frequency domain separately in the fuzzy-neural networks. The importance of this research is from actual data of the TE process and complete simulation in MATLAB to detect four faults (which there is concurrency possibility for two of them) and five different working modes in the system as real-time by the fuzzy-neural fusion classifier and compare classification results with the presented sample in other reliable materials [18,19,20,21,22,23,24,25,26,27,28,29,30]. “The proposed approach” is the description of the proposed approach and “Simulation results” focuses on the simulation results
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.
