Abstract
In order to realize the fault diagnosis of the polyvinyl chloride (PVC) polymerization kettle reactor, a rough set (RS)–probabilistic neural networks (PNN) fault diagnosis strategy is proposed. Firstly, through analysing the technique of the PVC polymerization reactor, the mapping between the polymerization process data and the fault modes is established. Then, the rough set theory is used to tackle the input vector of PNN so as to reduce the network dimensionality and improve the training speed of PNN. Shuffled frog leaping algorithm (SFLA) is adopted to optimize the smoothing factor of PNN. The fault pattern classification of polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the fault diagnosis simulation experiments are conducted by combining with the industrial on-site historical datum of polymerization kettle, and the results show that the RS–PNN fault diagnosis strategy is effective.
Highlights
Polyvinyl chloride (PVC) is one of the five largest thermoplastic synthetic resins, and its production is second only to polyethylene (PE) and polypropylene (PP)
For the fault diagnosis of the large-scale polyvinyl chloride (PVC) polymerization reactor, a fault diagnosis strategy of the polymerization reactor based on rough set–probabilistic neural networks optimized by shuffled frog leaping algorithm is proposed
Assume D is the decision attribute in accordance with the direct reasons of the faults, that is to say D = 0 stands for the normal working conditions of the polymerization kettle, D = 1 stands for the motor fault, D = 2 stands for the reducer fault, D = 3 stands for gland-shaft fault of the polymerization machine seal and D = 4 stands for the fault of polymerize component [3]
Summary
Polyvinyl chloride (PVC) is one of the five largest thermoplastic synthetic resins, and its production is second only to polyethylene (PE) and polypropylene (PP). The PNN results were compared with the results of the multilayer and learning vector quantization neural networks focusing on MM’s disease diagnosis and using same database It was observed the PNN is the best classification with 96.30% accuracy obtained via three-fold cross-validation. The shuffled frog leaping algorithm (SFLA) is used to optimize the smoothing factor σ in order to accelerate the convergence speed of the algorithm, increase the fault diagnosis accuracy of PNN. For the fault diagnosis of the large-scale PVC polymerization reactor, a fault diagnosis strategy of the polymerization reactor based on rough set–probabilistic neural networks optimized by shuffled frog leaping algorithm is proposed.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
