PlumX Metrics
Embed PlumX Metrics

Optimization of Palm Oil Mill Effluent (POME) Solubilization Using Linguistic Fuzzy Logic and Machine Learning Techniques

Springer Proceedings in Mathematics and Statistics, ISSN: 2194-1017, Vol: 413, Page: 225-242
2023
  • 0
    Citations
  • 0
    Usage
  • 3
    Captures
  • 0
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

Conference Paper Description

The continuous hike in the price of the edible vegetable oil has directly impacted upon the price growth of the palm oil. In this palm oil production, Indonesia and Malaysia are in top leading position at present. It is found that an increase in palm oil mill setup is radically increasing the produce of effluent discharge which is a severe threat to our environment. Hence to maintain the balance of our already affected ecosystem, the proper treatment of this residual product is becoming the dire need of the hour. The conventional method used for solubilization of palm oil mill effluent (POME) is thermal alkaline pre-treatment. In this paper, the linguistic fuzzy logic (LFL) and machine learning (ML) techniques have been used to analyze the data, and type-2 fuzzy logic controller (T2FLC) has been used to optimize the solubilization of POME. The effect of reaction time, NaOH concentration, and temperature on the solubilization has been evaluated. From the investigation of the surface plot, which developed in T2FLC environment, it has been observed that NaOH concentration has a significant effect on the solubilization of POME. The prediction efficiency of T2FLC then has been compared with T1FLC and RSM. By evaluating some statistical analyses, the sensitivity and validity of the proposed model have finally been measured.

Bibliographic Details

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know