Soft Sensing Modeling Based on Extreme Learning Machine for Biochemical Processes

摘要: An improved extreme learning machine (ELM) method was proposed for soft sensing modeling, and the disadvantage of profuse hidden nodes in ELM network overcome. By adding a kind sorting neurons into layer single-hidden-layer feed forward neural (SLFN), new SLFN structure proposed. A to solve problem number difference sample sorts, then same could be used fit different samples. this way, decreased, model simplified, on-line computation speed increased markedly. The provided approach build models, it successfully applied modeling thalli concentration Nosiheptied fermentation process realize prediction concentration.