Culture Conditions Optimization of Hyaluronic Acid Production Based on GP and QPSO Algorithms

Abstract

This study aimed to optimize the culture conditions (agitation speed, aeration rate and stirrer number) of hyaluronic acid production by Streptococcus zooepidemicus. Two optimization algorithms were used for comparison: response surface methodology (RSM) and genetic programming coupling Quantum-behaved particle swarm optimization algorithm (GP-QPSO). In GP -QPSO approach, GP is employed to model the microbial HA production and QPSO algorithm is used to find out the optimal culture conditions with the established GP estimator as the objective function. The maximum predicted value of HA production by RSM and GP-QPSO was 5.27 and 5.57 g/l, respectively. Here though both RSM and GP-QPSO approach provided good predictions, yet the proposed GP-QPSO method showed a clear superiority over RSM for both data fitting and optimization capabilities

Aging model development based on multidisciplinary parameters for lithium‐ion batteries

“…Li et al applied random forest regression (RFR) for the capacity estimation of batteries . He et al performed the prognostic the variety of the capacity of lithium‐ions batteries by using Bayesian Monte Carlo method (BMCM) …”

“…22 He et al performed the prognostic the variety of the capacity of lithium-ions batteries by using Bayesian Monte Carlo method (BMCM). 23,24 There exist many simulation techniques for battery aging model development. For RFR, the experimental data need to be classified (internal parameters of battery, external parameters of battery, etc.)…”