A fault diagnosis model for penicillin fermentation process based on Serval Optimization Algorithm on mixed strategies was proposed to optimize parameters of kernel extreme learning machine. In order to solve the problem that the population distribution of SOA algorithm is uneven in the early stage, and it is easy to fall into local optimization in the later stage, this paper firstly initializing the population with cubic mapping to enhance the randomness and variability of the population, then using golden sine strategy to expand the local search ability of the algorithm, and introducing Gaussian perturbation strategy to help the algorithm jump out of the local extreme point to enhance the global search ability of the algorithm. Finally, the algorithm was used to optimize the parameters of KELM to accurately diagnose the faults in penicillin fermentation process. By comparing SOA-KELM with other three optimization algorithms to optimize KELM, the results show that SOAM-KELM model has advantages in fault diagnosis of penicillin fermentation process.