Online quality prediction for cobalt oxalate synthesis process using least squares support vector regression approach with dual updating

• An adaptive LSSVR (ALSSVR) based on model performance assessment is proposed.
• An error Gaussian mixture model is developed to evaluate the model performance.
• LSSVR model updating and model offset updating can track the process dynamics.
• The ALSSVR model is used for soft sensing of nonlinear and time-varying processes.
• The efficiency of the soft sensor is demonstrated through an industrial application.

Online measurement of the average particle size is typically unavailable in industrial cobalt oxalate synthesis process, soft sensor prediction of the important quality variable is therefore required. Cobalt oxalate synthesis process is a complex multivariable and highly nonlinear process. In this paper, an effective soft sensor based on least squares support vector regression (LSSVR) with dual updating is developed for prediction the average particle size. In this soft sensor model, the methods of moving window LSSVR (MWLSSVR) updating and the model output offset updating is activated based on model performance assessment. Feasibility and efficiency of the proposed soft sensor are demonstrated through the application to an industrial cobalt oxalate synthesis process.