Improvement and estimation of prediction accuracy of soft sensor models based on time difference

Soft sensors are widely used to estimate process variables that are difficult to measure online. However, their predictive accuracy gradually decreases with changes in the state of the plants. We have been constructing soft sensor models based on the time difference of an objective variable y and that of explanatory variables (time difference models) for reducing the effects of deterioration with age such as the drift and gradual changes in the state of plants without reconstruction of the models. In this paper, we have attempted to improve and estimate the prediction accuracy of time difference models, and proposed to handle multiple y values predicted from multiple intervals of time difference. An exponentially-weighted average is the final predicted value and the standard deviation is the index of its prediction accuracy. This method was applied to real industrial data and its usefulness was confirmed.