Cooperative Sensorless Perception of Chemical Production Lines in Smart Factories

Recent years have seen traditional chemical factories are transforming into smart factories to improve the efficiency and reduce the cost. To do that, a large number of sensors are deployed on the production lines. However, in harsh chemical production environment, such as strong acid and high temperature, certain variables are very difficult to measure, since the corresponding sensors are costly and prone to failure. To address this challenge, we propose a cooperative sensorless perception approach to estimate hard-to-measure variables by exploring the correlation and regression among the estimated variables with the other easy-to-measure variables of the production line. Specifically, the production data is pre-processed through correlation analysis and data cleaning, which brings a valuable data set for modeling. Furthermore, a regression model based on random forest is built to forecast the targeted variables. We have verified our methodology in the practical $$AlF_3$$ production lines in a chemical company. Experiment results show that the accuracy of predicted results is higher than 95%, which verifies that the proposed method is feasible and reliable.