Method for monitoring on-line quality and updating prediction model of rubber hardness

Abstract

The invention discloses a method for monitoring the on-line quality and updating a prediction model of rubber hardness, which comprises the following steps of: building a hardness online predicting model according to a training data set, and computing an alarm limit, a warning limit and a selecting limit; inputting a reheological parameter new sample into the hardness online predicting model, and automatically outputting a rubber hardness value; and according to relationship between the Q statistics value of the reheological parameter new sample Xnew and the alarm limit, the warning limit and the selecting limit, confirming whether the hardness online predicting model to be updated or not or whether a quality monitoring system alarms or not, checking the working condition of a production line by operation workers, and carrying out corresponding technical adjustment, so that the current working condition can be recovered to be the normal status. The model is constantly updated by the method, so that the exact rubber hardness value can be obtained, the quality of the rubber can be improved, the practical test verifies that the higher precision can be obtained by the method, and the potential safety hazards can be reduced; and along with the reduction of the number of the samples, the memory space of a computer can be reduced, and the computing speed can be observably improved.

Description

technical field [0001] The invention relates to an online quality monitoring method in the field of rubber tire manufacturing, in particular to a method for online quality monitoring of rubber hardness and a prediction model update method. Background technique [0002] In recent years, with the continuous increase of the gross national product, the rubber industry has developed by leaps and bounds, coupled with the continuous development of China's automobile industry, it has played a huge role in promoting the rubber industry. No matter in the field of production or life, more and more rubber products are used. With the continuous emergence of new products and the continuous expansion of application fields, newer and higher requirements are put forward for the production of rubber products. [0003] Rubber mixing is one of the most important processes in rubber production, and the effective control of the rubber mixing process directly affects the quality of rubber product...

AI Technical Summary

Problems solved by technology

[0006] A big defect of the current data-driven method is that it cannot automatically update the model in real time, especially in the time-varying process, which will seriously affect the prediction accuracy of rubber hardness, resulting in errors in the measurement of rubber hardness and reducing the rubber hardness. Quality and life; once the statistic (Q statistic) of the traditional monitoring algorithm is established, it cannot be updated online, that is, as the industrial process progresses, the interpretation of the original model to the industrial parameters will become worse and worse, so its time-varying The tracking ability is gradually weakened, and the system with significant time-varying characteristics such as intermittent processes cannot be effectively monitored online

Images