A sparse data gas sensor array feature mining method for rubber Mooney viscosity measurement

Mooney viscosity is an important index to reflect the performance and quality of rubber. At present, the rubber Mooney test has the problems of large time delay, destructive and unable to detect online, which restricts the development of rubber industry. In this paper, a gas sensor array-based online inspection method for rubber Mooney viscosity is proposed to improve the problems of measurement delay and raw material waste in the traditional method. A multiple generator time series generative adversarial network (MGTSGAN) structure is proposed to address the problem that the lack of sample data volume and uneven data distribution make it difficult to model. Transformer is introduced to solve the problem of traditional generative adversarial networks in dealing with long sequential dependencies. In the experimental part, a rubber Mooney viscosity detection device is built to verify the effectiveness of the proposed method. The performance of different generative models on two gas sensor datasets is compared to verify the advancement and generalization of the proposed method. The experimental results show that the correct rate of this paper's method for rubber Mooney viscosity classification is higher than 96%. The correct rates are all improved after data enhancement, in which the MGTSGAN proposed in this paper obtains the highest correct rate of 98.35%. For the classification experiments on Gas sensor array under flow modulation dataset also achieved relatively good results. Among them, the highest correct classification rate of 95.63% is achieved after data enhancement using MGTSGAN.