Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts
This work addresses data efficiency and negative transfer issues in industrial soft sensors, offering an incremental improvement for multi-task learning in process industries.
The paper tackles the negative transfer problem in multi-variate soft sensor models for industrial quality estimation by proposing a balanced Mixture-of-Experts (BMoE) method, which achieves significantly better performance than baseline models on a sulfur recovery unit dataset.
Accurate estimation of multiple quality variables is critical for building industrial soft sensor models, which have long been confronted with data efficiency and negative transfer issues. Methods sharing backbone parameters among tasks address the data efficiency issue; however, they still fail to mitigate the negative transfer problem. To address this issue, a balanced Mixture-of-Experts (BMoE) is proposed in this work, which consists of a multi-gate mixture of experts (MMoE) module and a task gradient balancing (TGB) module. The MoE module aims to portray task relationships, while the TGB module balances the gradients among tasks dynamically. Both of them cooperate to mitigate the negative transfer problem. Experiments on the typical sulfur recovery unit demonstrate that BMoE models task relationship and balances the training process effectively, and achieves better performance than baseline models significantly.