Humberto Morales

Deep probabilistic learning networks have been applied in industrial soft sensors. However, they face significant challenges in latent variable inference, deep learning backend implementation, and labeled data scarcity. The first challenge arises when covariates directly infer the latent variable, potentially leading to inaccuracies. The second stems from discrepancies between the theoretical probabilistic distribution and practical instance-based deep learning backends. The third is commonly encountered in soft sensor applications, where unlabeled data often go unused, reducing accuracy. To address these challenges, this work proposes a novel semi-supervised probabilistic learning network (SS-PLN) for soft sensor modeling with partially labeled data. The first issue is addressed by formulating an optimization problem as the model’s learning objective. This optimization is efficiently solved by investigating the input of inference network through analyzing the optimal solution’s structure. For the second issue, mean and covariance equations are used to represent probabilistic distributions, ensuring effective deep learning backends. The third issue is addressed by integrating supervised and unsupervised probabilistic learning networks to form the SS-PLN model, thereby maximizing the use of unlabeled data and enhancing the soft sensing performance. The feasibility and effectiveness of the proposed SS-PLN are validated through comparisons with recent semi-supervised learning methods, using data from two industrial processes. Note to Practitioners—Soft sensors are extensively used to predict key variables in industrial processes, especially when direct measurement is challenging or infeasible. While deep learning models have shown promise for this purpose, several challenges remain. Directly inferring latent variables from covariates often results in inaccuracies due to the complexity of their relationships. Additionally, discrepancies between theoretical probabilistic distributions and practical instance-based implementations complicate soft sensor design, particularly under partially labeled data conditions. This paper proposes a novel semi-supervised probabilistic learning network (SS-PLN) to address these challenges. The SS-PLN leverages both labeled and unlabeled data to enhance prediction accuracy. By formulating a learnable optimization problem, the accuracy of inferring latent variable is improved. The mean and covariance expressions are utilized to represent the probabilistic distributions, facilitating numerical implementation. A supervised and an unsupervised probabilistic networks are integrated to construct SS-PLN, enabling effective modeling of partially labeled data. Experimental results from a sugar crystallization process and a steel-making process demonstrate the effective and suitable soft sensing performance of SS-PLN.

As modern industrial processes increase in integration and scale, there exist intricate dynamic time variability and nonlinearity within process data. Deep-learning-based nonlinear dynamic models, such as Transformer, are frequently applied to soft sensor modeling for industrial time sequences due to their powerful ability in learning temporal feature representations. Nevertheless, process data gathered from industrial plants are usually sampled at irregular intervals, posing a challenge for most mainstream dynamic models to handle the resulting temporally changeable relations in process sequence data. Thus, this article proposes a time-aware rotary Transformer (TART) for soft sensor modeling of irregular sampled time series in industrial processes, which adaptively and efficiently model the temporally changeable dynamics among series data. Specifically, a sampling interval embedding layer is devised to simultaneously encode the process variables, positional information, and sampling intervals, facilitating the efficient extraction of temporal dynamic features. Accordingly, a nonincreasing function-based time-aware rotary attention mechanism is proposed to deal with the temporally changeable sampling intervals via assigning proper weights to the corresponding feature representations. Theoretical analysis shows that the proposed time-aware rotary attention mechanism can adaptively assign temporal similarities according to the irregular sampling intervals. The TART-based soft sensor is applied to an actual-run industrial sugar crystallization process to predict the supersaturation and purity of mother liquor. In comparison with recent predictive modeling methods, the proposed TART achieves state-of-the-art performance, demonstrating its feasibility and efficacy for soft sensing of practical industrial processes.