Searcharxiv⌕ Search

arXiv subjects

Liqiu Dong

Publications and source records attributed to Liqiu Dong.

3 recordsLinked to original sources

Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process Critics

Start-ups and grade changes remain largely operator-driven, while developing and maintaining dynamic models for model-based control requires substantial engineering effort. Hybrid Offline Learning and Online Optimisation (HOFLON) uses one-step offline reinforcement learning to select actions from historical transition data. In its original implementation, the online objective combines the predicted return from a tree-ensemble critic with an adversarial-autoencoder (AAE) penalty for unfamiliar state-action pairs. We examine the effect of this penalty and replace the critic and AAE with a sparse variational Gaussian-process (sGP) critic. Actions maximise $μ- κσ$, an uncertainty-adjusted estimate of the return from one action followed by the historical operating practice. On the HOFLON polymerisation-reactor benchmark, removing the AAE from HOFLON led to 4 failed start-ups in 15 runs over five critics. At its published weight, the variation in the AAE penalty is four orders of magnitude smaller than the variation in the tree-ensemble critic. Nevertheless, it changes actions when the predicted returns of competing candidates are nearly equal, and paired runs with and without the penalty diverged from the first move. With a Matérn-5/2 sGP critic, $κ= 0$ led to failure in 13 of 15 runs, whereas with $κ= 3$ none of 15 runs (five critics, three noise realisations) failed. The median and lowest returns were 13,464 and 13,398 (HOFLON: 13,393 and 12,411). A squared-exponential sGP critic with learned inducing inputs needed $κ\geq 3$ to remain within the empirical data support in steady state, and then settled with a temperature offset of 2.0 K.

cs.LG↗

Bayesian Optimization of a Multi-Product Chemical Reactor Using Composite Models and Partial Physics Knowledge

We study data-driven real-time economic optimization of a multi-product chemical reactor when no reliable first-principles model is available beyond a steady-state energy balance. Instead of learning the economic objective directly as a black-box function, we use a composite formulation in which Gaussian process (GP) models predict physically meaningful outputs, including product concentrations and reactor temperature, while profit is computed analytically from these predictions together with raw-material, product, and utility prices. This preserves the structure of the economic objective, makes it parametric in changing prices without needing retraining, and allows candidate operating points to be checked against the available energy balance through a physics residual. The GPs also provide predictive uncertainty, which is exploited in a Bayesian optimization (BO) framework both for data-efficient exploration and for conservative enforcement of the reactor temperature constraint through an upper confidence bound. The acquisition function additionally penalizes large energy-balance mismatch obtained by substituting the GP-predicted outputs and candidate inputs into the available steady-state energy balance. The approach is demonstrated on a benchmark simulation of a non-isothermal multi-product reactor. Relative to a trust-region safe BO implementation, the proposed method achieves better simulated economic performance within the available iteration budget. Relative to a purely data-driven BO approach that does not use the available physics information, it avoids reactor temperature constraint violations.

eess.SY↗

PI-CoF: A Bilevel Optimization Framework for Solving Active Learning Problems using Physics-Information

Physics informed neural networks (PINNs) have recently been proposed as surrogate models for solving process optimization problems. However, in an active learning setting collecting enough data for reliably training PINNs poses a challenge. This study proposes a broadly applicable method for incorporating physics information into existing machine learning (ML) models of any type. The proposed method - referred to as PI-CoF for Physics-Informed Correction Factors - introduces additive or multiplicative correction factors for pointwise inference, which are identified by solving a regularized unconstrained optimization problem for reconciliation of physics information and ML model predictions. When ML models are used in an optimization context, using the proposed approach translates into a bilevel optimization problem, where the reconciliation problem is solved as an inner problem each time before evaluating the objective and constraint functions of the outer problem. The utility of the proposed approach is demonstrated through a numerical example, emphasizing constraint satisfaction in a safe Bayesian optimization (BO) setting. Furthermore, a simulation study is carried out by using PI-CoF for the real-time optimization of a fuel cell system. The results show reduced fuel consumption and better reference tracking performance when using the proposed PI-CoF approach in comparison to a constrained BO algorithm not using physics information.

eess.SY↗