Adaptive optimal control for a wastewater treatment plant based on a data-driven method.

In order to optimize the operating points of the dissolved oxygen concentration and the nitrate level in a wastewater treatment plant (WWTP) benchmark, a data-driven adaptive optimal controller (DDAOC) based on adaptive dynamical programming is proposed. This DDAOC consists of an evaluation module and an optimization module. When a certain group of operating points is given, first the evaluation module estimates the energy consumption and the effluent quality in the future under this policy, and then the optimization module adjusts the operating points according to the evaluation result generated by the evaluation module. The optimal operating points will be found gradually as this process continues repeatedly. During the optimization, only the input-output data measured from the plant are needed, while a mechanistic model is unnecessary. The DDAOC is tested and evaluated on BSM1 (Benchmark Simulation Model No.1), and its performance is compared to the performance of a proportional-integral-derivative (PID) controller with fixed operating points under the full range of operating conditions. The results show that DDAOC can reduce the energy consumption significantly.

Semi-supervised echo state network with temporal-spatial graph regularization for dynamic soft sensor modeling of industrial processes.

Echo state network (ESN) has been successfully applied to industrial soft sensor field because of its strong nonlinear and dynamic modeling capability. Nevertheless, the traditional ESN is intrinsically a supervised learning technique, which only depends on labeled samples, but omits a large number of unlabeled samples. In order to eliminate this limitation, this work proposes a semi-supervised ESN method assisted by a temporal-spatial graph regularization (TSG-SSESN) for constructing soft sensor model with all the available samples. Firstly, the traditional supervised ESN is enhanced to construct the semi-supervised ESN (SSESN) model by integrating both unlabeled and labeled samples in the reservoir computing procedure. The SSESN computes the reservoir states under high sampling rate for better process dynamic information mining. Furthermore, the SSESN's output optimization objective is modified by applying the local adjacency graph of all training samples as a regularization term. Especially, in view of the dynamic data characteristic, a temporal-spatial graph is constructed by considering both the temporal relationship and the spatial distances. The applications to a debutanizer column process and a wastewater treatment plant demonstrate that the TSG-SSESN model can build much smoother model and has better generalization capability than the basic ESN models in terms of soft sensor prediction results.

Evolutionary optimization assisted delayed deep cycle reservoir modeling method with its application to ship heave motion prediction.

As one emerging reservoir modeling method, cycle reservoir with regular jumps (CRJ) provides one effective tool for many time series analysis tasks such as ship heave motion prediction. However, the shallow learning structure of single CRJ model limits its memory capacity and leads to unsatisfactory prediction performance. In order to pursue the stronger dynamic characteristic description of time series data, a delayed deep CRJ model is presented in this paper by integrating the deep learning framework with delay links and the evolutionary optimization for mixed-integer problem. Different from the basic CRJ model with only one reservoir, delayed deep CRJ builds multiple serial reservoirs with inserting the delay links between adjacent reservoirs. Due to the design of dynamic deep learning structure, the memory capacity is enlarged to improve ship heave motion prediction. Aiming at the mix-integer optimization problem in delayed deep CRJ model, a heuristic evolutionary optimization scheme based on the stepwise differential evolution algorithm is applied to determine the delayed deep CRJ parameters automatically. The stepwise differential evolution assisted delayed deep CRJ model can avoid the non-optimal solution resulted from the manual parameter setting effectively. Finally, one numerical example and the real experiment data are utilized to validate the methods and the results demonstrate that delayed deep CRJ model has better prediction performance in contrast to the basic CRJ method.