Search

Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction to acquire the state and reward values. In this paper, we present a cost-efficient framework, such that the RL model can evolve for itself in a Virtual Space using the predictive models with only historical data. The proposed framework enables a step-by-step RL model to predict the future state and select optimal actions for long-sight decisions. The main focuses are summarized as: 1) how to balance the long-sight and short-sight rewards with an optimal strategy; 2) how to make the virtual model interacting with real environment to converge to a final learning policy. Under the experimental settings of Fed-Batch Process, our method consistently outperforms the existing state-of-the-art methods.

The pore structure of the regenerated cellulose hydrogel was used as a microreactor for generating magnetic MnFe2O4 nanoparticles via in situ co-precipitation technology. Sodium periodate and sodium chlorite were used as oxidants, and the carboxyl modification of magnetic cellulose aerogels was achieved through a two-step oxidation reaction. The method used was convenient and environmental-friendly, and the raw materials were also green and non-toxic. The addition of magnetic nanoparticles promoted the adsorption and enabled the recycling of materials. The results showed that the adsorption equilibrium time was only 120 min and adsorption capacity could be increased by increasing the adsorption temperature. The maximum adsorption capacity of Cu(II) was 73.70 mg/g at 25 °C when the initial concentration of solution was150 mg/L. The adsorption behaviour towards Cu(II) followed the pseudo-secondary reaction kinetics and the Langmuir isotherm adsorption model. According to the results of XPS, carboxyl and hydroxyl groups were the main active adsorption sites for Cu(II). Moreover, all the composite aerogels exhibited good reusability and could be easily separated from the water after adsorption. The pore structure of the regenerated cellulose hydrogel was used as a microreactor for generating magnetic MnFe2O4 nanoparticles via in situ co-precipitation technology. Sodium periodate and sodium chlorite were used as oxidants, and the carboxyl modification of magnetic cellulose aerogels was achieved through a two-step oxidation reaction. According to the results of XPS, carboxyl and hydroxyl groups were the main adsorption sites for Cu(II). Moreover, all the composite aerogels exhibited good reusability and could be easily separated from the water after adsorption.

Earthwork calculation occupies an important position in all aspects of engineering construction, and its calculation accuracy and efficiency will have a significant impact on engineering construction. This article analyzes and summarizes the calculation results of various methods and software used in calculating earthwork; points out the shortcomings of the existing earthwork calculation methods; discusses the future development direction of earthwork calculation, which requires not only high accuracy, but also Faster and smarter information feedback provides timely and effective reference and guidance for project construction.

Refereed/Peer-reviewed Mathematical modeling plays a critical role toward the mitigation of nitrous oxide (N2O) emissions from wastewater treatment plants (WWTPs). In this work, we proposed a novel hybrid modeling approach by integrating the first principal model with deep learning techniques to predict N2O emissions. The hybrid model was successfully implemented and validated with the N2O emission data from a full-scale WWTP. This hybrid model is demonstrated to have higher accuracy for N2O emission modeling in the WWTP than the mechanistic model or pure deep learning model. Equally important, the hybrid model is more applicable than the pure deep learning model due to the lower requirement of data and the pure mechanistic model due to the less calibration requirement. This superior performance was due to the hybrid nature of the proposed model. It integrated the essential wastewater treatment knowledge as the first principal component and the less understood N2O production processes by the data-driven deep learning approach. The developed hybrid model was also successfully implemented under different circumstances for the prediction of N2O flux, which showed the generalizability of the model. The hybrid model also showed great potential to be applied for the N2O mitigation work. Nevertheless, the capability of the hybrid model in evaluating N2O mitigation strategies still requires validation with experiments. Going beyond N2O modeling in WWTP, the novel hybridization modeling concept can potentially be applied to other environmental systems.

Refereed/Peer-reviewed Mainstream nitrogen removal via anammox is widely recognized as a promising wastewater treatment process. However, its application is challenging at large scale due to unstable suppression of nitrite-oxidizing bacteria (NOB). In this study, a pilot-scale mainstream anammox process was implemented in an Integrated Fixed-film Activated Sludge (IFAS) configuration. Stable operation with robust NOB suppression was maintained for over one year. This was achieved through integration of three key control strategies: i) low dissolved oxygen (DO = 0.4 ± 0.2 mg O2/L), ii) regular free nitrous acid (FNA)-based sludge treatment, and iii) residual ammonium concentration control (NH4+ with a setpoint of ∼8 mg N/L). Activity tests and FISH demonstrated that NOB barely survived in sludge flocs and were inhibited in biofilms. Despite receiving organic-deficient wastewater from a pilot-scale High-Rate Activated Sludge (HRAS) system as the feed, the system maintained a stable effluent total nitrogen concentration mostly below 10 mg N/L, which was attributed to the successful retention of anammox bacteria. This study successfully demonstrated large-scale long-term mainstream anammox application and generated new practical knowledge for NOB control and anammox retention.