Generative Upper-Level Policy Imitation Learning With Pareto-Improvement for Energy-Efficient Advanced Machining Systems.

The potential intelligence behind advanced machining systems (AMSs) offers positive contributions toward process improvement. Imitation learning (IL) offers an appealing approach to accessing this intelligence by observing demonstrations from skilled technologists. However, existing IL algorithms that implement single policy strategies have yet to consider realistic scenarios for complex AMS tasks, where the available demonstrations may have come from various experts. Moreover, most IL assumes that the expert's policy is optimal, preventing the learning from fulfilling the previously ignored green missions. This article introduces a novel three-phase policy search algorithm based on IL, enabling the learning of heterogeneous expert policies while balancing energy preferences. The first phase equips the agent with machining basics through upper-level policy learning, generating an imitation policy distribution with various decision-making principles. The second phase enhances energy conservation capabilities by employing Pareto-improvement learning and fine-tuning the agent's policies to a Pareto-policy manifold. The third phase produces outcomes and amplifies the efficacy of human feedback by utilizing ensemble policies. The experimental results indicate that the proposed method outperforms meta-heuristics, exhibiting superior solution quality and faster computation times compared to four diverse baseline methods, each with diverse samples.

Efficient Capture of Th(IV) and U(VI) by Radiation-Resistant Oxygen-Rich Ion Traps Based on a Metal-Organic Framework.

Herein, based on a well-stabilized Ti-MOF (IEF-11), an oxygen-rich ion trap with synergy interaction of active atoms was proposed for the removal of Th(IV) and U(VI) from aqueous solutions. Due to the high coordination number of Ti and compact framework structure, IEF-11 has excellent resistance toward ß-ray irradiation, even under 1000 kGy irradiation dosage. Meanwhile, owing to the special chelating effect of the oxygen-rich ion traps, the maximum adsorption amounts of IEF-11 for Th(IV) (pH = 3.0) and U(VI) (pH = 5.0) ions can reach 305.9 and 240.7 mg g-1, and the separation coefficients exceed 200 for Th(IV)/Nd(III), Th(IV)/Sm(III), and Th(IV)/Eu(III) and 100 for U(VI)/Eu(III), U(VI)/La(III), and U(VI)/Sr(II). Moreover, IEF-11 shows fast adsorption kinetics with an equilibrium time of ∼100 min. The adsorption amount almost remains even after four adsorption-desorption cycles. Finally, experimental and theoretical calculations indicate that Th(IV) and U(VI) ions are anchored in the ion trap in the form of chemical bonds. Meanwhile, the circular pore trap (class I trap) than the long pore trap (class II trap) is considered to be the better adsorption site. We expect that our work will provide a new insight for constructing effective adsorbents for radioactive nuclides.

Driving forces of China's CO2 emissions from energy consumption based on Kaya-LMDI methods.

Anthropogenic carbon emission gives rise to a situation where global warming is becoming serious. China is paying for reducing carbon emissions. The concept of carbon curse suggests that countries rich in fossil fuels tend to be closely linked to high carbon emissions, but this is not absolute, which reminds policymakers that the policies implemented are positivelycorrelateswith carbon emission reduction. This study is also aimed at this, hoping to provide some proposals about reducing CO2 emissions to policy-makers by decomposing and analyzing the important factors. To achieve this target, this paper employs the extended the Kaya identity, combines the LMDI method to analyze the impact factors of carbon emissions in China from 1996 to 2016 and discusses the effects and causes of each factor according to the actual situation. It is found that the economic activity is the greatest driving force to promote carbon emissions, while on the contrary, energy intensity is the biggest suppressor. Optimizing industrial structure, improving the structure of energy and export-import trade and intensifying the development of clean energy can effectively restrain the growth of carbon emissions. In addition, the relative innovation point in this study is to analyze carbon emissions with the combination of electricity trading and discusses that increasing imported electricity is also a strategy to reduce carbon emissions.