[Methodology for adaptive decision--making research on manufacturing process of traditional Chinese medicine based on deep reinforcement learning].

The manufacturing process of traditional Chinese medicine is subject to material fluctuation and other uncertain factors which usually cause non-optimal state and inconsistent product quality. Therefore, it is necessary to design and collect the quality-rela-ted physical parameters, process parameters, and equipment parameters in the whole manufacturing process of traditional Chinese medicine for digitization and modeling of the process. In this paper, a method for non-optimal state identification and self-recovering regulation was developed for active quality control in the manufacturing process of traditional Chinese medicine. Moreover, taking vacuum belt drying process as an example, a DQN algorithm-based intelligent decision model was established and verified and the implementation process was also discussed and studied. Thus, the process parameters-based self-optimization strategy discovery and path planning of optimal process control were rea-lized in this study. The results showed that the deep reinforcement learning-based artificial intelligence technology was helpful to improve the product quality consistency, reduce production cost, and increase benefit.

[Construction of knowledge base of Chinese medicine manufacturing].

Chinese medicine pharmaceutical industry is in the process of digital and intelligent transformation. Intelligent methods are required for efficient analysis and mining of the valuable information in the history data including literature data, pharmaceutical big data, and expert knowledge. Therefore, it is urgent to establish a knowledge-driven intelligent system of pharmaceutical technologies of Chinese medicine for efficient supplying of high-quality Chinese medicinal products. The present study proposed the construction method of the knowledge base of Chinese medicine manufacturing, which was preliminarily established from literature mining, case-based reasoning, and real-time prediction based on vacuum belt drying process optimization. Integrating the technologies(such as deep learning, case-based reasoning, and simulation modeling), pharmaceutical mechanisms, and big data, the knowledge base of Chinese medicine manufacturing can realize knowledge automation and scientific decision-making. It provides an example for upgrading from experience-based manufacturing to intelligent Chinese medicine manufacturing.

Insights into the highly efficient treatment of dyeing wastewater using algal bloom derived activated carbon with wide-range adaptability to solution pH and temperature.

Here, a low-cost acid-base and temperature tolerant algal bloom derived activated carbon (ABAC) was successfully prepared to remove rhodamine B (RhB) from water. The ABAC exhibited maximum adsorption capacity of RhB (1101 ± 11 mg/g), higher than that of laboratory-prepared rape straw activated carbon (176 ± 5 mg/g) and commercial activated carbon (489 ± 5 mg/g). It is attributed to larger surface area and mesoporous structure of the ABAC. Furthermore, the effective adsorption of RhB by using ABAC was achieved at a wide range of solution pH (3.2-10.8) and temperature(25-50 °C). The mass transfer resistance of RhB adsorption process well depicted by Langmuir model was controlled by external mass transfer. The adsorption process involved both secondly chemisorption (H-bonds and π-π interaction) and dominated physisorption. Four dyes in river water were efficiently removed. This work provides a promising approach for developing high-absorption biomass materials for actual dye wastewater treatment.

[Moisture content measurement model of whole package of Chinese medicinal materials based on microwave transmission technology].

In view of the relatively low representativeness of manual sampling inspection, and long time-consuming in oven detection of moisture content, which delayed the subsequent production period, this paper proposed a scheme for rapid moisture quantitative detection for Chinese medicinal materials by microwave transmission technology, and took 8 different types of Chinese medicinal mate-rials as examples to analyze the feasibility and reliability of the scheme for the detection results of moisture content of the whole package of Chinese medicine. In the experiment, the least square method was used to establish the measurement model of microwave absorption rate-moisture content for each kind of medicinal material. The results showed that the microwave transmission measurement of moisture content achieved high-precision measurement of the moisture content of Schisandrae Chinensis Fructus, Ziziphi Spinosae Semen, Poria, Pheretima, Lilii Bulbus, Scutellariae Radix, and Galli Gigerii Endothelium Corneum. The measurement model of Ziziphi Spinosae Semen had the highest accuracy, and the R~2 and root mean square error of the validation set were 0.951 5 and 0.15%, respectively. At the same time, this study found that the microwave absorption intensity of animal medicines including Pheretima and Galli Gigerii Endothelium Corneum was much weaker than that of plant medicines such as Schisandrae Chinensis Fructus, but there was also a good linear relationship between microwave absorption and moisture content, which proved the universality of this method. However, this method was not suitable for Phellodendri Chinensis Cortex because its package contained iron wire. For the whole package of medicinal materials with uniform density and no metal inside, the microwave transmission technology for moisture content measurement can be used to detect the moisture content, which is an effective alternative method to detect the moisture content of medicinal materials.

[Digital twin based key technologies for intelligent manufacturing of traditional Chinese medicine].

In this paper, we first introduced the concept of digital twin(DT) based key technologies for intelligent manufacturing of traditional Chinese medicine(TCM) and applied DT in two case studies of novel extraction equipment for traditional Chinese medicine and drying equipment for Chinese medicine pills to illustrate the advantages of DT in development of new pharmaceutical technology and optimization of pharmaceutical equipment structure. Furthermore, we discussed the feasibility to adopt DT in the production process of TCM for formation of data-driven real-time optimization of production process and dynamic prediction `of operation and maintenance service. The "ruled" production mode based on data and driven by algorithm was constructed to realize the technical scheme of quality perception, evaluation, prediction, intelligent control and intelligent decision-making in product life cycle.