Well-studied scheduling practices are fundamental for the successful support of core business processes in any manufacturing environment. Particularly, the Hybrid Flow Shop (HFS) scheduling problems are present in many manufacturing environments. The current advances in the field of Deep Reinforcement Learning (DRL) attracted the attention of both practitioners and academics to investigate their adoption beyond synthetic game-like applications. Therefore, we present an approach that is based on DRL techniques in conjunction with a discrete event simulation model to solve a real-world four-stage HFS scheduling problem. The main narrative behind the presented concepts is to expose a DRL agent to a gamelike environment using an indirect encoding. Two types of DRL techniques namely, Proximal Policy Optimization (PPO) and Asynchronous Advantage Actor-Critic (A3C), are evaluated for solving problems of different complexity. The computational results suggest that the DRL agents successfully learn appropriate policies for solving the investigated problem. In addition, the investigation shows that the agent can adjust their policies when we expose them to a different problem. We further evaluate the approach to solving problem instances published in the literature to establish a comparison.

A method for preparing functionalized styrene-butadiene copolymers on a new initiating system, which is a modifier consisting of a mixed sodium-calcium alkoxide of oxypropylated aniline dissolved in ?-methylstyrene and n-butyllithium has been developed. It was revealed that the lowered content of calcium ions makes it possible to obtain a modifier without colloidal fine-dispersed sludge, which negatively affects the operation of equipment in the industrial production of rubbers. The high initiation activity on lithium amides promoted a high conversion of monomers and a good stereoregulating ability of the 1.2-unit content of the butadiene part of the copolymer macromolecule, amounting to 66-68 wt%. The addition of a reactive compound to the end of the "living" polymer chain, stannous tetrachloride, improves the technological properties estimated by the Mooney viscosity, which increased by 5 units. It was shown on the example of prototypes of rubber mixtures, the polymer base of which was functionalized styrene-butadiene rubbers, that they are characterized by a sufficiently high rate of vulcanization, and in terms of technological, elastic and strength properties, the samples are identical with the foreign analogue NS-616, in terms of abrasion resistance they surpass the imported analogue by 20%, in resistance to crack growth by 36% was shown. The rubber mixture based on functionalized rubber was characterized by better adhesion on ice. The use of functionalized rubbers instead of serial rubber has little effect on tire rolling losses. A slight decrease in tan ? values at 0 °C for rubbers based on functionalized rubbers was noted, which can be compensated for by adjusting their microstructure and requires additional research.

No abstract

No abstract