This paper studies the influence of the conditions for obtaining materials based on the synthetic polymer polylactide on their physical-mechanical and rheological characteristics. These materials are promising for creating temporary biodegradable polymer implants to maintain the mechanical properties of broken bones during the healing period. They are designed to replace the titanium fixators currently used for these purposes, which is due not only to the need for repeated surgery to extract them but also to the fact that the strength and modulus of elasticity of titanium fixators exceed the values of bone strength indicators by an order of magnitude, which can cause the phenomenon of bone resorption and a decrease in its strength. It is established that with an increase in temperature in the plasticization and pressing zone, as well as with an increase in pressure in the press, there is a natural decrease in the viscosity of the polylactide melt, as well as the values of the elastic modulus and breaking stress of solid samples. Varying the cooling rate of the material during the pressing process affects the degree of its crystallinity. At the same time, the lower the cooling rate the greater the degree of crystallinity of the polylactide and the greater the values of the elastic modulus and breaking stress.

Thermoplastics in the recycling process are characterized by mechanical and thermo-oxidative degradation, which leads to deterioration of the operational properties of finished plastic products. A possible option for giving the secondary raw material optimal characteristics during processing may be the inclusion of aluminosilicate microspheres and modifiers that increase the fluidity of the melt. This paper presents the results of the study of rheological and physico-mechanical properties of polymer composites based on secondary polypropylene filled with aluminosilicate microspheres in the presence of stearic acid. It is shown that stearic acid increases the fluidity of the melt, improves technological performance during mechanical processing, including promotes uniform distribution of particles of aluminosilicate microspheres in the polymer volume. The optimal concentration of stearic acid is 0.5 % by weight, at which there is a maximum increase in the melt flow rate, a decrease in tensile strength of no more than 16 %, as well as an increase in resistance to dynamic impact without a significant change in the elastic modulus characterizing the stiffness of the material.

The nucleophilic substitution reaction of bisphenol A, Phenolphthalein, and resorcinol with 2-(4-fluorobenzoyl)benzoic acid gave previously undescribed diketoacids and their pseudochlorides. New polyarylenediphthalides with two hinged ether groups in the main chain, two of which (based on bisphenol A and resorcinol) exhibit a highly elastic state, were synthesized by the self-condensation of the pseudochlorides.

The paper is devoted to scheduling in multiagent systems in the framework of the Flatland 3 competition. The main aim of this competition is to develop an algorithm for the effective control of dense traffic in complex railroad networks according to a given schedule. The proposed solution is based on reinforcement learning. To adapt this method to the particular scheduling problem, a novel approach based on structuring the reward function that stimulates an agent to adhere to its schedule was developed. The architecture of the proposed model is based on a multiagent version of centralized critic with proximal policy optimization (PPO) learning. In addition, a curriculum learning strategy was developed and implemented. This allowed the agent to cope with each level of complexity on time and train the model in more difficult conditions. The proposed solution won first place in the Flatland 3 competition in the reinforcement learning track.

The relevance of the problem under study is due to an increase in the amount of polymer waste based on synthetic polymers, which determines the feasibility of its involvement in recycling in relation to thermoplastic polyolefins. A significant proportion of plastic waste falls on plastic products made of polypropylene, while the processed raw materials almost always contain a mixture of polypropylene with different polyethylene content. The aim of the work was to study the thermal characteristics of polymer compounds based on secondary polypropylene filled with high and low pressure polyethylene. The leading approach to the study of this problem is the use of methods of thermogravimetry and differential scanning calorimetry, which make it possible to identify patterns of changes in temperature and thermal characteristics of phase transitions, as well as thermal stability of polymer compounds. It is shown that the presence of two peaks of melting and crystallization on thermograms of differential scanning calorimetry of polypropylene-polyethylene mixtures indicates the incompatibility of polymers, while the polymer system is heterophase. In the presence of polyethylene, the crystallization rate of polypropylene changes, while its melting temperature decreases and the crystallization temperature increases compared to a pure polymer. Filling the compound with polyethylene of both low and high pressure reduces the rate of decomposition of secondary polypropylene and shifts the decomposition process of compounds to higher temperatures. The mass of the dry residue when heated to 400°C and 600°C for a polymer compound with low-pressure polyethylene is higher compared to high-pressure polyethylene. The materials of the article can be useful for the creation of polymer composites based on recycled polypropylene in the presence of polyethylene, as well as the development of technological modes of their processing.

In the previous work of the authors [1], an intelligent system for the automation of dispatching activities in organizing the movement of railway transport was presented. This concerned adjusting schedules in multiagent systems in the event of unexpected changes in situations. This article specifies the main approach and describes in detail the model, solution method, and possible modernization of the system.

The results of studying the architectures of deep neural networks designed to solve classification problems are presented. As a result, attributes are formed for effective decision-making automation. Multidimensional time series of financial markets are used as data. The problems of binary and multiple classification are considered. Fully connected, recurrent (long short-term memory (LSTM)) and hybrid combined architectures of neural networks are analyzed. The studied multivariate time series is obtained by combining a one-dimensional time series of asset value, trading volume, technical indicators, and other parameters.

Polymer composites based on recycled thermoplastic polymers filled with biodegradable components of plant origin are developed. Repeated thermal and mechanical action on polymers during their processing in the presence of dispersed phase particles leads to a change in the thermophysical and strength characteristics of finished products. The patterns of change in the heat resistance of the polymer composites based on a recycled block copolymer of propylene and ethylene and rice hulls processed by injection molding and pressing are studied. It is shown that filling the recycled polymer with rice hulls leads to an increase in the heat resistance of the composites, which is characterized by an increase in the deflection temperature under load, the Vicat softening temperature, and the decomposition temperature during thermogravimetric analysis in an inert atmosphere. Compared to the injection molding method, pressing of the polymer composites makes it possible to obtain more heat-resistant plastic products. This is obviously due to the differing degrees of crystallinity of the polymer phase. The high cooling rate of the polymer composite melt during the filling of the injection mold does not provide the time necessary for the corresponding change in the conformation of macromolecules and the formation of the crystalline phase. As a consequence, an increase in the content of the amorphous phase of the recycled block copolymer of propylene and ethylene reduces the heat resistance of the prototypes.

The application of artificial intelligence in the development of а decision support system for the implementation of transport traffic is presented. Such systems are designed to adjust the schedule of objects in cases of unforeseen situations. A fully connected artificial neural network with several hidden layers, trained using a genetic algorithm, is used. During training, the functionality that characterizes the deviation from the specified schedule is minimized. Railway traffic is one of the most important types of transport in Russia. Every year it becomes more and more intense, the density and volume of both cargo and passenger traffic increases. As a result, the requirements for the exact execution of the planned traffic schedule increase, since any deviation leads to significant penalties due, for example, to an increase in train delays, their cancellation, etc. The work of a dispatcher, a person who controls railway traffic, is quite time-consuming and becomes more difficult every day, so the development of dispatcher assistance systems is one of the most relevant areas in control automation in this area. At the same time, the existing high requirements for traffic safety, which impose additional restrictions, finally lead to the fact that in this kind of system, the final decision is left to the person, and computer development has a recommendatory character. This article describes the artificial intelligence apparatus in the form of training neural networks using a genetic algorithm to build an automated dispatcher that corrects movement.

A description of the use of artificial intelligence in the development of decision support systems, which are used for various types of transport, is given. These systems are aimed at restructuring the schedule of movement of objects due to unforeseen deviations from the preplanned schedules. Machine learning of a neural network using a genetic algorithm is used. This minimizes the functionality that characterizes the deviation from the given schedule.

The aqueous solutions of chitosan, succinyl chitosan sodium salt, and carboxymethylcellulose sodium salt are studied by the rheological method. An increase in the polymer concentration in solution leads to a sharp increase in viscosity due to formation of the entanglement network, the transition of the polymer solution to the gel-like state, a sharp increase in the relaxation time, and the appearance of elasticity of solutions. These systems are characterized by time anomalies characterized by a hysteresis loop, the area of which depends not only on concentration but also on the rate of increase/decrease of the shear rate. Thixotropy is observed in the intermediate concentration range, where supramolecular structures are formed and the time required for their destruction is comparable to the time of the experiment. This makes it possible to regulate a number of properties of materials formed from solutions. According to DSC studies, the glass transition temperatures and the melting temperatures of films obtained from solutions of different concentrations are different. The tensile stress and the elastic modulus of film polymeric materials pass through a maximum corresponding to the polymer concentration at which the maximum degree of structuring is implemented while maintaining the fluidity.

One of the most common ways to create polymer composites based on polypropylene is to fill it with chalk, which allows one to improve the appearance of the resulting plastic products and their performance properties. The thermoplasticity of the resulting polymer composites determines the possibility of involving retired polymer materials in reprocessing, which requires studying the laws of the influence of heating on the thermophysical properties of the polymer phase. The regularities of changes in the thermophysical parameters of polymer composites based on secondary polypropylene in the process of filling it with a chalk additive have been studied. It is shown that processing of primary polypropylene by injection molding leads to a decrease in the thermal stability of the resulting secondary polymer material without changing the melting and crystallization points of the polymer phase, but it is accompanied by a decrease in the melting enthalpy (by 9–11%) and the degree of crystallinity of the polymer (by 5.6–6.5%). Filling secondary polypropylene with chalk additionally reduces the temperature of the beginning of decomposition of the composite, while the temperature corresponding to the maximum rate of thermo-oxidative destruction is shifted by 18–25°С to the lower temperature region. The introduction of 2 wt parts chalk into polypropylene reduces the melting point by 3.6°С and increases the crystallization point of the polymer phase by 1.3°С. Filling of secondary polypropylene with a chalk additive in the amount of 5–10 wt parts reduces the degree of crystallinity of the polymer, which can lead to changes in the physical and mechanical properties of plastic products.

The effect of the method and the number of processing cycles on polypropylene thermal and physical-mechanical properties is studied. It is shown that, regardless of the processing method, the thermal stability of polypropylene, expressed by the temperature of the onset of decomposition, decreases, the content of thermally stable compounds increases, and the degree of crystallinity of the polymer decreases by 5.6–6.5%. With an increase in the number of heating-cooling cycles simulating the multiplicity of thermoplastic polypropylene processing, the temperature of the onset of decomposition decreases from 211°C to 166°C, the mass of the sample decreases due to its partial decomposition, the melting point decreases from 166°C to 158°C, the degree of crystallinity of the polymer decreases. With an increase in the number of polypropylene processing cycles by compounding in the mixing chamber of the plastograph, an increase in the load on the rotation of the screws during plasticization and in the melt flow is observed, while the strength and elongation at break of the plastic sample consistently decrease..

The relevance of the problem under study is due to the development of a method for the rational use of polypropylene-based polymer waste (PP) by creating polymer composites in a mixture with ultra-high molecular weight polyethylene (UHMWPE). The article is aimed at studying the physico-mechanical and thermophysical characteristics of polymer composites based on PP and UHMWPE. The leading research methods for this problem are the study of the strength characteristics of polymer composites at break and bending, thermogravimetric analysis and differential scanning calorimetry. It is shown that the maximum torque in the mixing chamber during polymer melting does not additively change depending on the composition of the mixture. The increase in maximum torque more than 2 times occurs when filling the secondary polypropylene 5 % of the mass. UHMWPE and only 25 – 35 % decreases when filling UHMWPE with polypropylene in an amount of 10 – 50 % of the mass. Filling of secondary UHMWPE polypropylene up to 3 % of the mass slightly strengthens the composition, and also increases its modulus of elasticity at break and bending. UHMWPE allows increasing the thermal stability of secondary polypropylene by increasing the decomposition onset temperature by 12°C, the mass of the residue upon heating to 400°C, and peak displacements corresponding to the maximum decomposition rate of the main substance in the high temperature region. Two endothermic peaks corresponding to the melting temperature of the starting polymers are observed in the DSC thermogram in the heating mode; the melting temperature of polypropylene in the composite is 3.1– 4.8°C lower than that of an individual polymer. The crystallization of PP and UHMWPE in the mixture proceeds in the same temperature range and is characterized by the presence of one exothermic maximum on the DSC curve, which is shifted to the temperature region corresponding to the crystallization temperature of an individual UHMWPE.