No abstract

The paper is aimed to create the mathematical model of the centrifugal compressor based on the group method of data handling-type neural networks to determine the compressor volumetric flow rate as the dependence on the centrifugal compressor’s technological parameters (the rotor’s angular velocity, the compressor’s inlet and outlet temperatures, the compressor’s inlet and outlet pressures, the atmospheric pressure). It is the important scientific task, because most centrifugal compressors used in the process industry don’t have equipment needed to measure the volumetric flow rate. It does not allow to estimate the compressor’s technical state during its operation. Verification of the developed model has been performed, based on the 336 data points (collected from the field measurements) and with using the centrifugal compressor of natural gas (16ГЦ2-395/53-76C) of Dolyna linear production administration of gas transmittal pipelines. The test results have been showed the adequate efficiency of the mathematical model. Keywords: volume flow, centrifugal supercharger, mathematical model, method of group consideration of arguments, neural networks, technological parameters, correlation coefficient.

An expert system is a computer program that simulates the judgment and behavior of a human or an organization that has expert knowledge and experience in a particular field. It is a program that emulates the interaction a user might have with a human expert to solve a problem. The end user provides input by selecting one or more answers from a list or by entering data. An Expert System is a problem solving and decision making system based on knowledge of its task and logical rules or procedures for using knowledge. Both the knowledge and the logic are obtained from the experience of a specialist in the area. This paper considers approaches to building a knowledge base for medical systems. In developing the knowledge base of the information system, Bayesian networks were chosen as the basis for the decision-making model by type of patient pathology. This choice was due to the availability of these networks the ability to work with uncertain knowledge used in the diagnosis of diseases, in choosing the optimal course of treatment and subsequent prediction of patients. In addition, they offer the most adequate formal representation of inaccurate knowledge, as they are the result of a synthesis of statistical methods of data analysis and artificial intelligence. The presence of hydrosulfide ion intoxication (HS-intoxication), divalent iron ion intoxication (Fe-intoxication), the patient's absence of pathology and the value of Ag2S and Pt electrode potentials were selected as nodes of this network. Based on the accumulated experience of monitoring the condition of patients during their postoperative treatment (data obtained in collaboration with Ivano-Frankivsk National Medical University), as well as experimental data, conditional probabilities of values that can take the readings of the electrodes were established. Experimental testing of the adequacy of the proposed and implemented model was performed on an array of data from potentiometric measurements of patients' biomaterial. The prediction made by the network was taken as the node that had the highest probability of being in a state that indicates the presence of a pathology. Comparison of the results of the network with data obtained by other methods showed their convergence in 85% of cases. Thus, the developed network can be used to facilitate the process of diagnosing the presence and type of intoxication of the patient and is included in the information system for monitoring the patient's condition.