Control model of parallel functioning production modules as fuzzy Petri nets

The article presents the results of research of Data Mining methods with Microsoft SQL Server. Microsoft Clustering algorithm was used for improving the effectiveness of medical prevention and treatment in a cohort of patients with arterial hypertension. There are rationales for monitoring of cardiovascular risk and desire to correct the risk with Data Mining at medical decision support systems. Authors used medical and sociological monitoring data from regional clinical hospital. The segmentation of arterial hypertension patients was performed using Microsoft Clustering algorithm. As a result, a quantitative assessment of the population profile for patients with arterial hypertension was obtained. The authors presented diagrams and profiles of clusters. They were compared. The developed approach is applied for decision support at regional health information management system for reduce of cardiovascular risk.


Introduction
While modeling and managing complex systems of various subject areas, operational accounting of many often conflicting factors is required. These primarily include [1,2]: complex parallel-sequential interaction of the elements of the object; the fuzzy nature of interacting dynamic processes and the space of their states; significant complexity of the tasks; a significant proportion of the human factor, which largely determines the quality and level of modern solutions.
Classical approaches to the construction of decision-making systems were largely oriented towards deterministic or stochastic processes, which fundamentally does not solve the problems of their use in conditions of essentially unclear state space [3,4]. Mathematical models based on the apparatus of fuzzy sets do not allow explicitly taking into account parallelism and dynamics in their interaction, as well as many parameters and features of the subject area. An effective solution to these problems requires the need for an integrated systematic approach based on the development of models, methods and algorithms using modern mathematical methods, modeling devices and computational intelligence technologies [5,6]. A promising direction in this case is the application of the mathematical apparatus of the theory of Petri nets (PNs) and their various expansion. In this regard, the presented work developed a fuzzy control model for parallel-functioning production modules in the machining system.

Rules for triggering and structural calculation algorithm elements of fuzzy joint ventures
The control model of parallel functioning flexible production modules in a machining system is presented in the form of fuzzy Petri nets.

Fuzzy model of parallel operating production modules in the machining system
Consider a model of parallel-functioning flexible production modules (FPM). In a flexible production system for machining, each FPM consists of one industrial robot (IR), one personal input drive, the same processing device for performing the same operations on different workpieces of the same type, and one personal output drive. Each module processes parts of the same type. The workpieces arrive at the personal input drive and await processing. A free device captures the workpiece from the input drive. After the operation is completed, the processed part enters the output personal drive.
The structure of parallel processing devices is shown in figure 1. In the graph model of parallel functioning FPMs in a flexible production system of machining (figure 2), their states are described by the following positions: p1stock of the work piece; p2, p3, p4respectively, the input drives of device 1, device 2, device 3; p5, p6, p7respectively labels excluding downloads of unloaded devices 1, devices 2, devices 3; p8, p9, p10respectively, an industrial robot (IR) 1, IR2, IR3 performing loading and unloading of device 1, device 2, device 3; p11, p12, p13respectively, device 1, device 2, device 3 performing operations on the workpiece; p14, p15, p16respectively, the output drives of device 1, device 2, device 3; p17warehouse of products. Possible events in parallel functioning FPMs are described by the following transitions: t1the delivery of the workpiece from the warehouse to the position of device 1; t2, t3, t4respectively, loading devices 2, device 3, device 4; t5, t6, t7respectively, the discharge of the device 1, device 2, device 3; t8, t9, t10respectively transporting the processed parts from the output of device 1, device 2 and device 3 to the product warehouse.