Abstract
The task on estimating the technical condition of a hydrogenerator under conditions of fuzzy information has been resolved. To this end, a series of models have been constructed for the integrated estimation of the technical condition of a hydrogenerator based on data about the states of its local nodes. The technical states of local nodes are determined based on the earlier devised fuzzy models of the Mamdani type and represent the fuzzy values, which was taken into consideration in the model for estimating technical condition of a hydrogenerator. The fuzzy methods by Mamdani, Sugeno, Zadeh, as well as the simplified fuzzy inference, were used to build the models. The fuzzy model by Mamdani has a qualitative base of rules only, which simplifies its construction by an expert. The models based on the fuzzy algorithm by Sugeno imply a rule base with weight coefficients, determined by the Saati method. The simplified method and the method by Zadeh require minimal expert participation when constructing a fuzzy model. Examples of estimating the technical condition of a hydrogenerator have been considered based on five devised fuzzy models; the sensitivity of models to the quality and reliability of input information has been tested. It has been determined that the most reliable result from estimating the state of a hydrogenerator with an error of 1.5–2 % is produced by models built according to Zadeh method and the simplified fuzzy inference, since they have the least dependence on the uncertainty of input data on the states of local nodes, which themselves were obtained based on fuzzy models. High accuracy of these models and low dependence on the quality of incoming information are explained by the minimal participation of an expert during its configuration. The fuzzy models built using the algorithms by Mamdani and Sugeno yield a greater error of 3–4 %. Oure findings could be used to assess the remaining or spent resource of hydrogenerators, the probability of their failure over a time interval, and to execute the risk-oriented control over an electricity energy system and its subsystems
Highlights
Modern operating conditions of electric power systems (EPS) require a comprehensive approach to the assessment of the technical condition (TC) of equipment in real time without disconnecting them from a power grid
Estimating the TC of a hydrogenerator based to their inherent fuzzy inference algorithms, have the smallest on the designed fuzzy models dependence on the interval variability of input values for the local states of a hydrogenerator’s nodes
Assessment of the overall TC of a hydrogenerator is performed under conditions of fuzzy output data, which are obtained from fuzzy models for evaluating the states of local nodes in a hydrogenerator
Summary
Modern operating conditions of electric power systems (EPS) require a comprehensive approach to the assessment of the technical condition (TC) of equipment in real time without disconnecting them from a power grid. The above factors indicate that the task on the integra ted estimation of the state of a hydrogenerator contains a significant number of uncertainties in its statement Solving problems with such uncertainties is in the field of fuzzy models and algorithms that are capable of taking them into consideration. The relevance of this task is defined by that the lack of reliable quantitative assessment of the technical condition of a hydraulic generator makes it impossible to assess the reliability of EPS operation and to determine the risk of an emergency in it. When compared with other EPS elements, hydrogenerators remain insufficiently studied in terms of their TC and reliability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Eastern-European Journal of Enterprise Technologies
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
