摘要：The study presents an optimization method of sliding windows parameters selection in the features extraction procedure in cyber physical systems during data processing of the technical condition of energy and electric infrastructure facilities. The method is based on utilizing genetic algorithm and objective functions related to the quality of the classification of the defects by hazard degree. Proposed method was verified on the experimental data acquired from the technical condition monitoring of the vertical oil tanks. The results obtained from the experiment confirm the proposal that this method can be applied for effectively solving problems related to features extraction in monitoring, risk management and classification of maintenance defects in the power and electrical engineering facilities.
其他摘要：The study presents an optimization method of sliding windows parameters selection in the features extraction procedure in cyber physical systems during data processing of the technical condition of energy and electric infrastructure facilities. The method is based on utilizing genetic algorithm and objective functions related to the quality of the classification of the defects by hazard degree. Proposed method was verified on the experimental data acquired from the technical condition monitoring of the vertical oil tanks. The results obtained from the experiment confirm the proposal that this method can be applied for effectively solving problems related to features extraction in monitoring, risk management and classification of maintenance defects in the power and electrical engineering facilities.
