The classic approach to evaluate the probability that an operational system is capable to operate satisfactorily and successfully perform the formulated tasks is based on availability that is coefficient which is determined based on the history of down-time and up-time occurring, while the risk-degree of down-time occurring strongly depends on the actual operational state of a system. The intelligence computational methods enable to create the diagnosis tools that allow to formulate the prognosis of operating time of a system and predict of failure occurring based on the past and actual information about system's operational state, especially genetic fuzzy systems (GFSs) that combine fuzzy approximate reasoning and capability to learn and adaptation. The paper presents the fuzzy rule-based inference system used to predict the operating time of exploitation system according to the specified operational conditions. The proposed algorithm was used to design the fuzzy model applied to estimate the operating time of a system between the actual time and predicted time of the next failure occurring under the stated operational parameters. The fuzzy system allows to prognoses the time of the predicted failure based on the operational parameters which are used to evaluate the actual operational state of the system. The attention in the paper is focused on the evolutionary computational techniques applied to design the fuzzy inference system. The paper proposes the genetic algorithm based on the Pittsburgh method and real-valued chromosomes used to optimize the knowledge base and parameters of antecedents and conclusions of the Takagi-Sugeno-Kang (TSK) fuzzy implications. The paper is the contribution to the GFSs, which aim is to find an appropriate balance between accuracy and interpretability, and also contribution to the research field on the diagnosis methods based on soft computing techniques. The evolutionary algorithm was tested for designing the fuzzy operating time predictor of material handling device.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.