Abstract
The main means of mechanization of technological processes of the functioning of sea and river ports, dockyards are ship repair enterprises are the lifting machines, and in particular, portal cranes (PC). Operability, performance and mode of operation of such cranes depend on their technical condition which is determined by the value of the defects (cracks, deformation, breaks of the elements of the tap metal construction, etc.). This approach in the diagnosis of the crane ignores the fact that such defects during operation of the PC are affected by a number of factors (technical, natural, human, loads characteristics etc.) which may affect their further development and thus result in an unusable state of the crane and thereby form an uncertain events system. This requires solving the problem of probabilistic inference which refers to the calculations of the probability of events based on the known probabilities of the other related events. To solve these problems several methods are proposed (output based on probability trees, probability trees, goal trees, etc.), however, such techniques have certain disadvantages along with their positive qualities. For example, when the number of uncertain events systems increase, the dimensions of the trees grow so fast that it becomes difficult to operate with them. Therefore, the approach based on the assurance networks seems promising to analyze such situations. This approach is demonstrated on the example of the problem of forecasting of the port gantry cranes performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.