| Summary: | The work environment of a mobile crane is hazardous where accidents can cause serious injuries or death for workers and non-workers. Therefore, the risk for these accidents should be avoided when possible. One way to avoid the potential accidents is to use mobile crane simulations instead, which removes the risk. Because of this, simulations have been developed to train operators and plan future operations. Mobile crane simulations can also be used to perform research related to mobile cranes, but for the result to be applicable to real-world settings the simulation has to be realistic enough. Therefore, this thesis evaluated an aspect of realism which is the lifting capacity of a mobile crane. This was done by having an artificial neural network train on values from load charts of a real crane, that was then used to predict the lifting capacities based on the boom length and the load radius of the virtual crane. An experiment was conducted in the simulation that collected the predicted lifting capacities which was then compared to the lifting capacities in the load charts of a real crane. The results showed that the lifting capacities could be predicted with little to no deviation except for in a few cases. When conducting the experiment, it was found that the virtual mobile crane could not reach all load radiuses documented in the real load charts. The predicted lifting capacities are concluded to be realistic enough for crane-related research, but should be refined if the lifting capacity plays a key role in the research. Future works such as improving and generalizing the artificial network, and performing the evaluation with user tests are prompted.
|
|---|
