Search Results

Neural networks (NN) for marine engines, using raw measurement data from laboratory measurements, are developed and verified. These models can be utilized as virtual sensors of engine-out NOx emissions and lambda (λ). Investigations for the optimal NN configuration targeting models were carried so they can capture the dynamic behavior of a marine diesel engine, can generalize within the training range, and have the minimum complexity due to execution performance and portability reasons. Two configurations of NNs are investigated, the recurrent (RNN) and the time-delay neural network (TDNN). The resulting NN models are deployed on a prototype engine control unit (ECU) platform and are validated in real time for operating points and patterns that are not included in the training dataset. The real-time validation shows that the predicted quantities remain consistent in most operating areas and the dynamic behavior of the system is captured and reproduced accurately.

A novel semi-analytical solution has been developed for the calculation of the static and dynamic response of an off road tire interacting with a deformable terrain, which utilizes soil parameters independent of the size of the contact patch (size-independent). The models involved in the solution presented, can be categorized in rigid and/or pneumatic tires, with or without tread pattern. After a concise literature review of related methods, a detailed presentation of the semi-analytical solution is presented, along with assumptions and limitations. A flowchart is provided, showing the main steps of the numerical implementation, and various test cases have been examined, characterized in terms of vertical load, tire dimensions, soil properties, deformability of the tire, and tread pattern. It has been found that the proposed model can qualitatively capture the response of a rolling wheel on deformable terrain.