This paper highlights the importance of considering required control rules from the real-world implementation inoffline optimal control optimisations used to generate online energy management strategies (EMS). The controlrules are constraints on the optimal control problem. If not considered, the control optimisation results do notrepresent the reality and the EMS will have poor performance. In this paper, a neural network predicts the optimalcontrol decisions whenever the rules are not taking place. It is a rule- and neural network-based energymanagement strategy. A limitation to the use of neural networks as part of the EMS is that they do not ensurestable behaviour outside the region they were trained for. In the real application – in this case, a hybrid wheelloader – they will be deployed alongside control rules to ensure safety and reasonable operation. Hence theimportance of implementing the rules in the optimal control problem. Results show that better performance of theEMS is achieved if the rules from the application are considered in the optimal control problem.