Research engines with optical access can assist traditional engine development and optimization by providing first-hand information of in-cylinder combustion process. However, the fragility of the optical engine components (e.g., the see-thru windows are usually made from fused silica) limit the engine operating conditions such as the maximum in-cylinder pressure and pressure rise rate. To make it easier to determine if a particular engine operating condition can be used for optical investigations, a back-propagation artificial neural network model was built to provide the values of pressure-based parameters of interest for engine safety. The training data came from steady-state engine experiments that changed spark timing, mixture equivalence ratio, and engine speed, but using the non-optical configuration of the engine to widen the testing conditions. The comparison between model predictions and experimental data indicated that the well-trained artificial neural network model can provide fast and consistent results, making it an easy-to-use tool for designing future optical engine investigations.