Modeling is a fundamental step in plant optimization and simulation. In this work, a new technique for modeling a gas-solid heterogeneous fixed-bed reactor is developed. Gas diffusion into the solid catalyst pellets requires solving the mass balance equations inside the catalyst. The computational load needed can be quite time-consuming due to system complexities and nonlinearities. This bottleneck prevents on-line optimization of the process. In this work, a trained three-layer neural network model is used to replace major parts of these computations. The model is then incorporated within the overall model of an adiabatic fixed-bed reactor to produce dimethyl ether (DME) from methanol dehydration over solid acidic catalysts. The performance of the reactor simulated using this procedure indicated good agreement with its experimental operation. Then an optimizer is employed to determine the best feed conditions. The proposed strategy can be applied to any heterogeneous fixed-bed reactor.