Force measurement and force prediction using scaled models is important in aerodynamics to understand the behavior of actual aerial vehicles under actual working conditions. An important part of force measurement is force calibration that involves observing the behavior of the force balance under application of loads. Dynamic calibration is usually performed on the force balance before actual shock tunnel testing of the balance and it involves application of sudden loads on the model and measuring the responses using sensors. This paper describes the dynamic calibration of an accelerometer force balance housed in a delta wing model and impulse forces are applied axially at three locations of the of the model with a tri-axial accelerometer being fixed inside the model. The prediction of the input forces was performed using deconvolution and adaptive neuro-fuzzy inference system (ANFIS) and the accuracy of the predicted forces have been compared with each other and with the experimental forces.