According to the relation between feed servo motor current and cutting force, online monitoring of cutting force is realized by measuring the motor current. For the delay of current signal to cutting force, a method with artificial neural network is proposed. Subtracting the geometric error from the total error which is measured with a laser interferometer within the working volume, the cutting force induced error is achieved. With the multi-body system theory and the back-propagation neural network, cutting force induced deflection prediction model is established, and an error compensation system is developed. Milling experiments are done to validate the prediction model and the system. The results show that force error is reduced markedly, and the method for prediction and compensation is of great important to precision manufacturing.