In a structural time series regression model, binary variables have been used to quantify qualitative or categorical quantitative events such as politic and economic structural breaks, regions, age groups and etc. The use of the binary dummy variables is not reasonable because the effect of an event decreases (increases) gradually over time not at once. The simple and basic idea in this paper is to involve a new transition function in a structural time series regression equation model in order to transform the binary dummy variables into a fuzzy set. The main purpose of this paper is to present a new method for endogenous modeling structural breaks in money demand function using fuzzy set. Hence, we model structural breaks in a money demand function via fuzzy set theory, transition functions and binary dummy variables and compare these. After introducing a new transition function, we model money volume shock in 1992 in money demand function. The results indicate that our transition function has better characteristics and accurate results than the binary dummy variable, exponential and logistic transition functions.