This paper gives an overview of different methods for automated fault detection. Emphasis will be put on the properties of model based techniques (which we will further divide into analytical model based and knowledge based), multivariate statistical process control and machine learning techniques. The machine learning techniques are not traditionally viewed as a standard method for fault detection, so they are especially highlighted in this paper. Each method is presented in detail, and we will also discuss alternative extensions for various applications. The paper is ended by proposing to use machine learning techniques as a robust and well-functioning method in general.