A Fault Detection System Based on two Complementary Methods and Continuous Updates

We propose a system for fault detection, which is continuously updated during the course of application. The system is based on two methods, where the first method is chosen to have high sensitivity and the second method is chosen to have high specificity. Both methods are updated through a continuous feedback, which can be provided by the user of the system. The combination of two complementary methods with feedback allows for the fault detection system to quickly adapt to changes in the boundary conditions of the application and to detect novel faults while keeping the amount of required feedback low. We illustrate the implementation and the performance of the proposed fault detection system with a real-world example using data from building services.