The widespread incorporation of Internet of Things (IoT) devices in various systems such as mobile phones, vehicles, and security systems is used to collect data. These large volumes of data can be used to train models to make predictions about various things. One such application that uses data from IoT devices is called predictive maintenance. Predictive maintenance involves collecting data from machines and using algorithms to analyze the machine’s condition or determine if the machine requires maintenance or repairs. The work in this paper presents an algorithm to perform predictive maintenance by detecting potential faults, and the algorithm is tested for the cooling system of a bus. We also generate a synthetic time series dataset to simulate normal buses, and buses with underlying intermittent faults and gradual deterioration that would not be detected by the standard maintenance systems. The data is used to train clustering models that identify deterioration patterns and detect faults before the deterioration patterns result in failure or breakdowns.