The dataset contains telemetry data from straddle carriers and was used for training and testing machine learning models for detecting overtemperature faults. The data originates from the straddle carriers’ PLC and contains measurements for inverter, motor, and engine temperatures, speed, torque, hydraulic pressure, and various error flags. Ambient temperature readings were also recorded using an on-site weather station and incorporated into the dataset. The dataset was manually labeled to consist of two classes: normal and faulty. Faulty data were identified from SCs involved in six recorded incidents, while data from other SCs operating simultaneously were labeled as normal.