Abstract: The present invention relates to a process and system capable of processing large volumes of petroleum samples to withdraw a sufficient amount for water characterization in petroleum, without the need for sample fractionation and subsequent volume recomposition. This reduces the number of steps and processing time, with low risk of contamination or decharacterization due to losses of important fractions. This process is carried out through the system consisting of the insulated and heated reservoir (1), temperature transmitter (2), temperature controller (3), electric resistance (4), flow control valve (5), blocking valves (6a; 6b; 6c; 6d), temperature indicator (7), self-desludging stacked plate centrifuge (8), oil sampling point (9), water sample extraction system (10), capillary tube (11), vacuum pump (12), water sample container (13), oil outlet (15), water inlet for activating the desludging (16), cleaning fluid inlet (17), outlet or vent (18).

Abstract: Examples of methods for fault prediction model training with audio data are described herein. In some examples, service event data and audio data corresponding to client devices are received. In some examples, a portion of the audio data is selected based on the service event data. In some examples, a machine learning model is trained for fault prediction based on the portion of audio data.