Partial Discharges are major source of insulation failure in power transformers. Therefore, partial discharge (PD) measurement has been commonly carried out to detect and monitor PD activity in insulation in order to avoid from any catastrophic failure. In this research work, acoustic emission (AE) detection system is used to detect PD in an experimental tank filled with transformer oil. Three different types of PD sources to generate PD in the experimental tank are created from pressboards which are the plain pressboard, the floating metal in the pressboard and the bubble in pressboard. The AE signals due to the occurrence of PD from these sources are captured and recorded. Due to the large number of AE signals to be recorded by the Data Acquisition System, some of these signals may not be stored correctly in the system. Some of these signals may also be affected by the reflection and refraction phenomena, interference and attenuation of the AE signals. Hence, the preprocessing and validation of the acquired AE signals from the experimental setup are also explored in this paper. Finally, the valid AE signals due to three different types of PD sources are identified for further analysis.