Corona and Arcs Electric Discharge (ED) constitute a significant threat to electrical safety, the apparatus, and the stability of a power system due to the aging and material degradation in the power apparatus. Hence, an early preventive approach must be performed effectively for a pre-fault threat. Recent developed systems include high performance, efficient, and smart characteristics for insulation condition monitoring of ED detection, localization, and recognition. However, there are constraints in the implementation due to the extensive data and memory system required for smart signal recognition. Multiple sensors are required to improve signal detection and localization from multiple ED sources concurrently. Furthermore, the implementation requires high costs for new upgrading works and installation to replace the existing monitoring system. In this paper, a pre-fault monitoring system utilizing a Perceptron-based UHF Sensor called Single Perceptron smart Sensor (SPSS) is developed for the Corona and Arcs ED localization. The SPSS, integrating a 2-element Linear Array Antenna with a Single Perceptron-Artificial Neural Network (SP-ANN). The SPSS antenna model is an amplitude-weighting antenna transceiver. It detects and localizes the ED signals based on the Direction of Arrival (DOA) angle. Frequency scanning is possible for SPSS, which does not require any phase-shifter unit, but the transmitted frequency from a desired DOA can be used for beam steering. The novelty of this work is that the SP-ANN algorithm has replaced the use of a phase shifter to shift the array antenna electronically. Thus, it has successfully suppressed the cost and complexity of the localization system, providing a speedy localization within seconds. The accuracy of the pre-fault monitoring is tested for the Corona and Arcs ED at a sampling frequency of 300 MHz to 3 GHz. The SPSS has revealed an average error of 2° for signal localization with minimal computational complexity.