Transmission lines constitute critical energy infrastructure in an electrical installation, as they ensure a reliable and efficient energy transition. However, they are prone to breakdowns, due to their significant length and their continuous exposure to atmospheric conditions. In addition, the photovoltaic energy sources integration can modify their behavior, which contributes to a greater increase in the breakdowns probability. Short circuits are the most common and dangerous fault type, leading in the majority of cases to other fault types. This research describes the development of a new intelligent system that consists of three stages. The first stage aim is to identify whether there is a short circuit or not using a binary SVM. In the second stage, an innovative expert system is used to determine the short circuit type among 11 potential faults. The output of this system depends on the inputs obtained by four binary SVM, each of which determines the fault presence or absence in a phase. The third stage is responsible for estimating the exact fault position in a 100 km transmission line. This stage is made up of 11 universal regressors of type MLP. The proposed system was validated using signals, obtained from a modelled High-Voltage Line with a PV Energy Source (25 kV-50 Hz-100 Km) and processed by the Discrete Wavelet Transform. Statistical metrics (with all p-value < 0.001) validate the proposed system performance with: 100% sensitivity and specificity for the fault detector ; an average sensitivity, specificity, and false alarms of 99.38%, 99.94%, and 0.17%, respectively, for the fault discriminator ; and a 2.66% mean squared error and a 97.80% overall sensitivity for the fault location estimator. These results conclude the proposed approach reliability, demonstrating its potential effectiveness in real-world scenarios.