Investigation on Online DGA Monitoring to Determine Transformer Health Index Using Machine Learning

The Dissolve Gas Analysis (DGA) to determine the ageing and degradation of the transformer is standard and routine periodic maintenance. In general, there are two DGA analysis methods which are conventional (lab-based) and online monitoring. DGA monitoring will be able to access to detect incipient fault and transformer failure. Several techniques are available to analyse, interpret and diagnose the DGA result, such as IEEE standard, IEC 60599 standard, Key Gas Method, and Duval methods. There are several Machine Learning (ML) techniques has been explored such as Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Neural Neighbours (KNN), Random Neural Network (RNN), and Fuzzy Logic for determining the transformer condition, including fault diagnostic and fault detection. However, there are unexplored studies to combine the commercial device to determine the Health Index (HI) of Transformer. In this study, an ML method with the available input feature from the commercial device to the network is trained to determine the HI. In general, the benchmark dataset from the existing work is employed to validate the proposed investigation. There are 730 datasets comprising five different classes; 1) Very Good, 2) Good, 3) Fair, 4) Poor, 5) Very Poor in determining the HI of a transformer. Conventional rule to partition the train and testing dataset with a 70:30 ratio is employed in this study. The maximum accuracy results and method for 1) M1 is 66.67% for ANN, 2) M2 is 68.49% for ANN, 3) M3 is 76.71% for KNN, 4) M5 is 76.26% for ANN, 5) M6 is 79.00% for ANN and 6) M7 is 86.30% for ANN. In conclusion, the multi-gas device will have a good accuracy performance and provide a good HI indicator to classify the condition of the transformer, which can be used for preventive maintenance.

5G Network Simulation in Smart Cities using Neural Network Algorithm

The speed of internet has increased dramatically with the introduction of 4G and 5G promises an even greater transmission rate with coverage outdoors and indoors in smart cities. This indicates that the introduction of 5G might result in replacing the Wi-Fi that is being currently used for applications such as geo-location using continuous radio coverage there by initiating the involvement of IoT in all devices that are used. The introduction of Wi-Fi 6 is already underway for applications that work with IoT, smart city applications will still require 5G to provide internet services using Big Data to reduce the requirement of mobile networks and additional private network infrastructure. However, as the network access begins to expand, it also introduces the risk of cyber security with the enhanced connectivity in the networking. Additional digital targets will be given to the cyber attackers and independent services will also be sharing access channel infrastructure between mobile and wireless network. In order to address these issues, we have introduced a random neural network blockchain technology that can be used to strengthen cybersecurity in many applications. Here the identity of the user is maintained as a secret while the information is codified using neural weights. However, when a cyber security breach occurs, the attacker will be easily tracked by mining the confidential identity. Thus a reliable and decentralized means of authentication method is proposed in this work. The results thus obtained are validated and shows that the introduction of the random neural network using blockchain improves connectivity, decentralized user access and cyber security resilience.