This paper evaluates the performance of six different machine learning (ML) algorithms for classifying power quality disturbances (PQDs), with statistical features extracted using discrete wavelet transform (DWT) as feature input. The statistical features have been extracted from coefficients of multi-resolution analysis (MRA) using four different mother wavelets: Daubechies 4 (‘db4’), ‘haar’, Discrete Meyer (‘dmey’), Coiflets 4 (‘coif4’). The performance analysis has been carried out with 5,500 synthetic signals pertaining to eleven different PQDs generated in accordance with IEEE 1159-2019. Moreover, the performance of the classifiers trained with synthetic signals has been investigated under the influence of unseen noisy signals, hardware PQD signals obtained from the experimental setup, and real PQD events. The analysis indicates that the performance of the extra tree (ET) classifier with the features extracted using ‘haar’ as a mother wavelet is superior and robust in comparison to other classifiers, viz k-nearest neighbor (kNN), random forest (RF), decision tree (DT), logistic regression model (LRM), and gaussian naïve bayes (GNB) with features extracted using different mother wavelets. Furthermore, the ‘haar-ET’ based technique demonstrated remarkable performance in classifying PQDs, showing strong generalization to both unseen hardware and noisy signals, and achieving consistent results when tested with real PQD events.

An advanced IoT-based Liquefied Petroleum Gas (LPG) cylinder monitoring and safety system is presented in this work. The proposed technique provides continuous monitoring of residential gas usage and detects any potential leakage. It utilizes an MQ135 gas sensor for gas leakage detection, a load cell to monitor the weight of the cylinder, and a DHT22 sensor for temperature sensing. The sensors are mounted on a customized trolley for domestic LPG cylinders. All the sensors are connected to a NodeMCU microcontroller, which exchanges sensor data with a cloud platform using HTTP GET and POST methods to transmit the data to a cloud-based MySQL database. Unlike other existing methods, the proposed approach does not necessitate any modifications to the existing setup, which includes the gas cylinder, regulating valve, and distribution pipe. Furthermore, a mobile application that emphasizes the needs of the user is developed to enable a wider range of functionalities using cloud data collected from the sensors. The software facilitates the real-time monitoring of gas levels, provides comprehensive usage records for daily, weekly, and monthly intervals, issues immediate alarms in the event of gas leakage and low gas levels, and detects any unauthorized movement of the LPG cylinder, such as theft. The proposed technique not only improves user safety but also streamlines gas cylinder management with predictive analytics based on gas consumption trends and projected days of usage. Moreover, the application includes functionality that automatically orders a new cylinder with the vendor when the gas level drops below a predetermined threshold, therefore ensuring continuous availability of gas supply.

This paper presents a new fault classification technique for Thyristor-Controlled Series-Compensated (TCSC) transmission lines using Support Vector Machine (SVM). The proposed technique is based on the utilization of post-fault magnitude of Rate-of-Change-of-Current (ROCC). Fault classification has been carried out by giving ROCC of three-phases and zero sequence current as inputs to SVM classifier. The performance of SVM as a binary-class, and multi-class classifier has been evaluated for the proposed feature. The validity of the suggested technique has been tested by modeling a TCSC based 400 kV, 300 km long transmission line using PSCAD/EMTDC software package. Based on the above model, a large number of diversified fault cases (41,220 cases) have been generated by varying fault and system parameters. The effect of window length, current transformer (CT) saturation, noise-signal, and sampling frequency have also been studied. It has been found that the proposed technique provides an accuracy of 99.98% for 37,620 test cases. Moreover, the performance of the suggested technique has also been found to be consistent upon evaluating in a 12-bus power system model consisting of a 365 kV, 60 Hz, 300 km long TCSC line. Comparative evaluation of the proposed SVM based technique with other recent techniques clearly indicates its superiority in terms of fault classification accuracy.

This paper presents a phasor-distance based faulty phase detection and fault classification technique for parallel transmission lines. Detection and classification of faulty phase(s) have been carried out by deriving indices from the change in phasor values of current with a distance of one cycle. The derived indices have zero values during normal operating conditions whereas the index corresponding to the faulty phase exceeds the pre-defined threshold in case of occurrence of a fault. A separate ground detection algorithm has been utilized for the identification of involvement of ground in a faulty situation. The performance of the proposed technique has been evaluated for intra-circuit, inter-circuit and simultaneous faults with wide variations in system and fault conditions. The suggested technique has been evaluated for over 23,000 diversified simulated fault cases as well as 14 recorded real fault events. The performance of the proposed technique remains consistent under Current Transformer (CT) saturation as well as different amount and direction of power flow. Moreover, suitability to different power system network has also been studied. Also, faults having fault current less than pre-fault conditions have been detected accurately. The results obtained suggest that it is able to detect faulty phases as well as classify faults within quarter-cycle from the inception of fault with impeccable accuracy. Besides, as modern digital relays have been already equipped with phasor computation facility, phasor-based technique can be easily incorporated with relative ease. At last, a comparative evaluation suggests its superiority in terms of fault classification accuracy, fault detection time, diversify fault scenarios and computational requirement among other existing techniques.