Among an electricity provider’s non-technical losses, electricity theft has the most severe and dangerous effects. Fraudulent electricity consumption decreases the supply quality, increases generation load, causes legitimate consumers to pay excessive electricity bills, and affects the overall economy. The adaptation of smart grids can significantly reduce this loss through data analysis techniques. The smart grid infrastructure generates a massive amount of data, including the power consumption of individual users. Utilizing this data, machine learning and deep learning techniques can accurately identify electricity theft users. In this paper, an electricity theft detection system is proposed based on a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) architecture. CNN is a widely used technique that automates feature extraction and the classification process. Since the power consumption signature is time-series data, we were led to build a CNN-based LSTM (CNN-LSTM) model for smart grid data classification. In this work, a novel data pre-processing algorithm was also implemented to compute the missing instances in the dataset, based on the local values relative to the missing data point. Furthermore, in this dataset, the count of electricity theft users was relatively low, which could have made the model inefficient at identifying theft users. This class imbalance scenario was addressed through synthetic data generation. Finally, the results obtained indicate the proposed scheme can classify both the majority class (normal users) and the minority class (electricity theft users) with good accuracy.

Efficient fault diagnosis of electrical and mechanical anomalies in induction motors (IMs) is challenging but necessary to ensure safety and economical operation in industries. Research has shown that bearing faults are the most frequently occurring faults in IMs. The vibration signals carry rich information about bearing health conditions and are commonly utilized for fault diagnosis in bearings. However, collecting these signals is expensive and sometimes impractical because it requires the use of external sensors. The external sensors demand enough space and are difficult to install in inaccessible sites. To overcome these disadvantages, motor current signal-based bearing fault diagnosis methods offer an attractive solution. As such, this paper proposes a hybrid motor-current data-driven approach that utilizes statistical features, genetic algorithm (GA) and machine learning models for bearing fault diagnosis. First, the statistical features are extracted from the motor current signals. Second, the GA is utilized to reduce the number of features and select the most important ones from the feature database. Finally, three different classification algorithms namely KNN, decision tree, and random forest, are trained and tested using these features in order to evaluate the bearing faults. This combination of techniques increases the accuracy and reduces the computational complexity. The experimental results show that the three classifiers achieve an accuracy of more than 97%. In addition, the evaluation parameters such as precision, F1-score, sensitivity, and specificity show better performance. Finally, to validate the efficiency of the proposed model, it is compared with some recently adopted techniques. The comparison results demonstrate that the suggested technique is promising for diagnosis of IM bearing faults.

Rolling element bearings cause the largest number of failures in induction motors. Predicting an impending failure and estimating the remaining useful life (RUL) of a bearing is essential for scheduling maintenance and avoiding abrupt shutdowns of critical systems. This paper presents a hybrid technique for bearing prognostics that utilizes regression-based adaptive predictive models to learn the evolving trend in a bearing's health indicator. These models are then used to project forward in time and estimate the RUL of a bearing. The proposed algorithm addresses some key issues in existing methods for bearing health prognosis that affect their prognostic performance, specifically determining the time to start prediction (TSP), handling random fluctuations in a bearing's health indicator, and setting a dynamic failure threshold. The proposed algorithm is validated on publicly available bearing prognostics data from the Center for Intelligent Maintenance Systems. Experimental results show that the proposed approach is effective in determining an accurate TSP and failure threshold, as well as handling random fluctuations. Moreover, this approach achieves excellent prognostic performance and estimates the RUL of bearings within the specified error bounds, even at points very close to the TSP, where traditional methods yield relatively poor RUL estimates.

Bearing fault diagnosis is imperative for the maintenance, reliability, and durability of rotary machines. It can reduce economical losses by eliminating unexpected downtime in industry due to failure of rotary machines. Though widely investigated in the past couple of decades, continued advancement is still desirable to improve upon existing fault diagnosis techniques. Vibration acceleration signals collected from machine bearings exhibit nonstationary behavior due to variable working conditions and multiple fault severities. In the current work, a two-layered bearing fault diagnosis scheme is proposed for the identification of fault pattern and crack size for a given fault type. A hybrid feature pool is used in combination with sparse stacked autoencoder (SAE)-based deep neural networks (DNNs) to perform effective diagnosis of bearing faults of multiple severities. The hybrid feature pool can extract more discriminating information from the raw vibration signals, to overcome the nonstationary behavior of the signals caused by multiple crack sizes. More discriminating information helps the subsequent classifier to effectively classify data into the respective classes. The results indicate that the proposed scheme provides satisfactory performance in diagnosing bearing defects of multiple severities. Moreover, the results also demonstrate that the proposed model outperforms other state-of-the-art algorithms, i.e., support vector machines (SVMs) and backpropagation neural networks (BPNNs).