In the era of big data, the growing volume of data in electrical systems has led to a rise in electric theft incidents, posing challenges to grid security. This paper introduces a detection method using the Sine chaotic genetic algorithm to optimize multilayer Backpropagation (BP) neural networks. Initially, a comprehensive dataset is compiled through extensive data collection. A multilayer BP neural network is then trained on this dataset for automated theft identification. Leveraging the Sine chaotic genetic algorithm further enhances network performance. Experimental results show an 88% prediction accuracy, offering improved accuracy, speed, and usability over traditional methods.