Memristor-Based Long and Short-Term Memory Network Models for Optimal Prediction in IoT

The operational integrity and rotational accuracy of bearings are critical in maintaining the reliability of precision devices within IoT systems. In order to improve the efficiency and accuracy of bearing fault diagnosis, a portable advanced bearing fault diagnosis model for IoT applications is proposed. It leverages a novel long short-term memory (LSTM) neural network architecture augmented with memristor technology for enhanced computational efficiency. In this work, a hardware neural network capable of running LSTM is designed, enabling low-power, fast and parallel computation. The circuit comprises three modules: 1) the weight calculation module; 2) the activation function module; and 3) the output module. The weights of the neural network are optimized and adjusted using the double-population jackal optimization algorithm. This algorithm performs convex lens imaging on the jackal population, applies reverse learning, and divides them into elite and ordinary jackals based on fitness values. It integrates the whale algorithm and cosine algorithm to strengthening the optimization ability of the jackal algorithm. Finally, the model is validated using the dataset from Paderborn University (PU). The results indicate that the accuracy of the model exceeds 96% for all four fault types. The findings underscore the potential of this model in powering the next generation of portable diagnostic tools for consumer electronics within the IoT framework.