The advent of internet of things has brought a revolution in the amount of data generated in industry. Researchers now have to develop ways to harness such huge amount of data. Thus, a new method called �predictive maintenance� was developed. In this technique, sensor data is used to predict failures so that appropriate actions are taken to save accidents and costs. Artificial neural networks have proven to be excellent tools for prediction. In this work, the echo state network (ESN), which is a new concept of recurrent neural network (RNN), is used to predict failures in turbofan engines. The ESN was developed to solve the complexities of earlier RNNs. However, choosing the right topology and parameters for the ESN is often a difficult problem. Hence, we develop a cuckoo search optimization-based algorithm to optimize the ESN. The approach is compared with three particle swarm optimization methods and two other methods, and it performed better. © 2019, King Fahd University of Petroleum & Minerals.