This paper presents the development of a methodology to detect and evaluate faults in cable-stayed towers, which are part of the infrastructure of Brazil’s interconnected electrical system. The proposed method increases system reliability and minimizes the risk of service failure and tower collapse through the introduction of predictive maintenance methods based on artificial intelligence, which will ultimately benefit the end consumer. The proposed signal processing and interpretation methods are based on a machine learning approach, where the tower vibration is acquired from accelerometers that measure the dynamic response caused by the effects of the environment on the towers through wind and weather conditions. Data-based models were developed to obtain a representation of health degradation, which is primarily based on the finite element model of the tower, subjected to wind excitation. This representation is also based on measurements using a mockup tower with different types of provoked degradation that was subjected to ambient changes in the laboratory. The sensor signals are preprocessed and submitted to an autoencoder neural network to minimize the dimensionality of the resources involved, being analyzed by a classifier, based on a Softmax configuration. The results of the proposed configuration indicate the possibility of early failure detection and evolution evaluation, providing an effective failure detection and monitoring system.

Summary: The oil and gas industry uses very expensive electrical submersible pumps (ESPs) to lift oil to the surface. It is common for the ESP to operate with a biphasic gas-liquid flow. However, large amounts of gas inside the pump generate instabilities, such as surges and gas locks. If operated for a long time under such instabilities, the performance of the ESP can decrease significantly, causing premature deterioration, which can lead to heavy losses and even a complete stoppage of production. To reduce the occurrence of this unstable operation, the research presented here proposes an adaptive controller based on the monitoring of the biphase condition. A nonlinear ESP model represents the pump behavior for a variable percentage of the two-phase flow, used by the controller learning complex adaptive technique, which is based on a genetic algorithm to generate a set of rules to keep the ESP in safe operating conditions. At the beginning of the training, the adaptive complex system generated erratic behavior; however, over time, it came to represent more precise rules, bringing performance to stable conditions. Furthermore, if the ESP eventually reaches a harmful condition, the adaptive controller takes action to return it to a safe condition. The result of the simulated tests shows that the complex adaptive controller can acquire enough knowledge after training to keep an ESP working in stable conditions, increasing the life of the production equipment and avoiding sudden stops during oil lifting.