Predictive maintenance has been employed to reduce costs and production losses prevent any failure before it occurs. The framework proposed in this work performs diesel engine prognosis by evaluating the absolute value of severity using random forest (RF) multilayer perceptron (MLP) neural networks. A database was implemented with 3500 scenarios overcome problem inducing destructive failures en...

Port state control (PSC) is the last line of defense for substandard ships. During a PSC inspection, ship detention most severe result if inspected identified with critical deficiencies. Regarding development prediction models, this paper identifies two challenges: learning from imbalanced data and unlabeled data. The first challenge, data, arises fact that minority ships were detained. second ...

We have developed a conventional benchmark model for the prediction of two days electricity consumption industrial and institutional customers an provider. This task predicting 96 values 15 min per day in one shot is successfully dealt with by dynamic regression that uses Seasonal Trend decomposition method (STL) estimation trend seasonal components based on (approximately) three years real dat...