Detecção De Vazamento Utilizando Técnicas De Machine Learning

Abstract

Data Science and advanced data analytics are technologies that enable the development of low cost solutions with a high degree of customization. Based on that, this article presents a leakage detection system in a slurry pipeline using a combination of machine learning techniques. The techniques used to detect leakage were based on artificial intelligence, a machine learning model for the energy balance of the pipe combined with an anomaly detection technique approach. The system predicts energy at one point of the pipe based on another point, in order to infer if there is loss of energy (leakage) on it. Although the machine learning model used is a simple parametric linear regression and this technique is well-known in the artificial intelligence domain, its competitive differential is the use of an open source machine learning platform to implement them, which allows clients to have a customized model instead of using costly instrumentation with embedded systems. This work was fully implemented in a ore tailings pipeline of one of the biggest Brazilian iron ore companies. It has already detected several real leakage occurrences, greater than 70 m³/h with only three to five leak false alarms per month. Based on these results, this solution can be considered as an alternative solution for leak detection in short length pipelines, especially for the ones that transport iron ore tailings. Although it can detect leakage between a pipe sections, it cannot detect the exact point of the leak that motivates further development, such the use of wavelet package technique.

A New Pressure-Based Modeling Approach for Early Leak Detection in Gas Processing Plants Using Machine Learning

“…The objectives are to develop a model for gas leak detection using machine learning. To generate a safety notification and improved flow system based on leak detection findings [10][11][12].…”