Electrical submersible pumps (ESPs) are considered the second-most widely used artificial lift method in the petroleum industry. As with any pumping artificial lift method, ESPs exhibit failures. The maintenance of ESPs expends a lot of resources, and manpower and is usually triggered and accompanied by the reactive process monitoring of multivariate sensor data. This paper presents a methodology to deploy the principal component analysis and extreme gradient boosting trees (XGBoosting) in predictive maintenance in order to analyze real-time sensor data to predict failures in ESPs. The system contributes to an efficiency increase by reducing the time required to dismantle the pumping system, inspect it, and perform failure analysis. This objective is achieved by applying the principal component analysis as an unsupervised technique; then, its output is pipelined with an XGBoosting model for further prediction of the system status. In comparison to traditional approaches that have been utilized for the diagnosis of ESPs, the proposed model is able to identify deeper functional relationships and longer-term trends inferred from historical data. The novel workflow with the predictive model can provide signals 7 days before the actual failure event, with an F1-score more than 0.71 on the test set. Increasing production efficiencies through the proactive identification of failure events and the avoidance of deferment losses can be accomplished by means of the real-time alarming system presented in this work.

In this study antimony concentration was analyzed in 30 plastic items (from polyethylene terephthalate (PET) bottles and e-waste) directly by X-ray fluorescence spectroscopy (XRF) spectroscopy. PET samples were digested in a microwave oven with aqua regia. The plastic components deriving from e-waste followed three parallel routes: 1. microwave digestion using different acids (aqua regia, 18 M H₂SO₄, 12 M HCl and 6 M HCl); 2. conversion into ash (at 600 °C) and then microwave digestion with aqua regia, and 3. extraction with 12 M HCl at room temperature for different durations (2 h and 24 h). Results showed that antimony extraction yields from PET were between 57% and 92%. Antimony extraction from e-waste plastics was more challenging: aqua regia was inefficient for poly (acrylonitrile butadiene styrene) (ABS) samples (extraction yield was about 20% only), while on a mixture of ABS and polycarbonate (PC), aqua regia, H₂SO₄ and HCl exhibited equivalent performances (~21%). Ashed samples returned yields ranging from 20% to over 50%. Room temperature extraction on e-waste plastics obtained lower extraction efficiencies, yet longer incubation durations lead to higher yields. In conclusion, the main challenge associated with antimony mining from plastic waste could be its heterogeneous composition; therefore, the development of reference analytical procedures is highly needed.