Fingerprinting is one of the most used biometrics for people identification, it relays on image processing and classification algorithms. In this work we propose and test a framework that enables fingerprint detection using a set of image pre-processing algorithm. Concerning the features extraction, we propose the use of the number of bifurcations in image localities, and we propose the use of Artificial Neural Network (ANN) for the classification. The performance of our framework is evaluated for three different activation functions and show that we can reach an accuracy of 81%.

In this paper, a data mining based methodology for process identification from historical data was proposed. Thereon, it considers the phases of process understanding, data collection, data preparation, data modeling, and model evaluation. As some parts of historical data are irrelevant, a data selection step, based on the Gaussian Mixture Model (GMM) clustering algorithm, was considered. Additionally, the methodology includes a data informativity step to study the richness of data. In this regard, the condition number (CN) and the extended CN for ridge regression (RR CN) were used. To evaluate the approach, 2 years of industrial thickener historical data were used. Thereafter, data were prepared and an ARX (Auto-Regressive with eXogenous inputs) model structure was adopted to identify the model. To estimate input delays, Granger causality was used. As for fit criteria, least square regression was tested and compared to ridge regression as a less sensitive method to multicollinearity. The results were then evaluated based on the 20-step ahead prediction and compared to existing methods. In this context, the proposed approach gave the best results with an R² of 98.11% and 62.70% for 1 and 20-step ahead predictions, respectively.

In the mining industry, thickeners are used to increase density of slurries by removing water. When a thickener is in operation, the underflow slurry density should follow a given setpoint and stay inside a boundary layer. In general, thickeners are manually controlled. However, industrial experience has shown that manual control is not sufficient. For this reason, an advanced process control strategy is proposed in this paper. On the one hand, using historical data, a linear dynamic model of the studied thickener is developed. In this regard, data is collected, prepared, and data informativity is studied to ensure model identifiability and interpretability. On the other hand, a model predictive control is designed to control the process by manipulating the feed and the underflow slurry flowrates. The simulation results show that the method can be successfully used to control the underflow slurry density in the presence of feed variations and unmeasured disturbances.

Sulfuric acid is a basic chemical used intensively in many industrial processes. To produce the sulfuric acid, there are two major processes: the lead chamber process and the current contact process. The first step in the latter process consists of burning sulfur in the air to form sulfur dioxide. In this paper, modeling and simulation of an industrial sulfur burning unit are performed. For the modeling task, an adiabatic conversion reactor was used for the sulfur burner, a centrifugal pump for the liquid sulfur pump, and an air compressor for the air supply. To simulate the model, the Unisim Design R451 simulator was used. Then, the simulation results were validated using industrial data. In addition, a parametric study was performed to analyze the effects of the inputs' variations on the sulfur burner outlet. The proposed model can be used to develop a digital twin of the studied sulfur burner to perform real-time simulations and test new control and optimization strategies.