The article presents an identification method of the model of the ball-and-race coal mill motor power signal with the use of machine learning techniques. The stages of preparing training data for model parameters identification purposes are described, as well as these aimed at verifying the quality of the evaluated model. In order to meet the tasks of machine learning, additive regression model was applied. Identification of the additive model parameters was performed on the basis of iterative backfitting algorithm combined with nonparametric estimation techniques. The proposed models have predictive nature and are aimed at simulation of the motor power signal of a coal mill during its regular operation, startup and shutdown. A comparative analysis has been performed of the models structured differently in terms of identification quality and sensitivity to the existence of an exemplary disturbance in the form of overhangs in the coal bunker. Tests carried out on the basis of real measuring data registered in the Polish power unit with a capacity of 200 MW confirm the effectiveness of the method.

This paper presents a study on applying machine learning algorithms for the classification of a two-phase flow regime and its internal structures. This research results may be used in adjusting optimal control of air pressure and liquid flow rate to pipeline and process vessels. To achieve this goal the model of an artificial neural network was built and trained using measurement data acquired from a 3D electrical capacitance tomography (ECT) measurement system. Because the set of measurement data collected to build the AI model was insufficient, a novel approach dedicated to data augmentation had to be developed. The main goal of the research was to examine the high adaptability of the artificial neural network (ANN) model in the case of emergency state and measurement system errors. Another goal was to test if it could resist unforeseen problems and correctly predict the flow type or detect these failures. It may help to avoid any pernicious damage and finally to compare its accuracy to the fuzzy classifier based on reconstructed tomography images – authors’ previous work.

Research focused on integration of machine operators with information flow in manufacturing process according to Industry 4.0 requirements are presented in this paper. A special IT system connecting together machine operators, machine control, process and machine monitoring with companywide IT systems is developed. It is an answer on manufacture of airplane industry requirements. The main aim of the system presented in the article is full automation of information flow between a management level represented by Integrated Management IT System and manufacturing process level. From the management level an information about particular orders are taken, back an on-line information about manufacturing process and manufactured parts are given. System allows automatic identification of tasks for machine operator and particular currently machined part. Operator can verify information about process and tasks. System allows on-line analyzing process data. It is based on information from machining acquired: machine operator, process and machine monitoring systems and measurement devices handled by operator. Process data is integrated with related order as a history of particular manufactured part. System allows for measurement data analysis based on Statistical Process Control algorithm dedicated for short batches. It supports operator in process control. Measurement data are integrated with order data as a part of history of manufactured product. Finally a conception of Cyber-Physical Systems applying in integrated Shop Floor Control and Monitoring systems is presented and discussed.