Groundwater quality monitoring in the vicinity of drilling sites is crucial for the protection of water resources. Selected physicochemical parameters of waters were marked in the study. The water was collected from 19 wells located close to a shale gas extraction site. The water quality index was determined from the obtained parameters. A secondary objective of the study was to test the capacity of the artificial neural network (ANN) methods to model the water quality index in groundwater. The number of ANN input parameters was optimized and limited to seven, which was derived using a multiple regression model. Subsequently, using the stepwise regression method, models with ever fewer variables were tested. The best parameters were obtained for a network with five input neurons (electrical conductivity, pH as well as calcium, magnesium and sodium ions), in addition to five neurons in the hidden layer. The results showed that the use of the parameters is a convenient approach to modeling water quality index with satisfactory and appropriate accuracy. Artificial neural network methods exhibited the capacity to predict water quality index at the desirable level of accuracy (RMSE = 0.651258, R = 0.9992 and R² = 0.9984). Neural network models can thus be used to directly predict the quality of groundwater, particularly in industrial areas. This proposed method, using advanced artificial intelligence, can aid in water treatment and management. The novelty of these studies is the use of the ANN network to forecast WQI groundwater in an area in eastern Poland that was not previously studied—in Lublin.

The fault diagnosis for maintenance of machines operating in variable conditions requires special dedicated methods. Variable load or temperature conditions affect the vibration signal values. The article presents a new approach to diagnosing rotating machines using an artificial neural network, the training of which does not require data from the damaged machine. This is a new approach not previously found in the literature. Until now, neural networks have been used for machine diagnosis in the form of classifiers, where data from individual faults were required. A new diagnostic parameter rDPNS (Relative Differences Product of Network Statistics) as a function of the machine's shaft order was proposed as a kind of new order spectrum independent of the machine's operating conditions. The presented work analyses the use of the proposed method to diagnose misalignment and unbalance. The results of an experiment carried out in the laboratory demonstrated the effectiveness of the proposed method.

The paper formulates some objections to the methods of evaluation of uncertainty in noise measurement which are presented in two standards: ISO 9612 (2009) and DIN 45641 (1990). In particular, it focuses on approximation of an equivalent sound level by a function which depends on the arithmetic average of sound levels. Depending on the nature of a random sample the exact value of the equivalent sound level may be significantly different from an approximate one, which might lead to erroneous estimation of the uncertainty of noise indicators. The article presents an analysis of this problem and the adequacy of the solution depending on the type of a random sample.

This paper presents the use of artificial neural networks in diagnosing the technical condition of drive systems operating under variable conditions. The effects of temperature and load variations on the values of diagnostic parameters were considered. An experiment was conducted on a testing rig where a variable load was introduced corresponding to the load of the main gearbox of the bucket wheel excavator. The signals of vibration acceleration on the gearbox body, rotational speed, and current consumption of the drive motor for different values of oil temperature were measured. Synchronous analysis was performed, and the values of order amplitudes and the corresponding values of current, speed, and temperature were determined. Such datasets were the learning vectors for a set of artificial deep learning neural networks. A new approach proposed in this paper is to train the network using a learning set consisting only of data from the efficient system. The responses of the trained neural networks to new data from the undamaged system were performed against the response to data recorded for three damage states: misalignment, unbalance, and simultaneous misalignment and unbalance. As a result, a diagnostic parameter as a normalized measure of the deviation of the network results was developed for the faulted system from the result for the undamaged condition.

The main goal of this paper is to research and analyze the problem of image reconstruction performance using machine learning methods in 3D electrical capacitance tomography (ECT) and electrical impedance tomography (EIT) by comparing the areas inside the tank to determine the finite elements for which one of the method reconstructions is more effective. The research was conducted on 5000 simulated cases, which ranged from one to five inclusions generated for a cylindrical tank. The authors first used the elastic net learning method to perform the reconstruction and then proposed a method for testing the effectiveness of reconstruction. Based on this approach, the reconstructions obtained by each method were compared, and the areas within the object were identified. Finally, the results obtained from the simulation tests were verified on real measurements made with two types of tomographs. It was found that areas closer to the edge of the tank were more effectively reconstructed by EIT, while ECT reconstructed areas closer to the center of the tank. Extensive analysis of the inclusions makes it possible to use this measurement for energy optimization of industrial processes and biogas plant operation.