The article presents the theoretical research on hydraulic processes occurring in hydraulic drives of transport machines. The research analysed the influence of hydrodynamic processes on the fluid flow characteristics following installation of angular fitting connections in pipeline systems. The analysis was based on the numerical simulations by Reynolds-averaged Navier–Stokes equations in 3D. The fluid flow in the hydraulic system pipeline connections were investigated for fluid flow rate up to 100 l/min. For numerical simulation, a mesh independence study was performed. By modeling. we obtained results of pressure drops, turbulence models, flow coefficients and energy losses at 45° and 90° angular fitting connections. The article compares the results obtained using the calculation method based on the standard of equivalent length fitting with the findings presented. The research conducted indicated that using the equivalent length method is not appropriate for studying angular fitting connections. It was found that additional investigations are necessary for each type of angular fitting connection.

This paper identifies mechanical vibrations occurring in the operating environment of hydraulic systems used in marine engineering. Particular attention was paid to the influence of periodic vibrations on changes in the amplitude-frequency spectrum in a marine hydraulic system. For the case of analysing the effect of vibration on changes in the pressure pulsation spectrum with a proportional directional valve, a modified mathematical model was used. Experimental results were presented and compared with the results obtained from the mathematical model. A way of limiting the transmission of vibrations to the directional control valve body was proposed.

With the automotive industry moving towards automated driving, sensing is increasingly important in enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long–Short Term Memory (BiLSTM) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which were used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors to estimate vehicle unsprung mass relative velocity.

With the automotive industry moving towards automated driving, sensing is becoming an increasingly important part of enabling technology. The virtual sensors allow data fusion from various vehicle sensors and provide a prediction for measurement that is hard or too expensive to measure in another way or in the case of demand on continuous detection. In this paper, virtual sensing is discussed for the case of vehicle suspension control, where information about the relative velocity of the unsprung mass for each vehicle corner is required. The corresponding goal can be identified as a regression task with multi-input sequence input. The hypothesis is that the state-of-art method of Bidirectional Long-Short Term Memory (BiLSMT) can solve it. In this paper, a virtual sensor has been proposed and developed by training a neural network model. The simulations have been performed using an experimentally validated full vehicle model in IPG Carmaker. Simulations provided the reference data which was used for Neural Network (NN) training. The extensive dataset covering 26 scenarios has been used to obtain training, validation and testing data. The Bayesian Search was used to select the best neural network structure using root mean square error as a metric. The best network is made of 167 BiLSTM, 256 fully connected hidden units and 4 output units. Error histograms and spectral analysis of the predicted signal compared to the reference signal are presented. The results demonstrate the good applicability of neural network-based virtual sensors for the estimation of vehicle unsprung mass relative velocity.

The reduction of the weight of high-pressure components and systems (including hydraulic) is especially important in aircraft or mobile machinery. An interesting trend that began in the first half of the 20th century in the aviation industry is the weight reduction of structures by using components made of composite materials in place of those made of conventional materials. This trend is not only not diminishing, but is actually increasing year by year. This paper investigates the effect of modifying the design of the sickle insert on the volumetric efficiency of the pump. Moreover, this work presents the replacement of the sickle insert of an internal gear pump made of bronze with plastic materials, reducing its weight by 80%. To ensure similar performance, its design was modified, increasing the pump’s efficiency while additionally reducing its weight. This material substitution allows the reduction of weight, but it can adversely affect the performance of the hydraulic component, this also applies to the displacement pumps. For this reason, the design had to be changed to obtain similar operational parameters after changing the material.