Oil leakage between the slipper and swash plate of an axial piston pump has a significant effect on the efficiency of the pump. Therefore, it is extremely important that any leakage can be predicted. This study investigates the leakage, oil film thickness, and pocket pressure values of a slipper with circular dimples under different working conditions. The results reveal that flat slippers suffer less leakage than those with textured surfaces. Also, a deep learning-based framework is proposed for modeling the slipper behavior. This framework is a long short-term memory-based deep neural network, which has been extremely successful in predicting time series. The model is compared with four conventional machine learning methods. In addition, statistical analyses and comparisons confirm the superiority of the proposed model.

Assembly refers both to the process of combining parts to create a structure and to the product resulting therefrom. The complexity of this process increases with the number of pieces in the assembly. This paper presents the assembly planning system design (APSD) program, a computer program developed based on a matrix-based approach and the discrete artificial bee colony (DABC) algorithm, which determines the optimum assembly sequence among numerous feasible assembly sequences (FAS). Specifically, the assembly sequences of three-dimensional (3D) parts prepared in the computer-aided design (CAD) software AutoCAD are first coded using the matrix-based methodology and the resulting FAS are assessed and the optimum assembly sequence is selected according to the assembly time optimisation criterion using DABC. The results of comparison of the performance of the proposed method with other methods proposed in the literature verify its superiority in finding the sequence with the lowest overall time. Further, examination of the results of application of APSD to assemblies consisting of parts in different numbers and shapes shows that it can select the optimum sequence from among hundreds of FAS.

Purpose: The purpose of this study is to investigate thermal conductivity and dynamic viscosity of graphene nanoplatelet-based (GNP) nanolubricant. Design/methodology/approach: Nanolubricants in concentrations of 0.025, 0.05, 0.1 and 0.5 Wt% were prepared by means of two-step method. The stability of nanolubricants was monitored by visual inspection and dynamic light scattering tests. Thermal conductivity and dynamic viscosity of nanolubricants in various temperatures between 25°C–70°C were measured with KD2-Pro analyser device and a rotational viscometer MRC VIS-8, respectively. A comparison between experimentally achieved results and those obtained from existing models was performed. New correlations were proposed and artificial neural network (ANN) model was used for predicting thermal conductivity and dynamic viscosity. Findings: The designed nanolubricant showed good stability after at least 21 days. Thermal conductivity and dynamic viscosity increased with particles concentration. In addition, as the temperature increased, thermal conductivity increased but dynamic viscosity decreased. Compared to the base oil, maximum enhancements were achieved at 70°C with the concentration of 0.5 Wt.% for dynamic viscosity and at 55°C with the same concentration for thermal conductivity. Besides, ANN results showed better performance than proposed correlations. Practical implications: This study outcomes will contribute to enhance thermophysical properties of conventional lubricating oils. Originality/value: To the best of our knowledge, there is no paper related to experimental study, new correlations and modelling with ANN of thermal conductivity and dynamic viscosity of GNPs/SAE 5W40 nanolubricant in the available literature. Peer review: The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-03-2020-0088/

The pressure distribution (PD) and leakage between the slipper and swash plate in an axial piston pump (APP) have a considerable impact on the pump efficiency, affecting aspects such as the load bearing and wear performance of the slipper. Herein, multigene genetic programming (MGGP) and artificial neural network (ANN) machine learning methods (MLMs) are incorporated into a novel approach towards predictive modelling of the PD and leakage on the slipper, which can function hydrostatically/hydrodynamically. Experimentally measured data are used as input for the MGGP and ANN models. The validity of the MGGP and ANN models is verified using test data excluded from the analyses. In addition, the model results are compared with analytic equations (AEs). Both MLMs are found to exhibit strong agreement with the measured data. In particular, the ANN model exhibits superior prediction performance to the MGGP model and AEs.

Lightweight and multifunctional carbon fiber‐reinforced composites with low production costs are crucial for aerospace and logistics applications. In this study, the integration of compatibilizer to polylactic acid (PLA)/thermoplastic polyurethane (TPU) blends filled with carbon fiber (CF) is performed due to cost‐lowering, besides enhanced mechanical performance and processability. Composite sample loaded with 30% CF is selected and optimized by the varied amount of polymeric MDI (pM) inclusions. As the tensile resistance of PLA/TPU/30CF and PLA/TPU/30CF/pM is compared, it is found that pM additions led to enhancements in tensile strength and tensile modulus. A total of 5% of pM inclusion results in 43% increament in tensile strength of the tensile strength of PLA/TPU/30CF. Similarly, the flexural modulus and flexural strength of composites are improved by a high amount of pM. The impact resistance of PLA significantly increases after CF inclusion. The incorporation of TPU and compatibilizer shifts impact strength to higher levels. 204% improvement is achieved for PLA/TPU blend involving 5 wt% of pM concerning unfilled PLA. According to the thermo‐mechanical analysis of composites, the presence of pM yields a higher elastic modulus for PLA/TPU/CF composites. Additionally, reductions in the glass transition temperature of PLA and composites are observed since the polymer gains ductility by elastomer and compatibilizer inclusions. Scanning electron microscopy (SEM) investigations of composites visualize these findings. Results postulated that pM integration can be utilized in large‐scale production of CF‐reinforced PLA‐TPU blend systems for cost reduction and performance improvement of composite parts in logistics and aerospace applications. Highlights: The compatibilizing effect of pMDI on the PLA/TPU/CF blend system is investigated. pMDI inclusions yield improvement in the mechanical resistance of composites. CF‐reinforced PLA/TPU composites gain ductile behavior by the addition of TPU. The increase in elastic modulus ensures an efficient enhancement of compatibility.

Discovering new applications for discarded materials, such as leather waste (LW), has proven to be an effective approach to an ecofriendly and sustainable production. The manufacture of halogen-free flame retardant LW containing thermoplastic polyurethane (TPU)-based samples containing an organic phosphinate (OP)-based flame retardant additive would represent an advance in this area. The effects of LW and OP levels on the thermal, flame retardant, and tensile properties of the samples using thermal gravimetric analysis (TGA), limiting oxygen index (LOI), vertical UL-94 (UL-94 V), mass loss calorimetry, and tensile tests have been assessed. OP is highly effective in LW-filled TPU. The highest UL-94 V rating of V0, LOI value of 31.4%, the lowest peak heat release rate (93 +/- 3 kW/m(2)), and total heat evolved (49 +/- 2 MJ/m(2)) values are obtained with the use of 20 wt % OP. OP is primarily promoted through the creation of a compact intumescent residue structure in the condensed phase. LW exhibits an adjuvant effect by producing nonflammable gases in the gas phase and raising the residual yield in the condensed phase. The most remarkable effect of the LW presence is observed in fire performance index (FPI) and fire growth rate (FIGRA) values. The highest FPI value of 0.49 sm(2)/kW and the lowest FIGRA value of 0.91 kW/m(2)s are observed with the use of 20 wt % LW.