Search

We consider the influence of vapor content in the mixed flow leaving a liquid-vapor ejector on the energy efficiency of a vacuum unit. As shown by numerical studies of liquid-vapor ejectors, this issue is important as vapor overproduction, which accompanies the process of secondary flow ejection, directly impacts the efficiency of the working process of both the liquid-vapor ejector and the vacuum unit as a whole. The greater the degree of vapor overproduction, the greater the load on the vapor phase of the separator, which is part of the vacuum unit. In addition, the liquid phase must be returned to the cycle to ensure the constancy of the mass flow rate of the working fluid of the primary flow. Our numerical study results revealed the rational value of the degree of vapor overproduction at which the efficiency of the liquid–vapor ejector was maximized, and the amount of additional working fluid that needed to enter the cycle of the vacuum unit was minimal. Experimental condition monitoring studies on the liquid–vapor ejector were carried out on plane-parallel transparent models with different flow path geometries. Through experimental studies, we confirmed and adjusted the values of the achievable efficiency of the working process of a liquid–vapor ejector, depending on the degree of vapor overproduction. Using a comparative analysis of liquid–vapor ejectors with different flow path geometries, differences were revealed in their working processes, which consisted of the degree of completion of the mixing of the working media of primary and secondary flows. To determine the feasibility of using liquid–vapor ejectors with different flow path geometries, exergy analysis was performed, resulting in achievable efficiency indicators.

The assisted assembly of customized products supported by collaborative robots combined with mixed reality devices is the current trend in the Industry 4.0 concept. This article introduces an experimental work cell with the implementation of the assisted assembly process for customized cam switches as a case study. The research is aimed to design a methodology for this complex task with full digitalization and transformation data to digital twin models from all vision systems. Recognition of position and orientation of assembled parts during manual assembly are marked and checked by convolutional neural network (CNN) model. Training of CNN was based on a new approach using virtual training samples with single shot detection and instance segmentation. The trained CNN model was transferred to an embedded artificial processing unit with a high-resolution camera sensor. The embedded device redistributes data with parts detected position and orientation into mixed reality devices and collaborative robot. This approach to assisted assembly using mixed reality, collaborative robot, vision systems, and CNN models can significantly decrease assembly and training time in real production.

Small series production with a high level of variability is not suitable for full automation. So, a manual assembly process must be used, which can be improved by cooperative robots and assisted by augmented reality devices. The assisted assembly process needs reliable object recognition implementation. Currently used technologies with markers do not work reliably with objects without distinctive texture, for example, screws, nuts, and washers (single colored parts). The methodology presented in the paper introduces a new approach to object detection using deep learning networks trained remotely by 3D virtual models. Remote web application generates training input datasets from virtual 3D models. This new approach was evaluated by two different neural network models (Faster RCNN Inception v2 with SSD, MobileNet V2 with SSD). The main advantage of this approach is the very fast preparation of the 2D sample training dataset from virtual 3D models. The whole process can run in Cloud. The experiments were conducted with standard parts (nuts, screws, washers) and the recognition precision achieved was comparable with training by real samples. The learned models were tested by two different embedded devices with an Android operating system: Virtual Reality (VR) glasses, Cardboard (Samsung S7), and Augmented Reality (AR) smart glasses (Epson Moverio M350). The recognition processing delays of the learned models running in embedded devices based on an ARM processor and standard x86 processing unit were also tested for performance comparison.