The article presents the results of a sensitivity analysis of artificial neural networks developed for a system which predicts the durability of forging tools used in the selected hot die forging process. The developed system makes it possible to calculate the geometric loss of the examined tool for the given values of its operating parameters (number of forgings, tool temperature at selected points, type of the applied protective layer, pressure and path of friction) and estimates the intensity of the occurrence of typical mechanisms of tool destruction, i.e. thermo-mechanical fatigue, mechanical wear, abrasive wear and plastic deformation. Nine neural networks operate in the developed system. Five of them determine the geometric loss of the material used for tools operating with protective layers, including a nitrided layer, a pad welded layer and three hybrid layers, i.e. AlCrTiSiN, Cr/CrN and Cr/AlCrTiN. Four networks make calculations determining the intensity of the occurrence of typical destructive mechanisms. The developed sensitivity analysis allows for each neural network to show which input parameters are most important and have the greatest impact on the explained variables. This is determined based on the network error analysis in the case of elimination of individual variables from the input data. The greater the network error calculated after rejecting an input variable relative to the error obtained for the network with all the input variables, the more sensitive the network to the lack of this variable. The best compliance was obtained for the first developed set of networks regarding the geometric loss of material, while the lowest compliance was obtained for the second developed set of networks regarding the applied protective layers, and in particular for plastic deformation and mechanical fatigue, probably due to the smallest size of these sets in the knowledge base. The obtained results of this analysis are important for the system operation, i.e. supporting the technologist's decision in the selection of such process parameter values that will increase the die's lifetime.
This article discusses the problems related to the use of non-contact 3D scanning techniques and their support by means of replication methods for the analysis of the geometrical changes in deep tool impressions used for the forward extrusion of valve-type elements assigned for motor truck engines. The 3D scanning method, despite its unquestionable advantages, also has certain limitations, such as scanning the inner surfaces of deep cavities. This is caused by the fact that the larger the angle between the reflected laser light and the normal direction to the measured surface, the larger the area covered for the analysis, yet at the same time, the higher the measurement error. The authors performed an analysis of the geometrical loss of the tools as well as the corresponding replication masses, together with a discussion of the results related to minimization of the measuring errors. For the analyzed tool, the maximum angle during direct scanning was 40 degrees, which unfortunately does not enable an analysis of the entire pattern, while for larger angles, it is necessary to make the measurement by indirect scanning, i.e., by replicating the cavity imprint of the tool. Therefore, for a given geometry, the reflection angle should be determined individually.
The paper presents the results of research on the influence of the settings of lubrication and cooling system parameters (solenoid valve opening time and lubricant feed pressure in terms of its quantity) in order to select the optimal lubricating conditions and thus reduce the wear of the dies used in the first forging operation of the valve forging made of high-nickel steel. Based on the observation of lubrication in the industrial process, it was found that a significant part of the lubricant fails to reach the die cavity, reaching the outside of it, which causes die wear due to seizure resulting from adhesion of the forging material to the tool surface as well as high lubricant consumption and dirt in the press chamber. The authors proposed their own mobile lubricating and cooling system, which allows for a wide range of adjustments and provided with automatic cleaning procedures of the entire system, unlike the fixed lubrication system used so far in the industrial process. First, tests were carried out in laboratory conditions to determine the highest wettability and the lubricant remaining inside the tool cavity. These tests determined the lubrication system parameter settings that ensured that the greatest amount of lubricant remains in the cold die cavity without the forging process. Then, to verify the obtained results, tests were carried out in the industrial process of hot die forging of valve forgings for short production runs of up to 500 forgings. The results were compared with the measurement of changes in the geometry of tools and forgings based on 3D scanning and surface topography analysis with the use of SEM (Scanning Electron Microscope). For the best results (the variant of the setting of the dose and the time of exposure to lubricant), the forging process was carried out with the use of a new tool up to the maximum service life.
This article discusses the possibilities of using replicas of the geometry of the tool shaping the product in the process of hot precision forging for the control of geometrical characteristics, with the use of the three-dimensional (3D) laser scanning technique. Two types of masses were selected for the studies and used to create replicas with similar parameters, with which a forging die with a deep working impression, applied in the process of forward extrusion, was filled. The obtained results demonstrated that, based on selected parameters characterizing the replicate masses and tests, it is possible to select the optimal mass for 3D scanning, due to the best mapping of the surface layer. With the proposed approach, it is possible to perform tests that do not damage forging dies with deep working impressions and to support the process by making decisions concerning the tools’ further operation through a reliable determination of their wear.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.