Investigation of the Applicability of Artificial Intelligence Based Predictive Models in Order to Improve the Quality of Production with Advanced Machining Processes
Thesis supervisor: Márton Takács
Location of studies (in Hungarian): BME Department of Manufacturing Science and Engineering Abbreviation of location of studies: GTT
Description of the research topic:
a.) Preliminaries:
Production of parts through material removal processes remains one of the most efficient methods for manufacturing device parts in terms of quality and production time. While 3D printing technologies offer unique advantages in design flexibility and customization, they still have limitations in surface quality and geometric accuracy. Therefore, traditional material removal technologies, especially for metal workpieces requiring high surface quality and geometric accuracy, will continue to be essential in the coming decades. Production efficiency and product quality can be improved by application of Artificial Intelligence based predicvtive models.
b.) Aim of research:
The motivation and main aim of this research work is to improve the quality and efficiency of machining processes in modern manufacturing technology. This can be realized by generating and applicaion of machining data on cutting force, vibration, sutface roughness, and tool wear. Artificial Intelligence based predictive modells should be trained, tested, and validated. The trained models will be able to provide the expected quality and remaining useful tool life based on instantaneous sensor signals. Based on these, it will be possible to change the machining parameters, if necessary, and it will be easier to make a decision on the ideal time to change the cutting tool. Optimal cutting parameters will be available in the case of advanced chip removal processes.
c.) Tasks, main items, necessary time:
• Literature survey regarding advanced chip removal processes, focusing on machining of hard materials, tool condition monitoring, AI-based predictive modelling of surface quality, power cosupmption, tool wear in the machining process, machining data processing (1st semester).
• Carrying out predictive modelling based on historical data in the literature. Evaluating of the results, and continuous improvement of the models (2nd semester). Summary of literature survey in written form. Specification and set-up of measurement system for recording machining data. Specification of workpiece materials and cutting parameters. Design of experiments (2nd and 3th semesters).
• Investigation of dynamic effects at machining of advanced materials. FEM modelling. Carrying out preliminary cutting experiments (3rd and 4th semesters).
• Cutting experiments of advanced maerials. Collecting data related to cutting force, vibration, tool life. Verification of FEM models (5th and 6th semesters)
• Creating Artificial Intelligence based predictive models of chip removal process. Validating the models (5th, 6th and 7th semesters).
• Determination of optimal cutting parameters at machining of advanced materials. Carrying out validation (6th and 7th semesters).
• Publication of the results (between 3rd and 8th semesters).
• Preparing and finishing of scientific thesis (7th and 8th semesters)
d.) Required equipment:
Tuning lathe, milling machine, force and vibration sensors, data equisition system, digital and confocal microscopes, surface roughness measuring units, evaluation software, FEM software are required, which are available at the department, or at partner departments.
e.) Expected scientific results:
Artificial Intelligence (AI) based predictive models will be available in order to improve the quality of production in advanced machining processes through advanced data analysis, machine learning, and statistical modeling techniques. These models enable the prediction of quality issues proactively, allowing for the identification of patterns, trends, and potential anomalies that could affect product quality. By continuously monitoring incoming data and comparing it against the models, manufacturers can take immediate action to prevent quality issues, such as adjusting process parameters, implementing maintenance procedures, or inspecting products. As a result of the research, it becomes possible to determine the ideal time to change the cutting tool, thereby realizing economic production and reducing the number of scraps.
f.) References:
Adizue, Ugonna Loveday, Amanuel Diriba Tura, Elly Ogutu Isaya, Balázs Zsolt Farkas, and Márton Takács. "Surface quality prediction by machine learning methods and process parameter optimization in ultra-precision machining of AISI D2 using CBN tool." The International Journal of Advanced Manufacturing Technology 129, no. 3 (2023): 1375-1394.
Balázs, Barnabás Zoltán, Norbert Geier, Márton Takács, and J. Paulo Davim. "A review on micro-milling: recent advances and future trends." The International Journal of Advanced Manufacturing Technology 112 (2021): 655-684.
Balázs, B. Z., and M. Takács. "Experimental investigation and optimisation of the micro milling process of hardened hot-work tool steel." The International Journal of Advanced Manufacturing Technology 106, no. 11-12 (2020): 5289-5305.
J C, Jáuregui ; J R, Reséndiz ; S, Thenozhi ; T, Szalay ; Á, Jacsó ; M, Takács: Frequency and Time-Frequency Analysis of Cutting Force and Vibration Signals for Tool Condition Monitoring, IEEE ACCESS 6 pp. 6400-6410., 11 p. (2018)
Marton, Takacs ; Balázs, Zsolt Farkas: Theoretical and Experimental Investigation of Machining of AISI H13 Steel, ADVANCED MATERIALS RESEARCH 818 pp. 187-192, 6 p. (2013)
Required language skills: English Number of students who can be accepted: 1
Deadline for application: 2024-10-15
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
