NationalResearch Institute of Mechanical Engineering plans to organize the Institute-level doctoral thesis evaluation committee for PhD candidate Nguyen Quang Vinh in early December 2024. The Institute posts the information of the candidate's doctoral thesis as follows:

Full name of PhD candidate: Nguyễn Quang Vinh

Supervisors: Assoc. Prof. Dr. Trần Ngọc Hiền and Assoc. Prof. Dr. Nguyễn Văn Cường

Field: Mechanical Engineering - Code: 9520103

Training institution: National Research Institute of Mechanical Engineering - Ministry of Industry and Trade

Thesis title: “Research on dynamic optimization of some technological parameters to ensure surface roughness of machined parts on CNC milling center”

Summary of new conclusions of the thesis

1. Scientific significance:

- The thesis has developed a dynamic optimization model in the machining process, particularly focusing on controlling surface roughness and vibration during machining on CNC machines. It improves the accuracy and efficiency of the machining process, providing scientific methods to adjust cutting parameters to ensure product quality.

- The thesis has researched and developed a self-optimizing control system for CNC machines, continuously optimizing machining parameters during production.

- The research analyzed the influence of cutting parameters (cutting speed, feed rate, depth of cut) on surface roughness and cutting force. These results help the machining system automatically adjust based on actual factors, contributing to ensuring stable product quality and minimizing errors in the production process.

- The thesis developed a self-optimizing control system (Self-HSM), which has the ability to automatically adjust cutting modes by predicting tool wear and controlling surface roughness. This system has important scientific significance, opening a new direction in intelligent machining process control and monitoring, meeting the requirements of Industry 4.0

2. Practical significance

Research results serve as a basis for application in factories and machining workshops to improve product quality:

- The self-adjusting control system (Self-HSM) allows optimization of cutting parameters during machining, ensuring surface roughness and high accuracy without human intervention.

- With self-adjusting and dynamic optimization capabilities, the system helps reduce machine downtime for manual inspection and adjustment, increase productivity, reduce production time, and improve operational efficiency.

- The tool wear prediction and cutting mode optimization system helps reduce tool consumption, save maintenance and replacement costs for cutting tools, optimize resource utilization, reduce material waste, and improve the economic efficiency of the machining process.

- The self-optimizing control system is part of a smart manufacturing solution, meeting the requirements of automation and self-optimization in Industry 4.0. The application of artificial intelligence to the machining system opens a new development direction, helping enterprises easily transform and apply smart technology, enhance flexible production capabilities, and quickly respond to market demands.

3. New contributions of the thesis

- From theoretical and experimental research, the thesis clearly determined the influence of technological parameters (cutting speed - v_c, feed per tooth - f_z, and depth of cut - a_r) on machining quality, including surface roughness, vibration, and tool wear. Research results show that feed rate is the parameter with the greatest influence on surface roughness, followed by cutting speed. Depth of cut is the parameter with the greatest influence on cutting force, followed by the influence of cutting speed and feed rate. Surface roughness regression equation:

-  The thesis successfully applied artificial intelligence to predict tool wear during machining. By using sensors and data from cutting force, cutting speed, feed rate, artificial intelligence (AI) can accurately predict the degree of tool wear after a certain machining time. The artificial neural network needs to be pre-trained, then will operate automatically. The structure of the artificial neural network for tool wear prediction is 6-10-1. The structure of the artificial neural network for generating optimal feed rate is 3-9-9-1.

-  The Self-HSM system has been successfully developed with the ability to automatically adjust cutting parameters (cutting speed, feed rate, depth of cut) based on machining conditions. This ensures the machining process is continuous and efficient without human intervention. The system was tested on the HS Super MC500 high-speed CNC machine, resulting in an initial surface roughness of the machined part reaching R_a = 0.388 μm when using optimal cutting parameters (v_c = 595 m/min; f = 2500 mm/min; a_r = 0.3 mm). After 5.4 minutes of machining, when tool wear reached 0.06 mm, the system automatically adjusted the cutting parameters (v_c = 595 m/min; f = 2452 mm/min; a_r = 0.3 mm) to ensure continued stable machining quality. Thanks to the automatic cutting parameter adjustment capability, the Self-HSM system helped maintain stable surface quality with surface roughness reaching R_a = 0.388 μm throughout the machining process, even when the cutting tool was worn.

- The thesis developed a smart manufacturing system based on a cyber-physical system (CPS), allowing the system to self-adjust cutting conditions according to tool condition and other machining factors. This CPS system demonstrates autonomy and flexibility in CNC machining, while contributing to the development of smart manufacturing solutions in the Fourth Industrial Revolution

Detailed information of the thesis can be viewed at here