This paper suggests the automated programming of CNC-machine tools with the help of artificial intelligence was suggested. Based on a CAD-model of the product, the system, without any help of an expert, automatically prepares a CNC-program, so that the machining is safe, accurate and time efficient. The developed CAD/CAM system uses NSGA-II multi-objective optimisation and swarm intelligence. The system consists of a prediction and evaluation module. In a prediction module artificial intelligence suggests solutions which include information about tool path, selected tools and suggested cutting parameters. The evaluation module estimates the suggested solutions by considering the geometrical, technological and time criteria, and the criterion of efficiency of machining. A simulation model was developed for searching optimal solutions. In the paper, the developed system is experimentally tested using a test case of manufacturing. The test results confirmed that with the help of this method of artificial intelligence, machine tools can be automatically programmed.
COBISS.SI-ID: 19404310
This paper presents a surface roughness control of end milling with associated simulation block diagram. The objective of the proposed surface roughness control is to assure the desired surface roughness by adjusting the cutting parameters and maintaining the cutting force constant. For simulation purposes an experimentally validated surface roughness control simulator is employed. Its structure combines genetic programming (GP), neural network (NN) and adaptive neuro fuzzy inference system (ANFIS) based models. The focus of this research is to develop a reliable method to predict surface roughness average during end milling process. An ANFIS is applied to predict the effect of cutting parameters (spindle speed, feed rate and axial/radial depth of cut) and cutting force signals on surface roughness. Machining experiments conducted using the proposed method indicate that using an appropriate cutting force signals, the surface roughness can be predicted within 3% of the actual surface roughness for various end-milling conditions.
COBISS.SI-ID: 19278870
The paper is concerned about the system of automatic detecting of wear and damages of the end mill tool by the use of computer vision. By using the algorithms developed for image segmentation and by an innovative approach to extraction of features describing individual end mill tool tooth the information representing significant features of the individual tool tooth is effectively gained from the captured image. The proposed approach to feature extraction is robust and independent of the scale and rotation of the end mill tool in the image. The features vectors have been classified by two approaches, i.e., k-nearest neighbor algorithm and artificial neural network. Both approaches have been tested by the test base of tool images and the results mutually compared. The classification being validated by 10-fold cross-validation method. The best precision of classification (92.63 %) has been reached by the use of artificial neural network. Simulation results have confirmed that the proposed approach can improve monitoring of tool wear and damages and, consequently, the effectiveness and reliability of CNC milling machine tool.
COBISS.SI-ID: 19214358
Research presents a system for distributed and collaborative environment which could assist manufacturing enterprises and experts in discussing, suggesting, evaluating and selecting the best process plans for family of manufacturing parts. System enables the implementation of the expert knowledge in an appropriate knowledge repository. The proposed internet-based collaborative environment represents another step in the direction of an advancement of distributed manufacturing.
COBISS.SI-ID: 20238870
The paper presents the evaluation of results of thermal insulation using thermal manikin. The analysis of thermal manikin stability is performed considering obtained results.
COBISS.SI-ID: 20067350