Neural-Network-Based Approaches for Optimization of Machining Parameters Using Small Dataset.

Surface quality is one of the most important indicators of the quality of machined parts. The analytical method of defining the arithmetic mean roughness is not applied in practice due to its complexity and empirical models are applied only for certain values of machining parameters. This paper presents the design and development of artificial neural networks (ANNs) for the prediction of the arithmetic mean roughness, which is one of the most common surface roughness parameters. The dataset used for ANN development were obtained experimentally by machining AA7075 aluminum alloy under various machining conditions. With four factors, each having three levels, the full factorial design considers a total of 81 experiments that have to be carried out. Using input factor-level settings and adopting the Taguchi method, the experiments were reduced from 81 runs to 27 runs through an orthogonal design. In this study we aimed to check how reliable the results of artificial neural networks were when obtained based on a small input-output dataset, as in the case of applying the Taguchi methodology of planning a four-factor and three-level experiment, in which 27 trials were conducted. Furthermore, this paper considers the optimization of machining parameters for minimizing surface roughness in machining AA7075 aluminum alloy. The results show that ANNs can be successfully trained with small data and used to predict the arithmetic mean roughness. The best results were achieved by backpropagation multilayer feedforward neural networks using the BR algorithm for training.

THE TIBIAL APERTURE SURFACE ANALYSIS IN ANTERIOR CRUCIATE LIGAMENT RECONSTRUCTION PROCESS.

INTRODUCTION: The tibial tunnel aperture in the anterior cruciate ligament reconstruction is usually analyzed as an ellipse, generated as an intersection between a tibial plateau and a tibial bone tunnel. The aim of this study is to show that the tibial tunnel aperture, which utilizes 3D tibial surface bone model, differs significantly from common computations which present the tibial tunnel anterior cruciate ligament aperture surface as an ellipse. MATERIAL AND METHODS: An interactive program system was developed for the tibial tunnel aperture analysis which included the real tibia 3D surface bone model generated from a series of computed tomography images of ten male patients, their mean age being 25 years. In aperture calculation, the transverse drill angle of 10 degrees was used, whereas sagittal drill angles of 40 degrees, 50 degrees and 60 degrees were used with the drill-bit diameter set to 10 mm. The real 3D and 2D tibial tunnel aperture surface projection was calculated and compared with an ellipse. RESULTS: According to the calculations, generated 3D aperture surfaces were different for every patient even though the same drill parameters were used. For the sagittal drill angles of 40 degrees, 50 degrees and 60 degrees, the mean difference between the projected 3D and 2D area on the tibial plateau was 19.6 +/- 5.4%, 21.1 +/- 8.0% and 21.3 +/- 9.6%, respectively. The difference between the projected 3D area on the tibial plateau and ellipse surface was 54.8 +/- 16.3%, 39.6 +/- 10.4% and 25.0 +/- 8.0% for sagittal drill angles of 40 degrees, 50 degrees and 60 degrees, respectively. CONCLUSION: The tibial tunnel aperture surface area differs significantly from the ellipse surface area, which is commonly used in the anterior cruciate ligament reconstruction analysis. Inclusion of the 3D shape of the tibial attachment site in the preoperative anterior cruciate ligament reconstruction planning process can lead to a more precise individual anatomic anterior cruciate ligament reconstruction on the tibial bone. Both tibial aperture area generated in 3D and its projection on a tibial plateau are larger than the ellipse surface; therefore, individual characteristics of each patient have to be taken into consideration.

Computer and experimental analyses of the stress state in the cement hip joint endoprosthesis body.

BACKGROUND/AIM: One of the possible complications after implantation of a cement hip-joint endoprosthesis is frac- ture in the endoprosthesis body. Fractures arise from overload or material fatigue of which an implant is made. The purpose of this research was to define the intensity of maximum stress and the positions of a critical cross-section in the endoprosthesis body. METHODS: Unilaterally changing forces which act on the hip joint during walking as well as the loads result in flexible deformations of the endoprosthesis body. Biomechanical analysis of the forces acting on the hip joint determine their direction and intensity, whereas on the basis of Gruen's classification of the endoprosthesis body loosening the level of fixation is established. The bodies of cement hip joint endoprosthesis are made of cobalt-chromium-molybdenum (CoCrMo) alloy, suitable for vacuum casting, are submitted to the analysis. Analysis of the critical stress in the endoprosthesis body was performed on the endoprosthesis body by means of the finite element method. The experimental verification of the obtained results was carried out on the physical prototype under laboratory conditions. RESULTS: Computer analysis, by means of the finite element method, determined the stress state by calculation of the maximum Von Mises stress and critical cross-sections for different angles of the resultant force action. The results obtained by the computer and experimental method correlate and are comparable to the results of similar analyses conducted on various endoprosthesis types. CONCLUSION: The analyses described in the paper make the basis for improving the process designing of hip joint endoprostheses and their customization to each individual patient (custom made).

[Designing special prosthesis "spacer"].

Malignant diseases of the medial part of the femur, humerus and tibia, treated with surgical removal of the affected part of the bone and prosthesis fitting special "Spacer". This type of prosthesis is made in the form of the proximal and distal components that connect by screws. The design of endoprosthesis provides without possible rotation linear relationship and allows the transfer of load from the proximal to the distal bone, but the screws that provide connection are not exposed to stress. For pro-per sizing and implementation of a special prosthesis is necessary to determine the geometric parameters of bone mass and disease and then develop a computer model of the prosthesis. Designing a special prosthesis "spacer" is a complex procedure based on the processing of diagnostic images (X-ray, CT or MRI) with the use of specialized software digitized picture elements pixels translate into voxels. In this way a geometric model contains a form of external (KORTEX), and the internal geometry of the bone (medullary canal). On the basis of such a developed computer models is possible accurately determine the part of the bone that is necessary to remove, and the size of medullary canal space that is built into proximal or distal component of special endoprosthesis "Spacer".