Miha Kovačič

Integrated Genetic Programming and Genetic Algorithm Approach to Predict Surface Roughness

Abstract In this article we propose a new integrated genetic programming and genetic algorithm approach to predict surface roughness in end-milling. Four independent variables, spindle speed, feed rate, depth of cut, and vibrations, were measured. Those variables influence the dependent variable (i.e., surface roughness). On the basis of training data set, different models for surface roughness were developed by genetic programming. The floating-point constants of the best model were additionally optimized by a genetic algorithm. Accuracy of the model was proved on the testing data set. By using the proposed approach, more accurate prediction of surface roughness was reached than if only modeling by genetic programming had been carried out. It was also established that the surface roughness is most influenced by the feed rate, whereas the vibrations increase the prediction accuracy.

Impact of Relaxation Training According to Yoga in Daily Life® System on Perceived Stress After Breast Cancer Surgery

The purpose of this pilot study was to gather information on the immediate and short-term effects of relaxation training according to Yoga In Daily Life® (YIDL) system on the psychological distress of breast cancer patients. 32 patients at the Institute for Oncology of Ljubljana were randomized to the experimental (N = 16) and to the control group (N = 16). Both groups received the same standard physiotherapy for 1 week, while the experimental group additionally received a group relaxation training sessions according to YIDL® system. At discharge the experimental group was issued with audiocassette recordings containing the similar instructions for relaxation training to be practiced individually at home (for further 3 weeks). An experimental repeated measures design was used to investigate the differences over 1 month period in stress levels, changes in mental health and psychological parameters. Measures were obtained at three time points during the study period: baseline, at 1 week, and at 4 weeks, by blinded investigators using standardized questionnaires General Health Questionnaire-12 (GHQ-12), Rotterdam Symptom Checklist (RSCL) psychological subscale, Perceived Stress Scale (PSS). Patients who received relaxation training reported feeling significantly less distressed during hospitalization and after discharge-period than did the controls that did not receive relaxation training. The results indicate that relaxation training according to Yoga in Daily Life® system could be useful clinical physiotherapy intervention for breast cancer patients experiencing psychological distress. Although this kind of relaxation training can be applied to clinical oncology in Slovenia, more studies need to be done.

Intelligent programming of CNC turning operations using genetic algorithm

CAD/CAM systems are nowadays tightly connected to ensure that CAD data can be used for optimal tool path determination and generation of CNC programs for machine tools. The aim of our research is the design of a computer-aided, intelligent and genetic algorithm(GA) based programming system for CNC cutting tools selection, tool sequences planning and optimisation of cutting conditions. The first step is geometrical feature recognition and classification. On the basis of recognised features the module for GA-based determination of technological data determine cutting tools, cutting parameters (according to work piece material and cutting tool material) and detailed tool sequence planning. Material, which will be removed, is split into several cuts, each consisting of a number of basic tool movements. In the next step, GA operations such as reproduction, crossover and mutation are applied. The process of GA-based optimisation runs in cycles in which new generations of individuals are created with increased average fitness of a population. During the evaluation of calculated results (generated NC programmes) several rules and constraints like rapid and cutting tool movement, collision, clamping and minimum machining time, which represent the fitness function, were taken into account.A case study was made for the turning operation of a rotational part. The results show that the GA-based programming has a higher efficiency. The total machining time was reduced by 16%. The demand for a high skilled worker on CAD/CAM systems and CNC machine tools was also reduced.

Prediction of the bending capability of rolled metal sheet by genetic programming

The paper proposes genetic programming (GP) to predict the bending capability of rolled titanzinc metal sheet. In this study ZnTiCu alloy with ∼ 0.1% Cu and ∼ 0.1% Ti was used for production of metal sheet. Three groups of independent input variables were measured: (1) chemical composition of the ZnTiCu alloy during casting (percentage of Cu, Ti, and Fe), (2) parameters of hot rolling (temperature of ingot before rolling, time of rolling, temperature of plate after rolling, time of cooling), and (3) parameters of cold rolling (temperature of plate before rolling, temperature of sheet after rolling). Therefore, nine input variables (parameters) influence the bending capability of the sheet metal. On the basis of the experimental data, several models for prediction of the bending capability of titanzinc metal sheet were developed by the simulated evolution. The influence of individual input variables on bending capability was also studied. The most accurate model was verified with an independent testing data set. The results showed that GP is a powerful tool for predicting the bending capability of metal sheet.

Application of the Genetic Programming for Increasing the Soft Annealing Productivity in Steel Industry

The optimal thermomechanical processing in steel industry is difficult because of the multiconstituent and multiphase character of the commercial steels, variety of the possible processing paths, and plant specific equipment characteristics. This article shows successful implementation of the genetic programming approach for increasing the furnace conveyor speed and consequently productivity of the heat treatment furnace in the soft annealing process. The data (222 samples covering 24 different steel grades) on a furnace conveyor speed, chemical composition of steel (weight percent of C, Cr, Mo, Ni, and V) and Brinell hardness, before and after the soft annealing, were collected during daily production. On the basis of the monitored data a mathematical model for the hardness after the soft annealing was developed by genetic programming. According to the modeled influences on the hardness, the higher furnace conveyor speed was attempted in practice. The experimental results of the hardness after the soft annealing with the increased conveyor speed and the predictions of the mathematical model were compared within the agreement of 3.24%. The genetic model was also compared and verified with linear regression model. The productivity of the soft annealing process increased (from the furnace conveyor speed 3.2 m/h to 7 m/h) as a consequence of the used computational intelligence approach.

Impact of relaxation training according to Yoga In Daily Life® system on self-esteem after breast cancer surgery.

OBJECTIVES The purpose of this pilot study was to gather information on the immediate and short-term effects of relaxation training according to the Yoga In Daily Life(®) system on the self-esteem of patients with breast cancer. DESIGN This is a parallel-groups design. SETTINGS/LOCATION Baseline interventions took place at the Institute for Oncology of Ljubljana (Slovenia). At discharge, the experimental group was issued with audiocassette recordings containing the instructions for relaxation training to be practiced individually at home for an additional 3 weeks. SUBJECTS The convenience sample of 32 patients with breast cancer was recruited from an accessible population of hospitalized women. Patients were randomized to the experimental (n=16) and to the control group (n=16). INTERVENTIONS Both groups received the same standard physiotherapy for 1 week, while the experimental group additionally received a group relaxation training sessions according to the Yoga in Daily Life(®) system. At discharge, the experimental group was issued with audiocassette recordings containing similar instructions for relaxation training to be practiced individually at home for an additional 3 weeks. OUTCOME MEASURES Outcome measures were obtained by blinded investigators (physiotherapists) using standardized questionnaires (Rosenberg Self-Esteem Scale) at baseline (after the surgery); at 1 week (1 week postattendance; at discharge); and at 4 weeks (4 weeks postattendance); prior the commencement of radiation. RESULTS Analysis of variance showed that there were statistically significant differences between the experimental and control group in all measuring self-esteem scores over the study period (p<0.0005). At the same time, the control groups scores remained unchanged over the study period (p>0.05). CONCLUSIONS The results indicate that relaxation training according to the Yoga in Daily Life system could be a useful clinical physiotherapy intervention for patients who have breast cancer and who are experiencing low self-esteem. Although this kind of relaxation training can be applied to clinical oncology in Slovenia, more studies need to be done.

Comparison Between Genetic Algorithm and Genetic Programming Approach for Modeling the Stress Distribution

ABSTRACT This article compares genetic algorithm (GA) and genetic programming (GP) for system modeling in metal forming. As an example, the radial stress distribution in a cold-formed specimen (steel X6Cr13) was predicted by GA and GP. First, cylindrical workpieces were forward extruded and analyzed by the visioplasticity method. After each extrusion, the values of independent variables (radial position of measured stress node, axial position of measured stress node, and coefficient of friction) were collected. These variables influence the value of the dependent variable, radial stress. On the basis of training data, different prediction models for radial stress distribution were developed independently by GA and GP. The obtained models were tested with the testing data. The research has shown that both approaches are suitable for system modeling. However, if the relations between input and output variables are complex, the models developed by the GP approach are much more accurate.

Impact of relaxation training according to the Yoga In Daily Life® system on anxiety after breast cancer surgery.

Abstract The purpose of this pilot study was to gather information on the immediate and short-term effects of relaxation training according to the Yoga In Daily Life® (YIDL®) system on anxiety of breast cancer patients. The YIDL® system is a holistic system being practised and taught worldwide and has been proven to be highly effective in the prevention and treatment of various diseases. The system aims to establish physical, mental, spiritual, and social health. Thirty-two patients at the Institute for Oncology Ljubljana were randomized to the experimental (n=16) and to the control groups (n=16). Both groups received the same standard physiotherapy for 1 week, while the experimental group additionally received 1-hour group relaxation training session according to the YIDL® system per day. At discharge, the experimental group was issued with audiocassette recordings containing similar instructions for relaxation training to be practiced for 3 weeks individually at home. Anxiety measures were obtained by blinded assessors using standardized questionnaires. The results indicate that relaxation training according to the YIDL® system could be a useful clinical physiotherapy intervention for breast cancer patients experiencing anxiety.

Residual Stress Field Analysis and Prediction in Nitrided Tool Steel

Residual stresses are present in engineering components as an unintended consequence of manufacturing processes, but they are also deliberately introduced to beneficial effect during surface engineering procedures. Plasma nitriding is a process of particular importance for forming tools and dies, giving significant advantages in wear, and fatigue resistance through the generation of near-surface compressive residual stresses. A precise knowledge of the level and distribution of residual stresses that exist in engineering components is necessary for an accurate design and prediction of a components fatigue resistance. However, measurement of residual stresses is not always possible, which is especially true for forming tools. Therefore, other methods for residual stress evaluation and prediction are required. Results of this investigation show that residual stress level and depth in plasma nitrided tool steel increase with nitriding time and temperature. On the other hand, experimental data indicates that the residual stress distribution in plasma nitrided tool steels can be determined on the basis of microhardness depth distribution. A minimum in the microhardness depth profile derived over depth corresponds to the location of the compressive residual stress maximum. Furthermore, the residual stress level can be extrapolated by using reference residual stress data and genetic programming. In this way the residual stress level and distribution can be obtained even for components where measurement is not possible.

Genetic Algorithm Rolling Mill Layout Optimization

Štore Steel Ltd. is a small flexible steel plant in Slovenia. In 2010, the new continuous rolling mill, which has a technical capacity of 250,000 tons per year, was installed. The new continuous rolling mill, which entailed a corresponding reduction in space, required an urgent relocation of machinery. The genetic algorithm was used for the optimal rearranging of the machinery. Two-dimensional or three-dimensional representation of the machines without any kind of geometrical restrictions can be used in the proposed genetic algorithm. The layout efficiency after machinery relocation could be increased by 58.1%, but due to spatial, financial, and practical constraints, the layout efficiency is only 13.58% higher.