Analyses of information flows in companies show that there are decisive information gaps particularly between the computer-aided design and computer-aided manufacturing. Therefore the paper deals with the development of intelligent CAD/CAM systems with integrated intelligent interface, which enables the data exchange between several subsystems, included in flexible manufacturing system. The interface is created specially for small and medium-sized enterprises and is very important part of the flexible manufacturing systems.

This paper presents a smart energy consumption monitoring platform for machining processes with a unique electrical energy consumption indicator (EECI) for the evaluation and comparison of machining processes in terms of energy efficiency. The purpose of the developed smart monitoring platform with the integrated EECI and the Industry 4.0 digital technologies is to raise the level of efficiency of the machining process and thus to stimulate more sustainable and environmentally friendly machining. The energy consumption monitoring of a milling process is performed by connecting a machine tool with integrated sensors for measuring electrical power and cutting force to a cloud platform by using resources for signal acquiring and data acquisition. The platform includes applications for energy consumption monitoring and/or analysis. Results of four machining experiments are presented to demonstrate the effectiveness of the proposed energy consumption monitoring in machining and the applicability of the newly introduced EECI at the engineering and the operational level.

A cyber-psychical machining system (CPMS) is developed to realize smart end-milling process monitoring. The CPMS provides a novel way for controlling the cutting chip size and monitoring the surface roughness in milling processes through Internet of Things (IoT) applications. The two level CPMS is realized by linking the IoT machining platform for process control to the machine tool with integrated visual system (VS). The VS is employed to acquire the signals of the cutting chip size during the machining of difficult to cut materials. The machining platform performs instant chip size and surface roughness control based on advanced signal processing, edge computing, modeling and cognitive corrective process control acting. A cognitive neural control system (CNCS) is employed to control the chip size by modifying the machining parameters and consequently maintaining surface roughness constant. An adaptive neural inference system (ANFIS) is applied to precisely model and in-process predict the surface roughness. Machining tests conducted using the proposed CPMS indicate that the cutting chip size and consequently the produced surface roughness are well maintained when the cutting-depth profile of a workpiece is varying step-wise or continuously.

This paper outlines the experimental exploration of cutting forces produced during ball-end milling of multi-layered metal materials manufactured by the laser engineered net shaping (LENS) process. The research employs an artificial neural network (ANN) technique for predicting the cutting forces during the machining of 16MnCr5/316L four-layered metal material with a solid carbide ball-end mill. Hardness and thickness of the particular manufactured layer in above mentioned advanced material have been considered during training of the ANN model. Model predictions were compared with experimental data and were found to be in good agreement. Experimental results demonstrate that this method can accurately predict cutting force within a maximum prediction error of 4.8 %.

The aim of this paper is to present a surface roughness control in turning with an associated simulation block diagram. The objective of the new model based controller is to assure the desired surface roughness by adjusting the machining parameters and maintaining a constant cutting force. It modifies the feed rate on-line to keep the surface roughness constant and to make machining more efficient. The control model was developed based on simplified models of the turning process and the feed drive servo-system. The experiments were performed to find the correlation between surface roughness and cutting forces in turning and to provide functional correlation with the controllable factors. Simulation setup and results are presented to demonstrate the efficiency of the proposed control model. In terms of surface roughness fluctuations and cutting efficiency, the suggested control model is much better than a conventional CNC controller alone. Integrating the developed control model with the CNC Machine controller significantly improves the quality of machined components.

In this paper, optimization system based on the artificial neural networks (ANN) and particle swarm optimization (PSO) algorithm was developed for the optimization of machining parameters for turning operation. The optimization system integrates the neural network modeling of the objective function and particle swarm optimization of turning parameters. New neural network assisted PSO algorithm is explained in detail. An objective function based on maximum profit, minimum costs and maximum cutting quality in turning operation has been used. This paper also exhibits the efficiency of the proposed optimization over the genetic algorithms (GA), ant colony optimization (ACO) and simulated annealing (SA).

The objective of this paper is to present surface roughness control strategy aimed at controlling the cutting force and maintaining constant roughness of the surface being milled by digital adaptation of cutting parameters. The idea of this control structure is to merge the off-line cutting condition optimization and genetic programming (GP) model based surface roughness control. The off-line optimization integrates the neural network (NN) modelling of the objective function and particle swarm optimization (PSO) of cutting parameters. The GP method is conducted to find the correlation between surface roughness and the cutting force and to provide a functional relationship with controllable factors. Simulation setup and simulation results are presented to confirm the efficiency of the control model and its relevance to industry.

SUMMARYBased on hybrid process modeling, off‐line optimization and neural control scheme (NCS), the combined system for off‐line optimization and adaptive adjustment of cutting parameters is built. This is an adaptive control system controlling the cutting force by digital adaptation of cutting parameters. In this way, it compensates all disturbances during the cutting process, prevents excessive tool wear, and maintains a high chip removal rate. It is the combination of these methods that yields accurate force control. The basic control principle is based on the NCS consisting of two neural identifiers of the process dynamics and feedback controller. An overall procedure of hybrid modeling of cutting process, used for working out the computer numerical control (CNC) milling simulator has been prepared. CNC simulator is used to evaluate the controller design before conducting experimental tests. Numerous simulations and experiments have been conducted to confirm the efficiency of this control architecture. The experimental results show that not only does the end‐milling system with the design controller have high robustness and global stability, but also the machining efficiency of the end milling system with the proposed controller is 27% higher than for traditional CNC milling system. Copyright © 2011 John Wiley & Sons, Ltd.

Quality is in machining usually defined with the surface quality of the machined part. The main influence comes from the selected cutting conditions - parameters. Monitoring of these parameters and the influence of them can be determined with different methods and systems. In this paper the development and application of a new monitoring system, based on visual detection, is described. The used equipment and software is outlined. Primary purpose of the system is to visually detect any problems or events improper for the selected cutting process. A program for insert and chip detection is developed and tested. Results are given and guidelines for further work are laid.

Original scientific paper This paper shows a thermal and tension analysis of a brake disc for railway vehicles. The FEM (Finite Element Method) was used to carry out the analysis. The analysis deals with one cycle of braking – braking from maximum velocity to a standstill, cooling off faze and then accelerating to maximum velocity and again braking to a standstill. This case of braking represents a part of a railway working conditions. The main boundary condition in this case was the entered heat flux on the braking surface, the centrifugal load and the force of the brake clamps. One type of disc was used with permitted wearing.

The aim of this paper is to present a tool condition monitoring (TCM) system that can detect tool breakage in real time using a combination of a neural decision system, an ANFIS tool wear estimator and a machining error compensation module. The principal presumption was that the force signals contain the most useful information for determining tool condition. Therefore, the ANFIS method is used to extract the features of tool states from cutting force signals. The trained ANFIS model of tool wear is then merged with a neural network for identifying tool wear condition (fresh, worn). A neural network is used in TCM as a decision making system to discriminate different malfunction states from measured signals. The overall machining error is predicted with very high accuracy by using the deflection module and a large percentage of it is eliminated through the proposed error compensation process. The fundamental challenge to research was to develop a single-sensor monitoring system, reliable as a commercially available system, but much cheaper than the multi-sensor approach.

Reliable tool wear monitoring system is one of the important aspects for achieving a self-adjusting manufacturing system.The original contribution of the research is the developed monitoring system that can detect tool breakage in real time by using a combination of neural decision system and ANFIS tool wear estimator.The principal presumption was that force signals contain the most useful information for determining the tool condition.Therefore, the ANFIS method is used to extract the features of tool states from cutting force signals.ANFIS method seeks to provide a linguistic model for the estimation of tool wear from the knowledge embedded in the artificial neural network.The ANFIS method uses the relationship between flank wear and the resultant cutting force to estimate tool wear.A series of experiments were conducted to determine the relationship between flank wear and cutting force as well as cutting parameters.Speed, feed, depth of cutting, time and cutting forces were used as input parameters and flank wear width and tool state were output parameters.The forces were measured using a piezoelectric dynamometer and data acquisition system.Simultaneously flank wear at the cutting edge was monitored by using a tool maker's microscope.The experimental force and wear data were utilized to train the developed simulation environment based on ANFIS modelling.The artificial neural network, was also used to discriminate different malfunction states from measured signals.By developed tool monitoring system (TCM) the machining process can be on-line monitored and stopped for tool change based on a pre-set tool-wear limit.The fundamental limitation of research was to develop a singlesensor monitoring system, reliable as commercially available system, but 80% cheaper than multisensor approach.

The process of surface roughness formation is complex and dependent on numerous factors. The analysis of the latest reports on the subject shows that mathematical relationships used for determining surface irregularities after turning and milling are not complete or accurate enough and, therefore, need to be corrected. A new generalized mathematical model of roughness formation was developed for surfaces shaped with round-nose tools. The model provides us with a quantitative analysis of the effects of the tool representation, undeformed chip thickness, tool vibrations in relation to the workpiece, tool runout (for multicutter tools) and, indirectly, also tool wear. This model can be used to prepare separate models for most of the typical machining operations. Surface roughness is represented here by two parameters Ra and Rt. Simulations carried out for this model helped to develop nomograms which can be used for predicting and controlling the roughness Ra of surfaces sculptured by face milling. (C) 2009 Journal of Mechanical Engineering. All rights reserved.

As the scope of logistics operations in the company increases from day to day it is necessary to provide quality and reliable IT support to operational work. Selection, implementation and the usage of the support tools is one of the critical tasks. The main tpoic of the article is upgrading the ERP system SAP R3 with the new system of advanced planning and optimization (Advanced Planning and Optimization - APO). In the company Krka, d.d. the business information system SAP R3 is used for to support most processes. For the management and control of production, the system Werum PAS-X is used. In the Supply Chain the APO, which is an upgrade of SAP R3 and is also a leading system for planning in the company has been implemented. All the three systems which are also integrated with each other constitute the basis of a new modern, efficient and transparent Supply Chain system.

Thermal and stress analysis of disc brakes under specific loads (driving downhill and braking to a standstill) was calculated. The FEM (Finite Element Method) was used to carry out the analysis. The analysis dealt with centrifugal load for two cases of braking, braking to a standstill on a flat surface and braking downhill, maintaining constant speed and afterwards braking to a standstill. The main boundary condition in both cases was the entered heat flux on the braking sin face of the disc and the force of the brake clamps. Two different discs were used, one brand new (unused) and one with permitted wearing. (C) 2009 Journal of Mechanical Engineering. All rights reserved.

In the paper an intelligent system, selecting the best set of tools on the basis of the 3D CAD model and the other relevant selection factor, has been conceived, For solving the complex classification problem the artificial intelligence method has been used; the neural networks. This concept has been used for the most widespread cutting process, i.e. turning. The results reached are in conforming with the expectations. A high degree of classification has been reached. The constant increase of the knowledge which the 6 system takes from the growing data base is considered to be a great benefit of the proposed system. Due to robustness and universality it is proper for classifying the cutting tools also in other cutting processes. The resulting solutions are comparable with the solutions given by experts. The system can be quite practically used with minor corrections adapted to the user.