This paper deals with production of safety inlay for steam locomotive valve by the Patternless Process method. For the moulds creation was used moulding mixtures of II. generation, whereas binder was used a water glass. CNC miller was used for creation of mould cavity. Core was created also by milling into block made of moulding compound. In this article will be presented also making of 3D model, setting of milling tool paths and parameters for milling.

The paper presents an off-line application that determines the maximum accuracy of the reference points for the given dynamics parameters of a CNC machine. These parameters are maximum speed, acceleration, and JERK. The JERK parameter determines the rate of change of acceleration. These parameters are defined for each working axis of the machine. The main achievement of the algorithm proposed in the article is the determination of the smallest error specified for each reference point resulting from the implemented G-code for the considered dynamic parameters of the CNC machine. The solutions to this problem in industry consider the improvement in the accuracy of hitting the reference points, but they do not provide information on whether the obtained solution is optimal for such parameters of the machine dynamics. The algorithm makes the accuracy dependent on the adopted dynamic parameters of the machine and the parameters of the PLC controller used in the CNC machine.

Optimization of industrial processes such as manufacturing or processing of specific materials is a point of interest for many researchers, and its application can lead not only to speeding up the processes in question, but also to reducing the energy cost incurred during them. This article presents a novel approach to optimizing the spindle motion of a computer numeric control (CNC) machine. The proposed solution is to use deep learning with reinforcement to map the performance of the Reference Points Realization Optimization (RPRO) algorithm used in industry. A detailed study was conducted to see how well the proposed method performs the targeted task. In addition, the influence of a number of different factors and hyperparameters of the learning process on the performance of the trained agent was investigated. The proposed solution achieved very good results, not only satisfactorily replicating the performance of the benchmark algorithm, but also, speeding up the machining process and providing significantly higher accuracy.

The machining accuracy of CNC machine tools is significantly affected by the thermal deformation of the feed system. The ball screw feed system is extensively used as a transmission component in precise CNC machine tools, responsible for converting rotational motion into linear motion or converting torque into repetitive axial force. This study presents a multi-physical coupling analysis model for the ball screw feed system, considering internal thermal generation, intending to reduce the influence of screw-induced thermal deformation on machining accuracy. This model utilizes the Fourier thermal conduction law and the principle of energy conservation. By performing calculations, the thermal source and thermal transfer coefficient of the ball screw feed system are determined. Moreover, the thermal characteristics of the ball screw feed system are effectively analyzed through the utilization of finite element analysis. To validate the proposed analysis model for the ball screw feed system, a dedicated test platform is designed and constructed specifically to investigate the thermal characteristics of the ball screw feed system in CNC machine tools. By selecting specific CNC machine tools as the subjects of investigation, a comprehensive study is conducted on the thermal characteristics of the ball screw feed system. The analysis entails evaluating parameters like temperature field distribution, thermal deformation, thermal stress, and thermal equilibrium state of the ball screw feed system. By comparing the simulation results from the analysis model with the experimental test results, the study yields the following findings: The maximum absolute error between the simulated and experimental temperatures at each measuring point of the feed system components is 2.4◦C, with a maximum relative error of 8.7%. The maximum absolute error between the simulated and experimental temperatures at the measuring point on the lead screw is 2.0◦C, with a maximum relative error of 6.8%. The thermal characteristics obtained from the steady-state thermal analysis model of the feed system exhibit a prominent level of agreement with the experimental results. The research outcomes presented in this paper provide valuable insights for the development of ball screw feed systems and offer guidance for the thermal design of machine tools.