Bayesian Regularization Algorithm Based Recurrent Neural Network Method and NSGA-II for the Optimal Design of the Reflector

The optical-mechanical system of a space camera is composed of several complex components, and the effects of several factors (weight, gravity, modal frequency, temperature, etc.) on its system performance need to be considered during ground tests, launch, and in-orbit operation. In order to meet the system specifications of the optical camera system, the dimensional parameters of the optical camera structure need to be optimized. There is a highly nonlinear functional relationship between the dimensional parameters of the optical machine structure and the design indexes. The traditional method takes a significant amount of time for finite element calculation and is less efficient. In order to improve the optimization efficiency, a recurrent neural network prediction model based on the Bayesian regularization algorithm is proposed in this paper, and the NSGA-II is used to globally optimize multiple prediction objectives of the prediction model. The reflector of the space camera is used as an example to predict the weight, first-order modal frequency, and gravitational mirror deformation root mean square of the reflector, and to complete the lightweight design. The results show that the prediction model established by BR-RNN-NSGA-II offers high prediction accuracy for the design indexes of the reflector, which all reach over 99.6%, and BR-RNN-NSGA-II can complete the multi-objective optimization search efficiently and accurately. This paper provides a new idea of optimization of optical machine structure, which enriches the theory of complex structure design.

Experimental investigation into the implications of transmission errors for rack-and-pinion drives

Rack-and-pinion drives are the preferred option in the machine tool sector when long ranges of motion and high loads are involved. However, their shortcomings particularly include deficiencies in the achievable positioning and path accuracy. The backlash as one of the main issues is well described in the literature and numerous solutions to reduce its negative effects exist. In contrast, there is a lack of literature regarding the scientific and systematic analysis of the transmission errors in rack-and-pinion drives. In this paper, the displacements originating in the drive train of a system with industrial components are measured under different operating conditions. The observed transmission errors are thoroughly analyzed in no-load operation and their sources are discussed. Subsequent investigations show significant load-dependent alterations of the transmission errors and direction-dependent characteristics, the causes of which are explained. It is shown, that transmission errors negatively affect the path accuracy of position controlled drives, which is amplified by excitation of the machine structure in certain operating conditions. To address this issue, different error compensation concepts are presented.

A PROPOSAL FOR A SYSTEMATIZATION AND TAXONOMY OF METHODS TO RECTIFY THERMALLY INDUCED ERRORS ON EXISTING MACHINE TOOLS

In most sectors of today’s industry, there is the requirement to manufacture work pieces with accuracy in micron range. However, maintaining this accuracy can be considerably impeded by thermally induced displacements which arise in the production process. Thermally induced errors cause large parts of residual machining errors on modern machine tools. Using climate control systems for whole workshops can counteract these errors. Yet, this method is extremely cost and energy intensive. To increase machine accuracy and meet the industrial demands in a more efficient way, research offers various methods to minimize this error. These methods differ greatly in their approaches and requirements. Some intervene in the machine structure, while others are based on thermomechanical models and need to be integrated into the software of the control system as correction algorithms. Since machine tools also vary in their kinematic structure and complexity, it is difficult for potential users to select suitable solutions and estimate the effort required to implement them with the available resources. This paper presents a systematization and taxonomy of such methods, which was elaborated based on solutions developed in the project CRC/TR 96. By conducting semi-structured expert interviews, the functional principle, prerequisites and resources required for the application of each solution were recorded, categorized and evaluated in terms of their effort. Based on the presented systematization, it is possible to compare these different methods and evaluate them regarding their implementation effort and flexibility. This is the first step towards a user-specific evaluation of these methods in the future and towards facilitating the transfer of this fundamental research into industrial application.

EXAMINATION OF COOLING SYSTEMS IN MACHINE TOOLS REGARDING SYSTEM STRUCTURE AND CONTROL STRATEGIES

When analyzing machine tools it is observable that despite sufficient cooling capacity thermo-elastic deformation of the machine structure is badly compensated due to heat input. The reason is the missing adaption of coolant and heat input into the system structure during the process, resulting in insufficient productivity and quality. In this paper, various system configurations are shown that can be used to achieve both adequate thermal performance and a reduction in energy consumption.

Optimization of Optical Machine Structure by Backpropagation Neural Network Based on Particle Swarm Optimization and Bayesian Regularization Algorithms

Fit of the highly nonlinear functional relationship between input variables and output response is important and challenging for the optical machine structure optimization design process. The backpropagation neural network method based on particle swarm optimization and Bayesian regularization algorithms (called BMPB) is proposed to solve this problem. A prediction model of the mass and first-order modal frequency of the supporting structure is developed using the supporting structure as an example. The first-order modal frequency is used as the constraint condition to optimize the lightweight design of the supporting structure’s mass. Results show that the prediction model has more than 99% accuracy in predicting the mass and the first-order modal frequency of the supporting structure, and converges quickly in the supporting structure’s mass-optimization process. The supporting structure results demonstrate the advantages of the method proposed in the article in terms of high accuracy and efficiency. The study in this paper provides an effective method for the optimized design of optical machine structures.

Effect of Time-Varying Moving Structures on the Spatial Accuracy of Five-Axis Machine Tools

Machine tools are constantly in motion during machining; however, studies have not considered the effect of the dynamic and static characteristics of the machine caused by the movement of the structure over time. In this study, the time-varying moving structure in the spatial coordinate arm is analyzed to improve the spatial accuracy of the motion of a five-axis machine tool in the cutting area. The objective is to design a high-speed five-axis moving-column machine tool and to perform structural analysis of spatial accuracy. We studied the static and dynamic characteristics of a five-axis machine tool, designed and improved its mechanical structure, and optimized its structural configuration. With further analysis, the entire machine structure was enhanced to improve its static and dynamic characteristics. The static and dynamic characteristics of the machine structure were found to directly affect its processing performance and the precision of the workpiece machined by the tool. Through this study, the design technology for speed, accuracy, and surface roughness of the machine tool was further improved.

Development of a vibration free machine structure for high-speed micro-milling center

The demand of ultra-precision micro-machine tools is growing day by day due to exigent requirements of miniaturized components. High accuracy, good dimensional precision and smooth surface finish are the major characteristics of these ultra-precision machine tools. High-speed machining has been adopted to increase the productivity using high-speed spindles. However, machine tool vibration is a major issue in high-speed machining. Vibration significantly deteriorates the quality of micro-machining in terms of dimensional precision and surface finish. This paper describes a design methodology of a closed type machine structure for vibration minimization of a high-speed micro-milling center. The rigid machine structure has provided plenty of stiffness and the damping capability to the machine tool without utilizing vibration absorbers . The models of the machine structures have been generated and assembled in AutoCAD 3D . The performances of the integrated micro-milling machine tools were determined by finite element analysis. The best model has been selected and proposed for manufacturing. Additionally, simulation results were validated by comparing with experimental results. Eventually, after manufacturing and assembly, experiments have been performed and determined that the amplitude of vibration was approaching towards nanometer level throughout the working range of the high-speed spindle. The machine tool was capable to fabricate miniaturized components with fine surface finish.

Minimization of the automatic machine structure process of accounting and control of railway automation and telemechanics devices

The article explores the features of electronic document management of technical documentation of railway automation and telemechanics. A block diagram of an automaton model of technical documentation is developed. The proposed block diagram of a formalized model of technical documentation consists of matrices of external microoperations, internal microoperations, code creation for the following microcomponents. The number of internal states of the firmware is completely determined by the number of logic elements of the algorithms. The size of the matrices depends on the number of operators and logical conditions in the logic circuits of the algorithms. In this paper, a non-maximal group of compatible elements of logic circuits of algorithms is used as a microcommand, which led to the simplification of the matrix of the circuit of the firmware automaton. In the considered method of forming the maximum groups of compatible elements of logic schemes of algorithms, micro operations included in each micro command are performed simultaneously in one microtact. The structure of the firmware of the machine is simplified due to the transition from simple to complex micro-ops.