No abstract

The classification performance of support vector machine (SVM) algorithm is highly dependent on the careful tuning of hyper-parameters and penalty coefficient. This paper introduces a novel SVM parameter optimization method by using the advanced whale optimization algorithm (AWOA) that is an improved whale of algorithm (WOA) with external archiving strategy. A new framework for SVM parameter optimization based on AWOA is built. To demonstrate the performance of our proposed method, six typical data sets are chosen to evaluate the effect of SVM classification problem. Experimental results show that the higher accuracy and better convergence can be achieved by AWOA compared with other three usual parameter optimization methods (WOA, PSO, and DE).

The wide application of large inertia loads in space drive mechanisms is relatively rare in theoretical research. An 8-degree-of-freedom nonlinear dynamic model is established for the time-varying and nonlinear perturbation problems of a large inertia load space drive mechanism. The model is a two-stage spur gear model in which the effects of backlash and time-varying stiffness are considered. The 3D model was imported into ADAMS, and the nonlinear dynamic response of the system was studied by motion simulation. This paper sets up a large inertia experimental device to collect and process data. Comparing experimental results with Adams results, the correctness of the numerical model was verified, and the reasons for the differences between the two were explained. A comparative analysis of the load response under different inertia was performed to illustrate the importance of studying large inertia loads. The simulation results show that the output shaft has a great influence on the dynamic response. Changing the material of the gear can improve the transmission precision of the gear system. The analysis results in this paper enrich the research on the dynamic response of gear system, and provide a theoretical basis for the subsequent design of large inertia load gear system and improve vibration and noise during operation.

To improve the workshop production efficiency and degree of automation, a PLC based magnetic guided AGV (automated guided vehicle) transport trolley was designed. Taking PLC as the control core and the inductance as the path detection sensor, hardware and software are developed. The inductance signal is amplified by the operational amplifier LM358, and the design of the AGV transport vehicle is completed according to the control and process requirements of the AGV system. Use Solidworks modeling the AGV, and simulate the actual path of motion simulation. Use CodeSys of the PLC programming and Realization of motion control, and on the scene of the input and output panel monitoring and simulation test. The test results show that the system has characteristics of simple operation, stable operation, reliable operation, etc., and can meet the design requirements.

Aiming at the distributed architecture of embedded computer system, the network communication middleware is designed based on Lightweight Communication and Marshalling (LCM). In order to improve the reliability and performance of inter-board message interaction, middleware realizes the bidirectional named pipeline, message publication confirmation mechanism, subscription message multithreading processing mode and other improved design schemes, and provides the standardized programming interface while inheriting the topic of “publish-subscribe” based on LCM. Finally, the message transmission delay design was tested on the hardware (Loongson 2K1000 processor) and software (VxWorks operating system) platform. The results show that the message transmission delay is very close to that of traditional UDP by using LCM-based embedded inter-board network communication middleware.