A Novel Principal Component Analysis Integrating Long Short-Term Memory Network and Its Application in Productivity Prediction of Cutter Suction Dredgers

Dredging is a basic construction for waterway improvement, harbor basin maintenance, land reclamation, environmental protection dredging, and deep-sea mining. The dredging process of cutter suction dredgers is so complex that the operational data show strong characteristics of dynamic, nonlinearity, and time delay, which make it difficult to predict the productivity accurately via basic principles models. In this paper, we propose a novel integrating PCA-LSTM model to improve the productivity prediction of cutter suction dredger. Firstly, multiple variables are reduced in dimension and selected by PCA method based on the working mechanism of cutter suction dredger. Then the productivity is predicted via mud concentration in long short-term memory network with relevant operational time-series data. Finally, the proposed method is successfully applied to an actual case study in China. Also, it performs well in the cross-validation and comparative study for several important characteristics: (i) it involves the operational parameters based on the mechanism analysis; and (ii) it is a deep-learning-based approach that can deal with operation series data with a special memory mechanism. This study provides a heuristic idea for integrating the data-driven method and supervision of human knowledge for application in practical engineering.

Electromagnetic piezoelectric hybrid driven multi-DOF motor contact model considering drive and load state

This paper proposes a new research method in view of the rare research on the contact state of hybrid drive multi-degree-of-freedom motor. Firstly, the basic principle and structure of hybrid drive motor are introduced. The air gap magnetic field model and electromagnetic torque model of permanent magnet rotor are obtained by analytical method. Static analysis of piezoelectric stators are carried out by stress-strain relationship. According to the analytical method and the spatial geometric relationship, the piezoelectric driving torque under different driving conditions is obtained. Introducing Hertz contact theory and Mindlin theory, combined with piezoelectric driving torque, electromagnetic driving torque and load torque to analyze the friction situation. A friction interface model considering the dynamic nonlinearity of friction coefficient and the nonlinear change of friction force distribution is established. Finally, using Matlab software, the friction distribution diagram of the contact surface of the hybrid drive three-degree-of-freedom motor under different driving and motion states is obtained. The analysis results verify the rationality of the electromagnetic piezoelectric hybrid driven three-degree-of-freedom motor. It shows that the contact state of the three sets of piezoelectric stators are determined according to the driving condition and load, the relative speed of the piezoelectric stators and the spherical rotor is proportional to the frictional force. It provides an idea for the research of contact state of hybrid drive multi-degree-of-freedom motor, and also lays a basis for further optimizing the friction interface of this kind of motors or actuators.

Nonlinear Modeling for Broadband Power Amplifiers based on Cloud Computing

This paper discusses the nonlinear dynamic behavior modeling for broadband power amplifiers based on cloud computing. The nonlinear parameters of the wideband amplifier were extracted through remote data acquisition and the analysis of the power amplifier’s input and output signals. The Long Short-Term Memory neural network was used to accurately model the dynamic nonlinearity of the power amplifier. It solved the problem of limitation by time and space for the digital pre-distortion system and addressed big data remote processing for the nonlinear modeling of the broadband amplifier in 5G high bandwidth and high rate communication environment. By using the technology, it provides support for the efficient utilization of experimental resources and accurate nonlinear modeling of a broadband power amplifier.