Search results

The purpose of this paper is to propose an accurate and practical imitation learning for robotics. The modified dynamic movement primitives (DMPs), global fitting DMPs (GLDMPs), is presented. Framework design, theoretical derivation and stability proof of GLDMPs are discussed in the paper.

Based on the DMPs, the hierarchical iterative parameter adaptive framework is developed as the hierarchical iteration stage of the GLDMPs to tune the designed parameters adaptively to extract richer features. Inspired by spatial transformations, the coupling analytical module which can be regarded as a reversible transformation is proposed to analyze the high-dimensional coupling information and transfer it to trajectory.

With the proposed framework and module, DMPs derive majority features of the demonstration and cope with three-dimensional rotations. Moreover, GLDMPs achieve favorable performance without specialized knowledge. The modified method has been demonstrated to be stable and convergent through inference.

GLDMPs have an advantage in accuracy, adaptability and practicality for it is capable of adaptively computing parameters to extract richer features and handling variations in coupling information. With demonstration and simple parameter settings, GLDMPs can exhibit excellent and stable performance, accomplish learning and generalize in other regions. The proposed framework and module in the paper are useful for imitation learning in robotics and could be intuitive for similar imitation learning methods.

Gives a bibliographical review of the finite element methods (FEMs) applied for the linear and nonlinear, static and dynamic analyses of basic structural elements from the theoretical as well as practical points of view. The range of applications of FEMs in this area is wide and cannot be presented in a single paper; therefore aims to give the reader an encyclopaedic view on the subject. The bibliography at the end of the paper contains 2,025 references to papers, conference proceedings and theses/dissertations dealing with the analysis of beams, columns, rods, bars, cables, discs, blades, shafts, membranes, plates and shells that were published in 1992‐1995.

This paper gives a review of the finite element techniques (FE) applied in the area of material processing. The latest trends in metal forming, non‐metal forming, powder metallurgy and composite material processing are briefly discussed. The range of applications of finite elements on these subjects is extremely wide and cannot be presented in a single paper; therefore the aim of the paper is to give FE researchers/users only an encyclopaedic view of the different possibilities that exist today in the various fields mentioned above. An appendix included at the end of the paper presents a bibliography on finite element applications in material processing for 1994‐1996, where 1,370 references are listed. This bibliography is an updating of the paper written by Brannberg and Mackerle which has been published in Engineering Computations, Vol. 11 No. 5, 1994, pp. 413‐55.

This paper gives a review of the finite element techniques (FE) applied in the area of material processing. The latest trends in metal forming, non‐metal forming and powder metallurgy are briefly discussed. The range of applications of finite elements on the subjects is extremely wide and cannot be presented in a single paper; therefore the aim of the paper is to give FE users only an encyclopaedic view of the different possibilities that exist today in the various fields mentioned above. An appendix included at the end of the paper presents a bibliography on finite element applications in material processing for the last five years, and more than 1100 references are listed.

The purpose of this paper is to study various combination forms of the three basic sharing elements (i.e. orders sharing, manufacturers capacity sharing and suppliers capacity sharing) in the cluster supply chain (CSC), formulate a distributed model to protect enterprises’ decision privacy and seek to develop an effective method for solving the distributed complex model.

A distributed assembly cluster supply chain configuration (ACSCC) model is formulated. An improved augmented Lagrangian coordination (ALC) is proposed and used to solve the ACSCC model. A series of experiments are conducted to validate the improved ALC and the model.

Two major findings are obtained. First, the market order’s quantity change and the sales price of the product have a great impact on both the optimal results of the ACSCC and the cooperative strategy, especially, when the market order increases sharply, enterprises have to adopt multiple cooperative strategies to complete the order; meanwhile, the lower sales price of the product helps independent suppliers to get more orders. Second, the efficiency and computational accuracy of the improved ALC method are validated as compared to the centralized ALC and Lingo11.

This paper formulated the single-period ACSCC model under certain assumptions, yet a multi-period ACSCC model is to be developed, a more comprehensive investigation of the relationships among combination forms is to be extended further and a rigid proof of the improved ALC is necessary.

Enterprises in the industrial cluster should adopt different cooperative strategies in terms of the market order’s quantity change and the sales price of the product.

The proposed various combination forms of sharing elements and the formulated ACSCC model provide guidance to managers in the industrial cluster to choose the proper policy.

This research studies various combination forms of the three basic sharing elements in the CSC. A distributed ACSCC model has been established considering simultaneously multiple sharing elements. An improved ALC is presented and applied to the ACSCC problem.

Flexible tooling for adjusting the posture of large components of aircraft (LCA) is composed of several numerical control locators (NCLs). Because of the manufacture and installation errors of NCL, the traditional control method of NCL may cause great interaction force between NCLs and form the internal force of LCA during the process of posture adjustment. Aiming at this problem, the purpose of this paper is to propose a control method for posture adjustment system based on hybrid force-position control (HFPC) to reduce the internal force of posture adjustment.

First of all, the causes of internal force of posture adjustment were analyzed by using homogeneous transformation matrix and inverse kinematics. Then, axles of NCLs were divided into position control axle and force control axle based on the screw theory, and the dynamic characteristics of each axle were simulated by MATLAB. Finally, a simulated posture adjustment system was built in the laboratory to carry out HFPC experiment and was compared with the other two traditional control methods for posture adjustment.

The experiment results show that HFPC method for redundant actuated parallel mechanism (RAPM) can significantly reduce the interaction force between NCLs.

In this paper, HFPC is applied to the control of the posture adjustment system, which reduces the internal force of LCA and improves the assembly quality of aircraft parts.

Compared with the time-consuming numerical method and the complex lumped parameter thermal network method to solve the steady-state heat distribution of the permanent magnet (PM) linear motor, there is no analytical method based on the thermal partial differential equations. This paper aims to propose a two-dimensional (2-D) analytical model for predicting the steady-state temperature distribution of PM linear motors to improve the prediction accuracy and speed up the calculation.

Based on the complex Fourier series theory and Cauchy’s product theorem, this paper presents for the first time a general analytical solution for 2-D temperature field in Cartesian coordinates. Then, by combining the electromagnetic field finite element model (FEM), the copper loss, iron loss and PM eddy current loss are used as the heat sources of the thermal analytical model. Finally, the solution to the temperature field is obtained by solving the system equations under boundary and interface conditions.

The analytical results are in good agreement with those from the thermal FEM, and the calculation speed is significantly faster than that of the thermal FEM.

The multilayer model proposed in this paper can consider heat conduction, convection and radiation. It is not only suitable for PM linear motors but also has significant application value for the thermal analysis of electromagnetic devices modeled in 2-D Cartesian coordinates.

This paper aims to propose an innovative parametric design for artificial neural network (ANN) modeling for the multi-quality function problem to determine the optimal process scenarios.

The innovative hybrid algorithm gray relational analysis (GRA)-ANN and the GRA-Entropy are proposed to effectively solve the multi-response optimization problem.

Both the GRA-ANN and the GRA-Entropy analytical approaches find that the optimal process scenario is a stencil aperture of 57 per cent and immediate processing of the printed circuit board after exposure to a room environment.

A six-week confirmation test indicates that the optimal process has improved quad flat non-lead assembly yield from 99.12 to 99.78 per cent.

The US-China trade war has brought forth the problem of balance of trade not only for them, but also for many other economies in the world. However, all the commodity segments are not equally affected and thus, the segment-wise trade analysis of commodities can bring up many valuable insights, vital for policy formulation process. Despite this, existing literature barely covered this aspect as a focal research. Therefore, this chapter has carried out segment-wise analysis of commodity classes popular in international trade discussions for the United States and China since the trade dispute intensified between them. In this chapter, we have built an argument around three commodity-segments which are popular in international trade studies namely, the raw material segment, semi-finished goods segment, and finished goods segments. While doing this analysis, we majorly focused on monopolistic power of economies in different commodity segments. We found that while in the segment of raw material, mostly cost is driving the trade, in the finished goods segment, variety and innovations are the key drivers that can boost trade by discovering new consumption spaces.