Dr. Zheng Jian

Committee: International Scientific Committee of Industrial and Manufacturing Engineering
University: Hitachi Ltd.
Department: R & D Group
Research Fields: constraint programming, factors considered in scheduling, machine learning, scheduling system,

Publications

1 Towards Developing a Self-Explanatory Scheduling System Based on a Hybrid Approach

Authors: Jian Zheng, Yoshiyasu Takahashi, Yuichi Kobayashi, Tatsuhiro Sato

Abstract:

In the study, we present a conceptual framework for developing a scheduling system that can generate self-explanatory and easy-understanding schedules. To this end, a user interface is conceived to help planners record factors that are considered crucial in scheduling, as well as internal and external sources relating to such factors. A hybrid approach combining machine learning and constraint programming is developed to generate schedules and the corresponding factors, and accordingly display them on the user interface. Effects of the proposed system on scheduling are discussed, and it is expected that scheduling efficiency and system understandability will be improved, compared with previous scheduling systems.

Keywords: Machine Learning, Constraint Programming, factors considered in scheduling, scheduling system

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 797

Abstracts

1 Study on Constitutive Model of Particle Filling Material Considering Volume Expansion

Authors: Zheng Jian, Tong Xin, Xu Jinsheng, Zhou Changsheng

Abstract:

The NEPE (nitrate ester plasticized polyether) propellant is a kind of particle filling material with relatively high filling fraction. The experimental results show that the microcracks, microvoids and dewetting can cause the stress softening of the material. In this paper, a series of mechanical testing in inclusion with CCD technique were conducted to analyze the evolution of internal defects of propellant. The volume expansion function of the particle filling material was established by measuring of longitudinal and transverse strain with optical deformation measurement system. By analyzing the defects and internal damages of the material, a visco-hyperelastic constitutive model based on free energy theory was proposed incorporating damage function. The proposed constitutive model could accurately predict the mechanical properties of uniaxial tensile tests and tensile-relaxation tests.

Keywords: Nonlinear, visco-hyperelastic, dewetting, constitutive model, uniaxial tensile tests

Procedia PDF Downloads 149