用YFSIM对混合数据系统仿真

ＹＨ—Ｆ２是国防科大研制成功的全数字仿真计算机系统。配置在其上的ＹＦＳＩＭ是非过程的仿真建模语言．它是专为连续动力学系统的实时仿真和时间要求苛刻的仿真而设计的，但也能够适用于仿真连续／离散混合数据系统。本文结合一个混合数据系统的简单实例．详细论述了如何用ＹＦＳＩＭ语言对混合数据系统建模和仿真。

Mixture Preparation and Combustion of CNG Low-Pressure Compound Direct Injection Spark-Ignited Engines

A set of compressed natural gas (CNG) multi-point direct injection system of spark-ignited engines and the corresponding measurement and data acquisition systems were developed in this paper. Based on different injection modes, the mixture formation and combustion of CNG low-pressure direct injection (LPDI) engines were studied under varying factors such as air/ fuel ratio, injection timing. Meanwhile, three-dimensional simulations were adopted to explain the mixture formation mechanisms of CNG low-pressure compound direct injection (LPCDI) mode. On the basis of test results and simulation of the mixture homogeneous degree, the conception of injection window was proposed, and the LPCDI mode was proved to be more beneficial to the mixture concentration stratification formation in cylinder under lean-burning conditions, which resulted in effective combustion and stability.

Typhoon Track Forecast with a Hybrid GSI-ETKF Data Assimilation System

A hybrid grid-point statistical interpolation-ensemble transform Kalman filter (GSI-ETKF) data assimilation system for the Weather Research and Forecasting (WRF) model was developed and applied to typhoon track forecast with simulated dropsonde observations. This hybrid system showed significantly improved results with respect to tropical cyclone track forecast compared to the standard GSI system in the case of Muifa in 2011. Further analyses revealed that the flow-dependent ensemble covariance was the major contributor to the better performance of the GSI-ETKF system than the standard GSI system; the GSI-ETKF system was found to be potentially able to adjust the position of the typhoon vortex systematically and better update the environmental field.

On Hybrid Computer-Aided Tools to Interface Design Data

Recognizing the drawbacks of stand-alone computer-aided tools in engineering, several hybrid systems are suggested with varying degree of success. In transforming the design concept to a finished product, in particular, smooth interfacing of the design data is crucial to reduce product cost and time to market. Having a product model that contains the complete product description and computer-aided tools that can understand each other are the primary requirements to achieve the interfacing goal. This article discusses the development methodology of hybrid engineering software systems with particular focus on application of soft computing tools such as genetic algorithms and neural networks. Forms of hybridization options are discussed and the applications are elaborated using two case studies. The forefront aims to develop hybrid systems that combine the strong side of each tool, such as, the learning, pattern recognition and classification power of neural networks with the powerful capacity of genetic algorithms in global search and optimization. While most optimization tasks need a certain form of model, there are many processes in the mechanical engineering field that are difficult to model using conventional modeling techniques. The proposed hybrid system solves such difficult-to-model processes and contributes to the effort of smooth interfacing design data to other downstream processes.

ONFS： a hierarchical hybrid file system based on memory, SSD, and HDD for high performance computers

With supercomputers developing towards exascale, the number of compute cores increases dramatically, making more complex and larger-scale applications possible. The input/output （I/O） requirements of large-scale applications, workflow applications, and their checkpointing include substantial bandwidth and an extremely low latency, posing a serious challenge to high performance computing （HPC） storage systems. Current hard disk drive （HDD） based underlying storage systems are becoming more and more incompetent to meet the requirements of next-generation exascale supercomputers. To rise to the challenge, we propose a hierarchical hybrid storage system, on-line and near-line file system （ONFS）. It leverages dynamic random access memory （DRAM） and solid state drive （SSD） in compute nodes, and HDD in storage servers to build a three-level storage system in a unified namespace. It supports portable operating system interface （POSIX） semantics, and provides high bandwidth, low latency, and huge storage capacity. In this paper, we present the technical details on distributed metadata management, the strategy of memory borrow and return, data consistency, parallel access control, and mechanisms guiding downward and upward migration in ONFS. We implement an ONFS prototype on the TH-1A supercomputer, and conduct experiments to test its I/O performance and scalability. The results show that the bandwidths of single-thread and multi-thread ＇read＇/＇write＇ are 6-fold and 5-fold better than HDD-based Lustre, respectively. The I/O bandwidth of data-intensive applications in ONFS can be 6.35 timcs that in Lustre.

A formal structure for symbolic reachability analysis of rectangular hybrid systems

For symbolic reachability analysis of rectangular hybrid systems, the basic issue is finding a formal structure to represent and manipulate its infinite state spaces. Firstly, this structure must be closed to the reachability operation which means that reachable states from states expressed by this structure can be presented by it too. Secondly, the operation of finding reachable states with this structure should take as less computation as possible. To this end, a constraint system called rectangular zone is formalized, which is a conjunction of fixed amount of inequalities that compare fixed types of linear expressions with two variables to rational numbers. It is proved that the rectangular zone is closed to those reachability operations-intersection, elapsing of time and edge transition. Since the number of inequalities and the linear expression of each inequality is fixed in rectangular zones, so to obtain reachable rectangular zones, it just needs to change the rational numbers to which these linear expressions need to compare. To represent rectangular zones and unions of rectangular zones, a data structure called three dimensional constraint matrix(TDCM) and a BDD-like structure rectangular hybrid diagram(RHD) are introduced.