As a common support of M&S (Modeling and Simulation) applications, M&S language and platform can effectively improve M&S capability for complex objects and systems. This paper proposes an Intelligent system Modeling and Simulation Language (IMSL) which integrates artificial intelligence theory and M&S technology to describe intelligent model structures, behaviors, facts, knowledge, and rules. Meanwhile, an M&S platform is implemented to provide a basic support for M&S of intelligent systems, featured as its convenience, efficiency and problem solving ability. Our research work has been focused on M&S methods and language specification of intelligence systems, intelligent simulation resource libraries and integrated development environment. As an application instance, M&S of a C3I (Command, Control, Communication and Information) system is conducted to evaluate the performance of IMSL and the IMSL platform. And the simulation result proves that IMSL can work effectively in solving practical problems.
System modeling and simulation is playing an important role in the modern field of M&S. With the development of computer technology and the increasing complexity of studied objects, different disciplines are involved and system simulation is tending to be more and more complex. The M&S of intelligent system is to apply intelligent theory and methodology to solve intelligent problems and is widely used in CIMS (Computer Integrated Manufacturing System), CGF (Computer Generated Forces), SBA (Simulation Based Acquisition), and so forth. With the development of artificial intelligent, many kinds of intelligent technologies (knowledge engineering, expert system, intelligent optimization algorithm, multi-agent technology, qualitative reasoning, neural network, etc.) have been widely used on the M&S of intelligent systems. M&S platform and language are aimed to provide a fundamental and universal support for M&S as well as promoting and improving the M&S capability of complex objects and systems. M&S languages are featured as providing the abilities of fast problem solving, convenient system applying and friendly user interface. Furthermore, M&S languages and platforms can free developers from messy work in building systems from scratch, accelerate the process of system development and improve the reuse of models and comparability of results. Therefore, it is important to develop a common and unified M&S platform for intelligent systems which can solve intelligent problems efficiently and reduce the user’s workload.
This paper, in collaboration with applied theory and techniques of artificial intelligence, builds an Intelligent System M&S Platform and proposes an Intelligent system Modeling and Simulation Language (IMSL), which can help to solve M&S problems of intelligent systems. In the M&S process of intelligent systems, there often exists qualitative knowledge. Thus, qualitative and quantitative integration methodology is introduced in IMSL to make full use of qualitative and quantitative information. Another problem is how to improve simulation efficiency, especially for intelligent optimization algorithms which need iterative searching. That is the reason why multi-core environment are highly integrated in the platform. IMSL is defined to support the M&S of systems through describing intelligent model structures, behaviors, facts, knowledge and rules and can be applied to a wide range of systems. And IMSL is designed to tackle with knowledge engineering, expert system, qualitative reasoning and intelligent optimization problems efficiently. Besides, this platform has a user-friendly interface providing both text and graphic development environment and supports the simulation result display of intelligent behaviors.
Related key technologies of Intelligent System M&S Platform are described in detail. The remainder of this paper is organized as follows. Section 2 summarizes related research. Section 3 gives an overview of Intelligent System M&S Platform. Section 4 discusses design and integration of intelligent models. Section 5 presents some key techniques of implementing the integrated development environment, including the definition of IMSL, translating and compiling technology, and simulation engine technology. Section 6 implements a C3I application instance. The functions of IMSL and the platform are verified through the modeling of air force combat rule sets and the simulation of cooperative attack target allocation. Finally, the paper is concluded in Section 7.
This paper proposes an IMSL for the M&S of intelligent systems and develops IMSL platform which provides a bunch of tools for modeling, translation, compiling, debugging and running. Techniques of different fields such as intelligent optimization algorithms, compiling principles, reasoning tools, qualitative theory and parallel computing techniques are used in IMSL. To verify the performance of IMSL platform, a practical model of the C3I application is constructed and simulated in the platform, which verifies that IMSL can work effectively in solving practical problems. Further work will be concentrated on enriching intelligent model libraries, improving graphical modeling approach and debugging function, as well as expanding the range of application, so as to provide more support for M&S of intelligent systems.