PlanMaker, a design knowledge entry tool based on the Falcon Framework, is presented. PlanMaker is a customized version of a spreadsheet. The spreadsheet is linked to a simulator and a schematic capture tool, allowing designers to capture their know-how to domains of design simulation, analysis, and verification. Know-how can be entered without great software expertise and can be stored in reusable external libraries.

A spreadsheet interface for analog design knowledge capture and re-use

A knowledge-based shell for circuit simulation has been developed as a part of a design environment for analog circuits. This shell offers circuit-specific simulation support exploiting expert knowledge for dealing with problems like test function generation and simulation clustering. Furthermore, it provides worst-case analysis capabilities as well as automatic documentation facilities like data sheet generation and a design database. The prototype implementation, SILAS, has been realized as an expert system with blackboard architecture. Knowledge and knowledge execution are strictly separated to allow an easy extension of the incorporated knowledge bases. SILAS is organized as a simulation assistant, which means the user may specify a specific task by a work plan while the task organization and control are taken over by the system. Application areas are all domains which require automated circuit characterization such as synthesis or cell library maintenance. >

SILAS: a knowledge-based simulation assistant

A knowledge-based shell for simulators has been developed as one part of a design environment for analog circuits. This shell offers circuit-specific simulation support exploiting expert knowledge for dealing with problems like test function generation and simulation clustering. Applications areas are all domains that require automated circuit characterization, such as synthesis or cell library maintenance. The prototype version has successfully been developed in the context of the OASE (operational amplifier and analog circuits synthesis expert system) analog circuit synthesis project. Currently it includes the BONSIM device-level simulator and opamp-specific circuit knowledge. >

http://ieeexplore.ieee.org/iel2/140/3519/00124707.pdf

A knowledge based simulation environment

In this paper, LEAR, a concept learning system for decision support in routine design tasks, is presented. LEAR learns incrementally from the instances which are generated during normal design sessions with a host CAD system. To achieve this an existing learning method was adapted to task specific constraints and complemented with several novel approaches to knowledge organization. This includes a flexible distributed concept representation which exploits background knowledge to reduce the complexity of the learning process as well as an efficient method for constructive induction which uses fuzzy sets to determine the most suitable high level attributes.

Incremental Learning for Improved Decision Support in Knowledge Based Design Systems

A novel approach to design automation for analog circuits is presented. The prototype implementation-OASE-has been realized as a set of cooperating expert systems with blackboard architecture. The circuit specific knowledge bases use hybrid representation schemes and are strictly separated from an execution engine containing the necessary control knowledge. This alleviates the knowledge acquisition process as well as the extension and maintenance of existing knowledge. OASE has been developed as a design assistant, featuring different levels of interactivity, a hierarchical design style and fully embedded algorithmic standard tools. In its current version it is able to design a broad range of different CMOS operational amplifiers.

An analog circuit design environment based on cooperating blackboard systems

A novel approach to the design automation of analog circuits is presented. The prototype implementation -OASE- has been realized as a set of cooperating expert systems with blackboard architectures. The circuit specific knowledge bases use hybrid representation schemes and are strictly separated from the execution engine. This alleviates the knowledge acquisition process as well as the extension and maintenance of existing knowledge. OASE has been developed as a design assistant, providing a hierarchical design style and fully embedded standard algorithmic tools.

K. Milzner

Papers

Synthesis of analog circuits using a blackboard approach