Process Knowledge Base Research Articles

Process Fault Diagnosis Based on Process Model Knowledge

A computer assisted fault diagnosis system (CAFD) is considered which allows the early detection and localization of process faults during normal operation or on request. Tt forms an on-line expert system, which consists in an analytic problem solution, a process knowledge base, a knowledge aquisition part and an inference mechanism. The analytic problem solution is based on process parameter estimation, and on the detection of process coefficient changes, which are symptoms of process faults. The process knowledge base comprises analytical knowledge in form of process models and heuristic knowledge in form of fault trees and fault statistics. In the phase of knowledge acquisition the process specific knowledge like theoretical process models, the normal behaviour and fault trees, is compiled. The inference mechanism performs the fault diagnosis, based on the observed symptoms, the fault trees, fault probabilities and the process history. Case study experiments with a d.c.-motor, centrifugal pump and an heat exchanger show the performance of the model based fault diagnosis.

An expert system shell for standardization of VLSI process data base and knowledge base

Manufacturing of VLSI products is one of the most complex processes available today. The variety of different areas involved (production, test, design, process development, production scheduling, sales) makes it a challenge for computer integrated manufacturing. The integration of production, test and design requires a new concepts for data base management and knowledge representations, serving the different applicational needs as well as a unification of organization and terminology. This paper presents an expert system concept with integrated knowledge and data base, that satisfies the complex needs stated above, stressing system transparency and natural language interfaces.

Integrating CAD and CAM through automated process planning

Computer-aided process planning is an important function in the integration of CAD and CAM. There are two approaches in computer-aided process planning— variant and generative. The generative is more suitable to CAD/CAM integration because it can synthesize a process plan. The success of developing a generative process planning system is dependent on the CAD interface and process capability analysis, The direct interface with CAD eliminates the tedious data preparation for a process planning system (i.e., it eliminates coding). The process capability analysis provides an information base for process and sequence selection. This paper presents a generative process planning system—TTPPS (Totally Integrated Process Planning System). TIPPS uses a boundary representation from a CAD database for a part. A user applies the crosshair cursor on a graphics terminal and a menu display to specify surfaces to be machined. The system then utilizes the information stored in a process knowledge base to determine manufacturing processes, sequence, cutting parameters and time estimation. The geometric modelling, process modelling, decision mechanism and a planning example are discussed.