A feature-recognition knowledge base for process planning of rotational mechanical components

A computer-aided process-planning (CAPP) system is a key factor in CAD/CAM Integration. In recent years, expert-system techniques have been introduced into this area. An increasing number of AI-based generative process-planning systems have been developed to automate machine process selection and tools selection. Of these, EXCAP, an integrated knowledge-based system developed at UMIST, distinguishes itself by its flexibility and ease of use. This paper gives an overview of EXCAP and focuses on the feature-recognition knowledge base.     

A knowledge-based jig-and-fixture designers' assistant

The state of the art in the technology of jigs and fixtures is reviewed. Heuristic and analytical principles of jig and fixture design are summarised. An interactive knowledge-based program for assisting designers of jigs and fixtures is described. The program incorporates design principles in the form of explicity declared facts and rules as well as numerical procedures. The declarative part of the program is implemented in an expert system shell with a powerful inference engine and comprehensive explanation and trace facilities. Details of these are given, together with a simplified example of a design session using the program.     

Process planning via computerassisted classification and coding

This paper describes the development of a classification system for process planning. The system generates both a process plan for production and a classification number based on classification theory. The system is implemented in the C programming language with interfaces to a relational database. This allows the generated process plan and the classification number to be loaded into the database for information retrieval.     

Concurrent design of manufacturing cell and control functions: A neural network approach

This paper presents a neural network based decision support system (DSS) for use in concurrently determining cell configuration, operation plans, and complexity requirements of cell control functions. Advanced simulators and neural network technology are used in developing the DSS. Simulation experiments were conducted with many possible combinations of design changes to generate training pairs for a neural network. Complexity of cell control functions required by each design option was assessed, based on operational requirements, and was used to train another neural net. Once both neural networks are properly trained, one network can be used to predict the cell design configuration given a set of desirable cell performance measures, while the other network can be used to identify complexity requirements of the cell control functions by using the output provided by the first network as input to the second neural net. An operation-driven cell design methodology was applied to sequentially predict requirements of both cell configuration and cell control functions from the trained neural networks. This innovative new design methodology was illustrated via a successful implementation exercise in acquiring a real automated manufacturing cell at industrial settings. The exercise proves that such a DSS serves well as an effective tool for cell designers and the management in determining appropriate cell configuration and cell control functions at the design stage.     

Integration of inspection planning system and CMM via DMIS

INSPEX is a computer-aided knowledge based inspection planning system for preparing inspection plans from CAD toleranced component models of rotational components. To achieve the complete automation of the inspection process, INSPEX has been integrated with CMMs (computer controlled coordinate measuring machines) via DMIS (Dimensional Measuring Interface Specification), where DMIS has been as a data exchange standard. The inspection procedures produced by INSPEX can be automatically converted into DMIS data format file by the DMIS pre-processor described in this paper, which can be fed into any CMMs with a DMIS interface for executing the inspection procedures.     

On-line cutting state recognition in turning Using a neural network

Tool wear, chatter vibration, chip breaking and built-up edge are the main phenomena to be monitored in modern manufacturing processes. Much work has been carried out in the analysis and detection of these phenomena. However, most work has been mainly concerned with single, isolated detection of such phenomena. The relationships between each fault have so far received very little attention. This paper presents a neural-network-based on-line fault diagnosis scheme which monitors the level of tool wear, chatter vibration and chip breaking in a turning operation. The experimental results show that the neural network has a high prediction success rate.     

Verification of ionization chamber theory

The response of a standard ionization detector to artificially generated test aerosols as well as to test fire and smoke has been determined experimentally. The size distribution and number concentration of these aerosols have been measured by independent methods.     

An integrated decision support system for FMS production planning and scheduling problems

This paper discusses planning and scheduling problems for efficient use of an FMS and presents an integrated decision support system for dealing with these problems.The decision support system, FMSDS (Flexible Manufacturing Systems Decision Support System), includes several modules: data handling module, part selection module, loading module, load adjusting module, scheduling module and simulation module.This paper suggests the solution methodology of each subproblem. Also, an integrated interface scheme between the subproblems is presented. The interface scheme considers the relationships between the subproblems and generates solutions using hierarchical and looping approaches.FMSDS is made up of six alternative models considering three loading objectives and two production order processing strategies. Performance comparison among the six alternatives is shown using the non-terminating simulation techniques.     

NC toolpath generation for arbitrary pockets with Islands

This paper presents an efficient algorithm for generating cutter paths for the NC milling of arbitrary pockets with multiple islands. In this algorithm, the pocket border and island profiles are made up of concave or convex segments comprising linear and circular arc elements. For the generation of NC tool paths, the algorithm is divided into four stages, namely, profile pre-processing stage, offset calculation, determination of the termination condition, and determination of the path sequence. Compared with the other pocketing algorithms, the main aspect of this work is that the pocket border and island profiles are pre-processed in the first stage of the algorithm. Making use of contour bridges in the profile pre-processing stage, the island profiles are connected to the pocket border profile to form a closed path. This then simplifies the calculations in cutter offsets and eliminates the problem of nesting which occurs in some other pocketing algorithms.