Institute for Systems Research

In this thesis, an approach involving the use of a hybrid system involving both neural networks and expert systems for performing automated network fault management is investigated. Data networks using the X.25 protocol are considered. A minimum cost routing scheme is used for re-routing future calls given the occurrence of a fault. A method for partitioning the data (obtained from the X.25 network) between the neural network and the expert system is suggested. Radial basis function networks are used as the neural network architecture for performing fault classification using performance data. Queries are provided for the expert system to determine the type of fault that occurred using the results of the neural network, together with alarms, SNMP traps, and X.25 SNMP statistics.

The work is initially planned to be divided in five parts: assessment of the raw data (measurements from the network), feature extraction (data preprocessing), classification (data clustering according to the network potential problems), system training (tuning methods) and self-improving (module learning capability).

Raw data analysis: The network database will be accessed to identify the, measurement being performed. The data context and problem definition are, also part of the data analysis process. The problem, the solution to the problem and strategies for solving such problems will be defined according to the network management standards. The data organization, parameters being monitored, data context and its amount are the targets at this level of the research.

Feature extraction: The data is preprocessed in such a way that events in the network are converted into a vector of parameters. The vector that is obtained is called "feature vector". The objective at this level is to transform data into information to be used further in the network monitoring system.

Documentation is a key aspect of the registration process. The most important element of the documentation requirements is the quality manual, a collection of documented procedures reflecting the daily operations of a company. The structure, content, and control of the quality manual are critical to the ISO 9000 registration process. However, problems with documentation are the primary cause of failure of an audit.

This thesis work addresses the pressing need to reduce documentation-related problems by designing and developing a software tool that assists users in creating a quality manual. A methodology based on systems engineering principles if followed to ensure that early requirements are understood and met. The unique highlights and contributions of the software developed in support of this thesis include: Emphasis on early analysis activities, especially user analysis, before coding of software.

Performance of trade-off analysis to determine the best Windows programming tool.

Utilization of human factors and graphical user interface (GUI) principles.

Incorporation of ISO 900 tutorial in software.

Formatted screens for easy creation of sections Examples and Help to increase users' understanding of ISO 9000 requirements

As an example, in this paper we describe the techniques for manufacturing-operation planning used in IMACS (Interactive Manufacturability Analysis and Critiquing System). We compare and contrast them with the techniques used in classical AI planning systems, and point out that some of the techniques used in IMACS may also be useful in other kinds of planning problems.

In this thesis work, an investigation is made to study the impact of implementing electronic controls to medium and heavy duty vehicles systems on the shop floor procedure when maintenance is performed. The impact reflects a significant change in the diagnostic procedures. Several manufacturers, such as Cummins, Caterpillar, Detroit Diesel, and Rockwell, design their systems with different electronic control units. Once these different systems are assembled together as a single entity in a vehicle, different formats and procedures must be followed when performing diagnostic procedures. Because of the change of procedures, traditional offboard diagnostic tools have to be replaced by new tools to ensure quality diagnostic repairs, thus introducing the cost consideration to system analysis.

The main contribution of this thesis is to present a Systems Engineering Approach to integrate Medium and Heavy Duty Vehicles Electronic Controls (so the same off-board diagnostic tool can be used on all manufactured vehicles) and Shop Floor Procedures (human factors and quality control in maintenance). An intelligent off-board diagnostic tool will be designed and act as an expert system to aid the service technician(s) in performing diagnostic procedures. Consequently, a significant reduction of work time for repairing can be achieved for productivity improvement, and the retraining of the service technician(s) can also be realized. The results from this thesis work can effectively assist the top managers, service managers, and mechanics in performing diagnostic repairs, and can provide a mean for effective communications between the manufacturers, the repair facilities, and the customers.