Marcin Amarowicz

Development Environment for Diagnostic Multimodal Statement Networks

Development of effective diagnostic systems for the recognition of technical conditions of complex objects or processes requires the use of knowledge from multiple sources. Gathering of diagnostic knowledge acquired from diagnostic experiments as well as independent experts in the form of an information system database is one of the most important stages in the process of designing diagnostic systems. The task can be supported through suitable modeling activities and diagnostic knowledge management. Briefly, this paper presents an example of an application of multimodal diagnostic statement networks for the purpose of knowledge representation. Multimodal statement networks allow for approximate diagnostic reasoning based on a knowledge that is imprecise or even contradictory in part. The authors also describe the software environment REx for the development and testing of multimodal statement networks. The environment is a system for integrating knowledge from various sources and from independent domain experts in particular.

Simulators for Defining of Requirements for Diagnostic Systems

The paper deals with the problem of designing diagnostic systems. It was noticed that the expected functionalities of such systems can be described by sets of requirements. In many cases, different solutions of diagnostic systems will be described by these requirements. One important task is the problem of selecting optimal solution from these sets of likely solutions. This task could be difficult and time-consuming in case of large set of likely solutions of the diagnostic systems. Therefore, it is necessary to limit this set to some subset of solutions, which contains useful examples from the diagnostic point of view. The relations technical state → symptom can be used for this purpose. For simple technical objects these relations can be elaborated based on the available literature data, which describes the process of their utilization. This approach will be difficult for more complex objects which contain e.g. innovative solutions. As the answer to this problem the author proposes diagnostic simulators.

Faults diagnosis using self-organizing maps: A case study on the DAMADICS Benchmark problem

This paper deals with a method of faults detection and identification based on the clusterization of the multiple diagnostic signals. Various types of faults and character of their occurrence were simulated using DAMADICS Benchmark Process Control System. A great advantage of the applied approach based on self-organizing (Kohonen) maps is that even the smallest differences in signals allow for detection, isolation and identification of type of occurred faults with respect to the healthy condition of the investigated system based on the unsupervised learning. It was shown that in some cases the faults, which are undetectable during monitoring of simple heuristic and statistical parameters and other previously applied methods, are recognizable when the approach based on self-organizing maps is applied. The case studies presented in this paper show the faults detection procedure as well as clusterization of types and successful classification of almost all the unique faulty states of the investigated system.

Management of requirements for the projects of the diagnostic systems

The paper deals with the problem of designing diagnostic systems for technical objects such as power plant, machining etc. The new approach for this problem that is based on the methodology that are used in the design of machines and some aspects of requirement engineering that derived from the software area is considered in the article. In general case the requirements may be used to formalized notation of the project need, that described the designed diagnostic systems. The evaluation of gathered set of requirements may be done by using the specialized expert systems, that may be developed as part of proposed approach. The whole process related to gathering, writing and evaluation of requirements for the purpose of designing diagnostic system is presented in the article.

Multimodal Statement Networks for Organic Rankine Cycle Diagnostics – Use Case of Diagnostic Modeling

The paper shows an example of application of modeling process of diagnostic knowledge with the use of multimodal statement networks. The goal is to present generic approach to modeling complex diagnostic domains by many independent experts. As an object cogeneration power plant with Organic Rankine Cycle is presented. Implementation of diagnostic model was performed using REx system that enables among other things knowledge management and the application and preliminary evaluation of diagnostic knowledge of gathered knowledge for the purpose of its further incorporation to diagnostic systems.

Clustering of Delaminations in Composite Rotors Using Self-Organizing Maps

The study presented in this paper concerned with the evaluation of delamination presence and its type basing on the analysis of vibration data of composite rotors using Kohonen self-organizing maps. The approach used for the evaluation considered axial displacements of modal shapes of rotated composite rotors with simulated delaminations and measurement points on the surface of a rotor in order to detect and classify the delaminations with respect to their geometric properties and location. A large number of numerical models with simulated delaminations were considered in order to create representative training sets. Obtained results show that the proposed approach allows for detection of delaminations with unknown shapes and locations. The approach could be further applied in practical solutions using advanced non-contact or embedded measurement systems.

Application of the REx5 Expert System to Condition Monitoring of the Simple Liquid Flow Process Control Trainer

This work deals with the problems that are related to the condition monitoring of the selected technical object. For this purpose, specialized software called REx5 was developed. The REx5 is a modular expert system. Inference module of this system allows to conduct the inference process for two types of knowledge representation: the intuitionistic and Bayesian statement networks. All data required for the inference processes are stored in especially designed OPC UA Server with archive database of process data. Another module, designed to manage diagnostic tasks, allows to configure the parameters for condition monitoring of observed technical object. The simple liquid flow process control trainer is the studied object. This trainer allows for various control functions, like the control of the medium level in the tank, control of the flow rate, or control of the medium temperature. Additionally, the trainer is equipped with a data acquisition subsystem. The purpose of this subsystem is the acquisition values of the selected process signals and sharing these data for external systems used by OPC UA Server.