Dominik Wachla

Identification of dynamic diagnostic models with the use of methodology of knowledge discovery in databases

This paper deals with an approach to knowledge discovery in databases applied in order to identify a dynamic model of a real-existing machine. The problem considered within the paper is how to identify dynamic models suitable for model-based diagnosing of a physical object. A special attention is paid to identification on unsupervised way, while big databases collected by a SCADA system is handled. In the paper a method of identification of dynamic models of objects and processes is presented. The usefulness of the method in technical diagnostics are shown. The elaborated method of analysis of quantitative dynamic data is based on applications of accessible methods of knowledge discovery in databases. The essence of the method is to project values of considered set of attributes into the so-called multidimensional space of regressors. In order to select the subset of relevant features the genetic algorithm was used. Knowledge was induced using the support vector machines (SVM) method. The AIC measure as well as our own heuristic function were applied as evaluation criteria. The method was applied in a process of discovery of a model of changes of temperature of a pump. Within framework of the research, data gathered by means of an industrial system registering data on a peculiar object, which was deep-well pumping station, was analyzed.

A methodology of leakage detection and location in water distribution networks — The case study

The paper deals with a methodology of detecting and localizing leakages in water distribution networks. Two approaches are presented: based on a hydraulic model of the network, and based on approximate models and fuzzy classifiers. Moreover, a case study concerning applications of the methodology to a real network in Rybnik, Poland is presented. A pilot version of the system has been running since 2013 and shows quite satisfactory efficiency.

Development of Expert System Shell with Context-Based Reasoning

The paper focuses on the expert system shell which is proposed as a tool that can be used for a wide spectrum of industrial applications. A new architecture of the system enables reasoning by means of multi-domain knowledge representations and multi-inference engines. Moreover, the extended functionality of the system is developed using a context based approach. The system is implemented applying a data mining software which makes possible to acquire domain-specific knowledge and its direct application in the expert system shell. In this study, the preliminary verification is presented using the data registered by the SCADA system of the water supply network. The case study results are useful to illustrate the merits and limitations of the proposed approach.

Determination of fatigue limit of polymeric composites in fully reversed bending loading mode using self-heating effect:

In this paper, the fatigue limit in fibre-reinforced polymeric composites loaded in the fully reversed bending loading mode is investigated by using the self-heating effect occurring during such a type of testing. This approach provides the possibility of fast estimation of fatigue limit without the necessity of performing time-consuming high cycle fatigue tests. In order to validate the determined fatigue limit, the obtained results of temperature evolution were compared with the results of acoustic emission measurements. Based on the performed observations and comparisons, a structural degradation of polymeric composites subjected to cyclic loading with accompanied self-heating effect was described in terms of critical self-heating temperature concept. This allows for estimating the criticality of fatigue from the point of view of both mechanical and thermal failure.

A Mathematical Model of a Longwall Shearer Cutting System with Selected Faults

The paper describes a mathematical model of a longwall shearer cutting system using the JOY’s 4LS20 shearer as an example. The derived mathematical model consists of three submodels, i.e., a model of a 3-phase electric motor, a model of a gear train system and an algebraic model of a process of rock cutting by means of conical cutting tools which are installed on a drum called a cutter head. The model of the gear train system is a system of ordinary differential equations of the second order which include parametric models of stiffness of both gears and shafts. This approach allows modeling of different faults, e.g., tooth breaking, shaft cracking, etc. The algebraic model of the rock cutting process includes construction features of the cutter head, mechanical properties of the cut rock, and allows estimation the current cutting force acting on the cutting system. The last model, i.e., the model of the electric motor is used for calculation of (a) the input torque and the angular velocity of the gear train system, and (b) the corresponding 3-phase electric current flowing through the motor. These parameters allow to compare simulation results with measurement data acquired from longwall systems.

Application of the DiaSter System

The functions of the DiaSter system are realized by means of specialized user packages. These packages cooperate by means of the system software platform. Particular packages can be developed as specialized libraries of modeling, system variables processing and visualization modules or as stand-alone software modules. Individual packages or a specified set of packages can be used to implement particular tasks connected with process modeling, supervisory control, optimization and diagnostics. The functions of individual packages complete each other, giving the possibility to realize even more complex tasks.

Knowledge Discovery in Databases

Contemporary SCADA systems allow collecting huge amounts of data that originates from diverse data sources. There are at least two groups of such sources: