Ágnes Werner-Stark

DISCRETE EVENT MODEL STRUCTURE IDENTIFICATION USING PROCESS MINING

A novel structure identification procedure for discrete event systems described by Petri nets are proposed in this paper for model-based diagnostic purposes that utilize the notions and tools of process mining. The identification of the structurally different discrete event system models describing a system in its normal and/or faulty modes was used for model-based isolation of the considered faulty modes. From the available process mining techniques that allow for the automatic construction of process models in Petri net form based on event logs, the genetic algorithmbased structure identification procedure has been found to be most capable of identifying the characteristic structural elements of the faulty models. The proposed procedures are illustrated on a simple example of an operated parking gate automaton with two faulty modes.

Visualization of topology representing networks

As data analysis tasks often have to face the analysis of huge and complex data sets there is a need for new algorithms that combine vector quantization and mapping methods to visualize the hidden data structure in a low-dimensional vector space. In this paper a new class of algorithms is defined. Topology representing networks are applied to quantify and disclose the data structure and different nonlinear mapping algorithms for the low-dimensional visualization are applied for the mapping of the quantized data. To evaluate the main properties of the resulted topology representing network based mapping methods a detailed analysis based on the wine benchmark example is given.

A Database-oriented Workflow Scheduler with Historical Data and Resource Substitution Possibilities

This paper presents the database of a novel workflow scheduler that is able to handle resource substitution and takes into account historical data. The generated schedule can be optimized either in time or cost. The scheduler enables a resource substitution in case of an immediate event or when costor time-efficiency-related reasons necessitates it. The underlying database is able to handle complex workflows, represents the fleet of various resources and supports data mining from the data of the logged execution of the schedule in order to further improving the schedule. The database and the scheduler is a part of a complex project which schedules workflows described in XPDL by an agent system taking into account the real-time events and historical data served by process mining. Our scheduler system is intended to be applied both in business and industrial

Topology representing networks for the visualization of manifolds

In practical data mining tasks, high-dimensional data has to be analyzed. In most of the cases it is very informative to map and visualize the hidden structure of a complex data set in a low-dimensional space. In this paper a new class of mapping algorithms is defined. These algorithms combine topology representing networks and different nonlinear mapping algorithms. While the former methods aim to quantify the data and disclose the real structure of the objects, the nonlinear mapping algorithms are able to visualize the quantized data in the low-dimensional vector space. In this paper, techniques based on these methods are gathered and the results of a detailed analysis performed on them are shown. The primary aim of this analysis is to examine the preservation of distances and neighborhood relations of the objects. Preservation of neighborhood relations was analyzed both in local and global environments. To evaluate the main properties of the examined methods we show the outcome of the analysis based both on synthetic and real benchmark examples.

Immediate Event-Aware Model and Algorithm of a General Scheduler

A stochastic scheduling problem is investigated in this work that considers workpieces to be manufactured according to individual recipes containing manufacturing steps performed by workstations as resources. Unexpected stochastic breakdown of a workstation or the faulty termination of a recipe, when a manufacturing failure renders the workpiece out of specifications, forms the set of immediate events. A model and an algorithm are proposed as the basis of a scheduler, which takes into account the possible immediate events, estimates their probability and suggests resource allocations which provide the best overall work-flow even when an immediate event happens. This model includes the possibility of handling alternative resources that can substitute each other in case of an immediate event, like sudden technical failure of a resource. Immediate events are not exactly predictable; however, based on previous experiences, their probabilities can be estimated. Our model uses the properties of the resources (including how they can substitute other types of resources) and the required sequence of them during the workflow (i.e. the recipes). The proposed scheduling algorithm constructs a solution workflow that reacts in the best way (in average) even for an unexpected event. The proposed model and scheduling algorithm is illustrated on two industrial case studies.

Knowledge-based diagnosis of process systems using procedure HAZID information

Earlier investigations show that the results of hazard identification (HAZID) and analysis (e.g. HAZOP or FMEA) can effectively be used for knowledge-based diagnosis of complex process systems in their steady-state operation. In order to extend this approach for transient operating conditions controlled by operating procedures, the notion of nominal input-output event sequences of qualitative signals has been introduced, and the deviations used in the procedure HAZID analysis have been defined therefrom. The diagnosis can then be performed algorithmically by matching the deviation sequences of the observed input-output event sequences and the nominal ones generated by qualitative dynamic models. The concepts and methods are illustrated using a simple case study consisting of a simple tank, controlled by an operating procedure.

An Industrial Application Using Process Mining to Reduce the Number of Faulty Products

Process mining is a field of research that provides mining of more and more useful hidden information to the industry. The core of effective information retrieval lies in the application of process mining tools that best fits the task and the data. The current problem is that there is no universal solution available to track the formation of faulty products in time and space to make it possible to be reduced. To solve this problem, methods have been developed that can be used to analyze a production process from multiple perspectives. The methods were also implemented in software and tested on real production data. The methods created are based on time and space distribution and grouping of faulty products. The methods were applied to the processing and measurement data of an automated coil production and assembly line. The data is originally stored in different files, so before they were used, they had to be transformed and sorted into database. Using the software which use the methods, a comprehensive view of the production process can be obtained, and conclusions can be drawn from the generated statements about the state of the production tools and the possible source of the errors. The results make it possible to design more efficient maintenance, reduce outage time, and increase production time, thus reducing the number of faulty products.

Modeling of an agent system to support the management of cooperating and rival resources for business workflows

Modeling and analysis of business workflows may be strategic on behalf of the optimal execution. This paper proposes an innovative model-based approach, which can be used to resource scheduling of business workflows. To this we defined such functions that help the operation of processes, resource scheduling can be described formally during the modeling. The system uses all the information during the scheduling, which may be recorded in a log file in connection with the process execution. We can extract useful information concerning allocation of resources by analysis of the historical data, which are used to assign the resources to the implemented tasks. In the system the cooperation and contention of the resources as agents will play important role. The scheduling can be tested in an agent simulation environment. By the aid of this approach we can give decision proposal to the operator in real time to promote more optimal realization of the workflow.

A Structured Model-Based Diagnosis Method for Discrete Dynamic Processes Using Event Sequences

A novel model-based fault detection and diagnosis method is proposed that is based on following event sequences measured in a discrete dynamic process. The model of the nominal and faulty operation modes is given in the form of event sequences, that are decomposed according to the components and sub-components present in the process system. The faulty event sequences are defined using extended procedure HAZID tables. A diagnostic algorithm is also presented that uses a component-wise decomposed form of the event sequences. The operation of the algorithm is illustrated on a simple example of a process system consisting of three similar tanks.