Mikko Vermasvuori

A process monitoring system based on the Kohonen self-organizing maps

Process monitoring and fault diagnosis have been studied widely in recent years, and the number of industrial applications with encouraging results has grown rapidly. In the case of complex processes a computer-aided monitoring enhances operators possibilities to run the process economically. In this paper, a fault diagnosis system will be described and some application results from the Outokumpu Harjavalta smelter will be discussed. The system monitors process states using neural networks (Kohonen self-organizing maps, SOMs) in conjunction with heuristic rules, which are also used to detect equipment malfunctions.

Industrial applications of the intelligent fault diagnosis system

Process monitoring and fault diagnosis have been widely studied in recent years, and a large number of industrial applications are reviewed. For further improvement of the reliability and safety of the process and the process equipment, the automatic early detection and localisation of faults is of high interest. This paper presents an intelligent process fault diagnosis system. The system is capable of detecting faults of the process and equipment. The process monitoring is performed using Kohonen self-organizing maps and the analysis of the equipment failures are integrated to the system. The structure of the integrated system is described and its performance is illustrated by case studies.

Operator Support System for the Larox Pressure Filter

Abstract Artificial intelligence methods such as expert systems, fuzzy systems, neural networks and combinations of these, have become invaluable tools in helping operators to monitor and control processes. These methods can also be used to run processes in a more economically effective way and, in the case of equipment malfunction, they can propose appropriate corrective measures. In this paper an operator support system for the Larox pressure filter is presented.

FTC based on data driven FDI for a dearomatisation process

In this paper, a fault tolerant control (FTC) system based on data driven fault detection (FDI) is presented. The behaviour of the system with proactive and reactive FTC strategies is studied in the presence of faults in an online product quality analyser with a simulated dearomatisation process operated under model predictive control (MPC). The performance of the system is validated onsite at the Neste Oil Oyj Naantali refinery. It is shown, that the inherent accommodation properties and model information in the studied MPC provide means to realise the proposed types of FTC strategies as confirmed both by simulation and the real process results. It is also shown that similar results are achieved within a simulated and the real process environments.

Support vector machines for detection of analyzer faults- a case study

Abstract The aim of the work presented in this paper is to assess the ability of support vector machines (SVM) for detecting measurement faults. Two different support vector machine approaches for detecting faults are tested and compared to neural networks. The first method is based on a SVM regression model together with an analysis of the residuals whereas the second method is based on a SVM classifier. The methods were applied to a rigorous first principles based dynamic simulator of a dearomatization process.

Operation Cycle Optimisation of the Larox Pressure Filter

Abstract Artificial intelligence methods such as expert systems, fuzzy systems, neural networks and combinations of these, have become invaluable tools in helping operators to monitor and control processes. These methods can also be used to run processes in a more economically effective way and, in the case of equipment malfunction, they can propose appropriate corrective measures. In this paper a system for operation cycle optimisation of the Larox pressure filter is presented and some test results are discussed.

An intelligent, integrated control system for a pressure filter

Artificial intelligence methods like expert systems and self-organizing maps have proved to be excellent tools for the control of mineral processes. This technology is currently being embedded directly into process equipment like flotation cells and dewatering filters. In this paper an intelligent, integrated control system for a pressure filter is described and the testing results presented and discussed.

A TOOLBOX FOR ON-LINE PROCESS MONITORING WITH SOME INDUSTRIAL APPLICATIONS

Abstract On-line process monitoring with fault detection can provide stability and efficiency for a wide range of processes. A toolbox for on-line monitoring using Kohonen self-organizing maps (SOM), in conjunction with heuristic rules is described in this paper. Four different industrial applications using the toolbox are presented and discussed at the end of the paper.