Browsing by Author "Vermasvuori, Mikko"
Now showing 1 - 12 of 12
- Results Per Page
- Sort Options
- DATA BASED FAULT DETECTION OF THE ONLINE ANALYSERS IN A DEAROMATISATION PROCESS
A4 Artikkeli konferenssijulkaisussa(2005) Vermasvuori, Mikko; Vatanski, Nikolai; Jämsä-Jounela, Sirkka-LiisaFault diagnosis methods based on process history data have been studied widely in recent years, and several successful industrial applications have been reported. In this paper a comparison of four monitoring methods, PCA, PLS, subspace identification and self-organising maps, for fault detection of the online analysers in a dearomatisation process is presented. The effectiveness of different statistical process monitoring methods in FDI of the online analysers is evaluated on the basis of a large number of simulation studies. Finally the results are presented and discussed. - Effect of viscosity on gas-liquid flow calculation in a dynamic process simulator
Kemian tekniikan korkeakoulu | Master's thesis(2014-05-06) Heikkilä, TomiGas-liquid two-phase flow occurs in safety valve calculations in the process industry. In order to size the safety valves reliably, the pressure drop calculations of the two-phase flow needs to be accurate. Two-phase flow is affected by many variables such as the viscosity. The aim of this thesis is to implement reliable and accurate calculation methods for viscosity and pressure drop for two-phase flows in a dynamic process simulator, ProsDS. Furthermore, the effect of viscosity on two-phase flow is studied. The literature part of this thesis consists of two main chapters. In the first chapter, the viscosity methods for gas and liquid phases are reviewed. In addition, the viscosity methods for petroleum fractions and crude oils are introduced. The second chapter focuses on the two-phase flow. Different variables related to two-phase calculations, flow patterns and pressure drop calculations methods are introduced. The effect of the viscosity on the two-phase flow is studied in the end of the second chapter. The applied part is also divided into two sections. In the first part, the most accurate and practical viscosity methods of FLOWBAT simulator were integrated into ProsDS. The methods were verified using experimental values presented in the literature. In the second part, several two-phase pressure drop methods were compared to the experimental values from the literature containing gas-liquid flows with various viscosities. Pressure drop methods of Lockhart-Martinelli, Müller-Steinhagen-Heck and Bandel gave the most accurate results and they were implemented into ProsDS. The methods were tested in a safety valve inlet piping case. The results of the simulated case differed significantly from each other. The inconsistency of the results indicates that it is difficult to predict two-phase pressure drops reliably. - FTC based on data driven FDI for a dearomatisation process
A4 Artikkeli konferenssijulkaisussa(2008) Vermasvuori, Mikko; Sourander, Mauri; Liikala, Teemu; Sauter, Dominique; Jämsä-Jounela, Sirkka-LiisaIn 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. - Intelligent Support System for a Pressure Filter
A4 Artikkeli konferenssijulkaisussa(2003) Jämsä-Jounela, Sirkka-Liisa; Kämpe, Jerri; Vermasvuori, Mikko; Koskela, KariThis paper presents the intelligent operating system for the Larox variable volume pressure filter and the online test results obtained with an industrial Larox filter at a Finnish process site. Preliminary analysis of the results indicates that the system works well. During testing, suitable operating parameters for faster filtration cycle were discovered and the production rate was increased. - Kohinan ja muiden häiriöiden poistaminen mittaussignaalista
Kemian ja materiaalitieteiden tiedekunta | Bachelor's thesis(2008) Boriouchkine, Alexandre - Methodology for utilising prior knowledge in constructing data-based process monitoring systems with an application to a dearomatisation process
Doctoral dissertation (monograph)(2008) Vermasvuori, MikkoGlobal competition is forcing the process industry to optimise the production processes. One key factor in optimisation is effective process state monitoring and fault detection. Another motivator to improve process monitoring systems are the substantial losses of revenue resulting from abnormal process conditions. It has been estimated that the petrochemical industry in the US alone loses 20 billion dollars per year because of unoptimal handling of abnormal process situations. Traditionally, the monitoring systems have been based on first principle models, constructed by specialists with process specific expertise. In contrast, the use of data-based modelling methods require less expertise and offers the possibilities to build and update the monitoring models in a short period of time, thus allowing more efficient development of monitoring systems. The aims of this thesis are to augment data-driven modelling with existing process knowledge, to combine different data-based modelling methods, and to utilise calculated variables in modelling in order to improve the accuracy of fault detection and identification (FDI) and to provide all necessary diagnostic information for fault tolerant control. The suggested improvements are included in a methodology for setting up FDI systems. The methodology has been tested by building FDI systems for detecting faults in two online quality analysers in a simulated and in a real industrial dearomatisation process at the Naantali oil refinery (Neste Oil Oyj). In developing an FDI system, background information about the user requirements for the monitoring system is first acquired. The information is then analysed and suitable modelling methods are selected according to the guidelines given in the methodology. Second, the process data are prepared for the modelling methods and augmented with appropriate calculated variables. Next, the input variable sets are determined with the introduced method and the models are constructed. After the estimation accuracy of the models is validated, the values of the fault detection parameters are determined. Finally, the fault detection performance of the system is tested. The system was evaluated during a period of one month at the Naantali refinery in 2007. The monitoring system was able to detect all the introduced analyser faults and to provide the information needed for a fault tolerant control system, thus validating the methodology. The effects of a number of suggested improvements in data-based modelling are analysed by means of a comparison study. - Kuparin liekkisulatusprosessin häiriöiden on-line monitorointi
Helsinki University of Technology | Master's thesis(2001) Vermasvuori, Mikko - OPC UA based multivariate analysis and data acquisition system for chemometric applications
Kemian tekniikan korkeakoulu | Master's thesis(2015-05-12) Sintonen, MarkusChemical industries utilize a variety of different types of online analyzers, for example, in areas like quality monitoring and process control applications. Large production plants typically use several analyzer devices from multiple manufacturers which are employed to measure different target quantities. As manufacturers have their own proprietary protocols for accessing analyzer information it is usually only the target property estimates that are transferred to the higher level automation systems. Other analyzer data, for example spectra, are generally not in a suitable format for further action on the higher level systems. This thesis outlines a solution to the analyzer data acquisition problem by utilizing OPC UA standard and OPC UA analyzer devices companion specification (ADI) to create a data acquisition system for analyzer information. The created system consists of an OPC UA server, which is used as a single access point for all analyzer related information. In addition, the analyzer data is collected and archived into a SQL database, which is accessible through the OPC UA server. The data acquisition system makes it convenient for the end users to access plant analyzer information using the standardized protocols. Furthermore, the OPC UA based data acquisition system can be used to integrate analyzer data with other types of process measurements. This thesis presents an example application where this type of data integration is utilized to increase the accuracy of the target quantity estimates of an analyzer. The same system also has a wide range of other potential applications, some of which are briefly examined in this work. The literature part of the thesis mainly focuses on different aspects of chemometrics; pre-processing and multivariate modelling of the analyzer spectra. These techniques are used in the thesis' experimental part to process data obtained from Neste Oil Oy’s Porvoo refinery. The literature part also briefly examines different protocols used for the transfer of analyzer data through the automation networks. The experimental part the thesis consists of three main parts: The first part is a case study where the refinery measurement data and the analyzer spectra are utilized to demonstrate how product quality estimates accuracies can be improved through data integration. In the second part, the analyzer data acquisition system is developed, including the provision of a separate OPC UA ADI wrapper server for ABB online analyzers. This wrapper was created in order to obtain the data from the production unit analyzers used in the case study. In the final part, a chemometric calculation platform is designed in order to implement the data processing sequence used to process the refinery data. This platform also utilizes the newly created data acquisition system through the OPC UA protocol. - Operator Support System for the Pressure Filter
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2005) Jämsä-Jounela, Sirkka-Liisa; Vermasvuori, Mikko; Kämpe, Jerri; Koskela, KariStrong competition in the process industries is forcing the optimization of process operation at each production level, including the operation of process equipment.Overall optimization of process equipment requires an efficient control strategy based on process models and a fault diagnosis system in order to prevent equipment malfunctions.In this paper an integrated operator support system for a pressure filter is presented.The system structure is modular and consists of classification, modelling, optimization, fault diagnostic, and remote support modules.Finally the test results from a pilot plant and an industrial environment are presented and discussed. - A process monitoring system based on the Kohonen self-organizing maps
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä(2003) Jämsä-Jounela, Sirkka-Liisa; Vermasvuori, Mikko; Endén, Petri; Haavisto, SasaProcess 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. - Support vector machines for detection of analyzer faults- a case study
A4 Artikkeli konferenssijulkaisussa(2006) Nikus, Mats; Vermasvuori, Mikko; Vatanski, Nikolai; Jämsä-Jounela, Sirkka-LiisaThe 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. - A toolbox for on-line process monitoring with some industrial applications
A4 Artikkeli konferenssijulkaisussa(2002) Jämsä-Jounela, Sirkka-Liisa; Vermasvuori, Mikko; Haavisto, Sasa; Endén, PetriOn-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.