Fault diagnosis and condition monitoring can be based on analytical process models, explicit knowledge or direct process measurements. When the structure of the process is unknown, the data-based approach based on the...
详细信息
Fault diagnosis and condition monitoring can be based on analytical process models, explicit knowledge or direct process measurements. When the structure of the process is unknown, the data-based approach based on the measurements is the most practical one. This is the case also with X-ray fluorescence analyzers. Appropriate analyzer calibration is a key factor in obtaining the best performance from the analysis system. As the mineralogy of the processed material is slowly changing the calibration must be maintained over time. The possible indicators for the calibration validity are studied in this paper.
The X-ray fluorescence analyzers are widely used for on-line analysis of minerals. Even though the X-ray spectral intensities are proportional to the atom contents in the material, differing process conditions, slurry...
详细信息
The X-ray fluorescence analyzers are widely used for on-line analysis of minerals. Even though the X-ray spectral intensities are proportional to the atom contents in the material, differing process conditions, slurry densities, and particle size distributions affect the measurement results, and analyzers need to be calibrated against laboratory assays. The models mapping the spectral channel intensities to concentrations of basic elements are normally based on the standard least-squares regression analysis. However, there exist various problems when the basic regression models are used; the reasons for these problems are both theoretical (due to colinearity) and practical (time-varying nature of the process). To attack the problems, more sophisticated model structures can be introduced. First, the clustered nature of the long-term observations can be taken into account when a kind of model library is utilized; the integrity of the clustered set of models can be maintained utilizing self-organization. Second, the colinearity problem is avoided when latent variables are introduced and the prediction model is constructed using the measurements only after they are projected onto this hidden internal basis. Third, the special statistical structure of the measurements can be taken into account when the latent variables are independent components extracted from the data. From the mathematical point of view, the above ideas can be implemented in the framework of sparse coded linear structures.
Remote, telecommunications based support for process equipment operation and maintenance can offer substantial benefits for the end-user in terms of improved up¬time and better quality of operation. Equipment ven...
详细信息
Remote, telecommunications based support for process equipment operation and maintenance can offer substantial benefits for the end-user in terms of improved up¬time and better quality of operation. Equipment vendors can utilize this kind of facility to improve their after-sales services for the end-user. A remote operations support system has been designed and realized. The prototype system has been applied to and experimented with an on-line X-ray fluorescence analyzer manufactured by outokumpu Mintec oy. The system comprises software modules in the analyzer operating station end and in the remote expert station end. The communications between both ends uses TCp/Ipprotocol and the communications media can be Internet, or wired and/or wireless or satellite-based telephony network.
We have developed an image retrieval system named picSoM which uses Tree Structured Self-organizing Maps (TS-SoMs) as the method for retrieving images similar to a given set of reference images. A novel technique intr...
详细信息
We have developed an adaptive handwriting recognizer for isolated Latin characters in which the adaptive behavior is based on the dynamically expanding context (DEC) algorithm. In our current system, the outputs of a ...
In the literature there exist several soft computing methods for building predictive models: neural network models, fuzzy models and probabilistic approaches. In this paper we are interested in the question which one ...
详细信息
This paper describes the basic operations of a navigating convoy of vehicles which are automatic but are led by a manually driven master vehicle. The convoy navigation system simulated and tested is based on distance ...
详细信息
This paper describes the basic operations of a navigating convoy of vehicles which are automatic but are led by a manually driven master vehicle. The convoy navigation system simulated and tested is based on distance measurement between the vehicles. The navigation is aided by dead reckoning of all the vehicles.
暂无评论