Results 1  10
of
11
A Support Vector Approach to the AcoustictoArticulatory Mapping
, 2005
"... We report work on mapping the acoustic speech signal, parametrized using Mel Frequency Cepstral Analysis, onto electromagnetic articulography trajectories from the MOCHA database. We employ the machine learning technique of Support Vector Regression, contrasting previous works that applied Neural Ne ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
(Show Context)
We report work on mapping the acoustic speech signal, parametrized using Mel Frequency Cepstral Analysis, onto electromagnetic articulography trajectories from the MOCHA database. We employ the machine learning technique of Support Vector Regression, contrasting previous works that applied Neural Networks to the same task. Our results are comparable to those older attempts, even though, due to training time considerations, we use a much smaller training set, derived by means of clustering the acoustic data.
Towards New Languages for Systems Modelling
 Proceedings of the 42’nd Scandinavian Simulation Conference SIMS’02, September 26–27, 2002
"... This paper discusses what the future modeling environments could look like. To tackle with ever increasing complexity of process models, higher level of abstraction needs to be exploited. It is noticed that the most natural way to connect lowlevel models to highlevel tools is simulation. Based on ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
This paper discusses what the future modeling environments could look like. To tackle with ever increasing complexity of process models, higher level of abstraction needs to be exploited. It is noticed that the most natural way to connect lowlevel models to highlevel tools is simulation. Based on such semantic grounding, new description formalisms can perhaps be implemented. 1. NEW CHALLENGES Because of the fieldbuses, and because of the modern sensor technology, etc., the availability of the industrial processes has been enhanced considerably. There is an explosion of structureless data facing us. The problem is that there do not exist enough domain area experts that could analyze the data and rewrite the models for the processes appropriately. Automatic modeling systems would be invaluable – systems that could not only adapt the model parameters within a predetermined structural framework, but also determine the structures themselves without too much human intervention. The modeling problems are attacked by utilizing different kinds of description formalisms. One major approach is to define more and more general formalisms (like Java language) for system description: In such environments, anything can be expressed, but this means that large numbers of expressions are needed
Defect Localization on a PCB with Functional Testing
, 2002
"... Abstract: This paper describes how Linguistic Equations, an intelligent method derived from Fuzzy Algorithms, have been used in a decisionhelping tool adapted to the specific needs of electronics manufacturing. In our case the company involved in the project, PKC Group, is mainly producing control ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Abstract: This paper describes how Linguistic Equations, an intelligent method derived from Fuzzy Algorithms, have been used in a decisionhelping tool adapted to the specific needs of electronics manufacturing. In our case the company involved in the project, PKC Group, is mainly producing control cards for the telecommunication and automotive industry. In their business, nearly 70 percent of the cost of a product is material cost. Detecting defects and repairing the Printed Circuit Boards is therefore a necessity. With an ever increasing complexity of the products, defects are very likely to occur, no matter how much attention is put into their prevention. The work focused therefore on defect detection during the final testing of the product. The approach is based on experience using intelligent methods such as Fuzzy Logic or Linguistic Equations in fault diagnosis. An intelligent system based on expert knowledge was developed for analyzing test data. This analysis emphasizes localization of the defective components more than possible causes of those defects. Expert knowledge was essential for the development of the system as the number of defects is too low for a databased approach. According to the first results, the system is successful for new products, even in the rampup stage. On the other hand, the underlying methodology provides techniques for tuning the tool parameters when amount of testing data increases. Diagnosis
Process Performance Optimization Using Iterative Regression Tuning”Helsinki
, 2004
"... Abstract: A novel methodology, called Iterative Regression Tuning, for simultaneous tuning of multiple controllers is implemented in this report. Results from the first industrial scale application of the method are presented. A dynamical simulator representing a realistic power plant process is app ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Abstract: A novel methodology, called Iterative Regression Tuning, for simultaneous tuning of multiple controllers is implemented in this report. Results from the first industrial scale application of the method are presented. A dynamical simulator representing a realistic power plant process is applied as the test case. The report presents a comprehensible overview of the proposed tuning technique, the related algorithms and the application possibilities of the method.
KNOWLEDGEBASED DECISION SUPPORT SYSTEMS FOR PRODUCTION OPTIMIZATION AND QUALITY IMPROVEMENT IN THE ELECTRONICS INDUSTRY
, 2006
"... Academic dissertation to be presented, with the assent of ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Academic dissertation to be presented, with the assent of
1 LIST OF SYMBOLS
"... a: Zero mean white noise signal C(·): Controller transfer function e, E: Scalar error signal and a k×m matrix containing error signal values f(·): Arbitrary function F: Linear mapping matrix of dimension n×m G(·): Transfer function (for a process, closed loop system etc.) i,j: Indices for vector and ..."
Abstract
 Add to MetaCart
a: Zero mean white noise signal C(·): Controller transfer function e, E: Scalar error signal and a k×m matrix containing error signal values f(·): Arbitrary function F: Linear mapping matrix of dimension n×m G(·): Transfer function (for a process, closed loop system etc.) i,j: Indices for vector and matrix elements J(·): Cost function k: Number of data samples, i.e., local iteration steps K: Number of global iteration steps Kc: Critical gain of the controller KOL: Open loop gain of the process KP: Proportional gain of the PID controller L: Time lag, delay L(·): Filter transfer function m: Number of quality measures; dimension of output space M: Number of latent basis vectors in output oriented subspace n: Number of the parameters; dimension of input space N: Number of latent basis vectors in input oriented subspace q, Q: Quality measure vector and matrix, dimensions m×1 and k×m, respectively; shift operator r: Reference signal; setpoint R n: ndimensional linear space s: Laplace variable t: Continuous or discrete time index Tc: Period of the critical oscillation TI: Integration time TD: Derivation time TR: Rise time TS: Settling time
On Emergent Models and Optimization of Parameters
"... There has been considerable interest on the “New Science ” and its promises, but very few practical evidence has been presented to motivate the complex systems hype. However, it seems that the new approaches can give new insights. This paper shows how the new conceptual tools can help also in practi ..."
Abstract
 Add to MetaCart
(Show Context)
There has been considerable interest on the “New Science ” and its promises, but very few practical evidence has been presented to motivate the complex systems hype. However, it seems that the new approaches can give new insights. This paper shows how the new conceptual tools can help also in practical control engineering tasks as in optimization of parameters. Discussions here are closely related to another paper [4]. 1. COMPLEX SYSTEMS AND EMERGENCE Assume that a set of experts has been developing a sophisticated partial differential equation model for, say, some chemical reactor. Typically, such a model is based on partial differential equations – making this kind of model useful for simulation or control design purposes, it has to be approximated. The resulting lumped parameter model will typically have dozens of free parameters that cannot be exactly determined using physical knowledge, and some kind of parameter tuning has to be carried out. Validation of such a model against actual measurements, simplifying it, and detecting the actual relevance of the individual parameters can be an extremely difficult task, and tools that could help in this task would be invaluable. As presented in [4], theory of complex systems may give new tools when searching for new tools for
Application of Elastic Intuitions to Process Engineering
"... In this paper the intuitions of the elastic systems and neocybernetics are applied to large scale industrial systems. The process performance enhancement can be seen as technical evolution of the system. The objectives of technical evolution are somewhat different from those of natural neocybernetic ..."
Abstract
 Add to MetaCart
(Show Context)
In this paper the intuitions of the elastic systems and neocybernetics are applied to large scale industrial systems. The process performance enhancement can be seen as technical evolution of the system. The objectives of technical evolution are somewhat different from those of natural neocybernetic systems. The performance of the system can be characterized by means of quality measures and the parameters of the system can be tuned along the axes of freedoms in the parameter space towards values that result in better process performance. Results from a simulated case study on a continuous pulp digester model are presented and discussed. 1