University of Macau / Faculty of Science and Technology / Department of Computer and Information Science

Se estudian y caracterizan los sistemas expertos en su aplicación a la gestión de la empresa y particularmente a los problemas de toma de decisiones de inversión. La conexión entre sistemas expertos y bases de datos ofrece, en el ámbito de la empresa, un marco de actuación que incorpora a las técnicas de almacenamiento y control de grandes volúmenes de información, aquéllas que significan conocimiento heurístico, capacidad de razonamiento, aprendizaje y comunicación con el usuario. El objetivo es establecer un marco de acción, que consiga acercarse a un control efectivo y global de la información que se requiere en los procesos de toma de decisión. La optimización de la interacción entre sistema experto y base de datos, se concreta en compartir un mismo diseño lógico de la información, para obtener tanto el esquema conceptual de la bases de datos, como la base de conocimiento del sistema experto. / This Thesis studies and characterizes the application of Expert Systems in the management of companies, particularly in problems related to decision making. The connection between Expert Systems and Databases offer new possibilities in the study of Business Management. Expert Systems provide techniques for; the control of large volumes of information and heuristic knowledge, reasoning and learning capabilities and interactive user communication. The objective of knowledge and data base integration is to establish a framework for effective and global control of decision making processes. The interaction of Expert Systems and Databases could be improved by sharing one logical design for information in order to obtain a unique Conceptual Scheme of the Database and Knowledge Base of Expert Systems.

An expert system is useful when conventional programming techniques fall short of capturing human expert knowledge and making decisions using this information. In this study, we describe a framework for capturing expert knowledge under a decision tree form and this framework can be used for making decisions based on captured knowledge. The framework proposed in this study is generic and can be used to create domain specific expert systems for different problems. Features are created or processed by the nodes of decision tree and a final conclusion is reached for each feature. Framework supplies 3 types of nodes to construct a decision tree. First type is the decision node, which guides the search path with its answers. Second type is the operator node, which creates new features using the inputs. Last type of node is the end node, which corresponds to a conclusion about a feature. Once the nodes of the tree are developed, then user can interactively create the decision tree and run the supplied inference engine to collect the result on a specific problem. The framework proposed is experimented with two case studies / &quot / Airport Runway Detection in High Resolution Satellite Images&quot / and &quot / Urban Area Detection in High Resolution Satellite Images&quot / . In these studies linear features are used for structural decisions and Scale Invariant Feature Transform (SIFT) features are used for testing existence of man made structures.

This dissertation introduces a new problem in the delivery of healthcare, which could result in lower cost and a higher quality of medical care as compared to the current healthcare practice. In particular, a framework is developed for sedation and cardiopulmonary management for patients in the intensive care unit. A method is introduced to automatically detect pain and agitation in nonverbal patients, specifically in sedated patients in the intensive care unit, using their facial expressions. Furthermore, deterministic as well as probabilistic expert systems are developed to suggest the appropriate drug dose based on patient sedation level. This framework can be used to automatically control the level of sedation in the intensive care unit patients via a closed-loop control system. Specifically, video and other physiological variables of a patient can be constantly monitored by a computer and used as a feedback signal in a closed-loop control architecture. In addition, the expert system selects the appropriate drug dose based on the patient's sedation level. In clinical intensive care unit practice sedative/analgesic agents are titrated to achieve a specific level of sedation. The level of sedation is currently based on clinical scoring systems. In general, the goal of the clinician is to find the drug dose that maintains the patient at a sedation score corresponding to a moderately sedated state. This is typically done empirically, administering a drug dose that usually is in the effective range for most patients, observing the patient's response, and then adjusting the dose accordingly. However, the response of patients to any drug dose is a reflection of the pharmacokinetic and pharmacodynamic properties of the drug and the specific patient. In this research, we use pharmacokinetic and pharmacodynamic modeling to find an optimal drug dosing control policy to drive the patient to a desired sedation score.

Includes vita. / Title from PDF of title page. / Document formatted into pages; contains 222 pages. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: This dissertation presents a knowledge-guided expert system that is capable of applying routinesfor multispectral analysis, (un)supervised clustering, and basic image processing to automatically detect and segment brain tissue abnormalities, and then label glioblastoma-multiforme brain tumors in magnetic resonance volumes of the human brain. The magnetic resonance images used here consist of three feature images (T1-weighted, proton density, T2-weighted) and the system is designed to be independent of a particular scanning protocol. Separate, but contiguous 2D slices in the transaxial plane form a brain volume. This allows complete tumor volumes to be measured and if repeat scans are taken over time, the system may be used to monitor tumor response to past treatments and aid in the planning of future treatment. Furthermore, once processing begins, the system is completely unsupervised, thus avoiding the problems of human variability found in supervised segmentation efforts.Each slice is initially segmented by an unsupervised fuzzy c-means algorithm. The segmented image, along with its respective cluster centers, is then analyzed by a rule-based expert system which iteratively locates tissues of interest based on the hierarchy of cluster centers in feature space. Model-based recognition techniques analyze tissues of interest by searching for expected characteristics and comparing those found with previously defined qualitative models. Normal/abnormal classification is performed through a default reasoning method: if a significant model deviation is found, the slice is considered abnormal. Otherwise, the slice is considered normal. Tumor segmentation in abnormal slices begins with multispectral histogram analysis and thresholding to separate suspected tumor from the rest of the intra-cranial region. The tumor is then refined with a variant of seed growing, followed by spatial component analysis and a final thresholding step to remove non-tumor pixels.The knowledge used in this system was extracted from general principles of magnetic resonance imaging, the distributions of individual voxels and cluster centers in feature space, and anatomical information. Knowledge is used both for single slice processing and information propagation between slices. A standard rule-based expert system shell (CLIPS) was modified to include the multispectral analysis, clustering, and image processing tools.A total of sixty-three volume data sets from eight patients and seventeen volunteers (four with and thirteen without gadolinium enhancement) were acquired from a single magnetic resonance imaging system with slightly varying scanning protocols were available for processing. All volumes were processed for normal/abnormal classification. Tumor segmentation was performed on the abnormal slices and the results were compared with a radiologist-labeled ground truth' tumor volume and tumor segmentations created by applying supervised k-nearest neighbors, a partially supervised variant of the fuzzy c-means clustering algorithm, and a commercially available seed growing package. The results of the developed automatic system generally correspond well to ground truth, both on a per slice basis and more importantly in tracking total tumor volume during treatment over time. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.

Univ., Diss.--Wien, 2006.

Η διαλογή (Triage) των ασθενών, που προσέρχονται στο Τμήμα Επειγόντων Περιστατικών (ΤΕΠ), αποτελεί μια διαδικασία, η οποία εφαρμόζεται όταν ο αριθμός των προσερχόμενων πασχόντων είναι μεγαλύτερος από την δυνατότητα του προσωπικού και των διαθέσιμων πόρων του εκάστοτε φορέα. Στην Ελλάδα, η οικονομική ύφεση φαίνεται να έχει επηρεάσει την επισκεψιμότητα στα ΤΕΠ, καθώς υπάρχει ένα τεράστιο ποσοστό του πληθυσμού, που είναι ανασφάλιστοι και που για οποιοδήποτε πρόβλημα υγείας, απευθύνονται στα ΤΕΠ τριτοβάθμιων νοσοκομείων. Ωστόσο, αν και οι ανάγκες απαιτούν ένα πιο ολοκληρωμένο σύστημα ΤΕΠ, τα αποτελέσματα είναι δυσμενή. Η Επείγουσα Ιατρική, αν και είναι νομικά κατοχυρωμένη ειδικότητα σε >54 χώρες παγκοσμίως και σε 19/27 χώρες-μέλη της Ε.Ε., στην Ελλάδα ακόμη δεν είναι αναγνωρισμένη ως ειδικότητα ή εξειδίκευση. Επιπροσθέτως, η διαλογή των ασθενών, δεν είναι οργανωμένη και δεν ακολουθεί τις κατευθυντήριες οδηγίες.. Μόνη εξαίρεση αποτελεί το Γ.Ν. Θεσσαλονίκης ‘Παπαγεωργίου’, στο οποίο εφαρμόζεται διαλογή με 5-level σύστημα, κάνοντας χρήση του αλγορίθμου ESI (Emergency Severity Index). Σκοπός της εργασίας αυτής, αποτελεί αφ' ενός μεν η δημιουργία ενός ευφυούς συστήματος διαλογής και κατηγοριοποίησης των ασθενών, που προσέρχονται στο Τμήμα Επειγόντων Περιστατικών, αφ' ετέρου δε η σύγκριση διαφόρων μεθόδων δημιουργίας του πυρήνα του ευφυούς συστήματος. Στόχος του συστήματος είναι να αποτελέσει ένα χρήσιμο εργαλείο για την αποτελεσματικότερη και ταχύτερη διαλογή των ασθενών. Αρχικά, πραγματοποιήθηκε η συλλογή ενός σημαντικού αριθμού δεδομένων ασθενών, οι οποίοι προσήλθαν στα ΤΕΠ του ΠΓΝ Πατρών. Τα δεδομένα αυτά, τα οποία και συλλέχθηκαν ανώνυμα, περιλαμβάνουν δημογραφικά στοιχεία, το κύριο σύμπτωμα του ασθενή, την αξιολόγηση TRIAGE, τον τρόπο άφιξης στα ΤΕΠ καθώς και ένα σύνολο από χαρακτηριστικά γνωρίσματα για κάθε ξεχωριστό οργανικό σύστημα. Παράλληλα, πραγματοποιήθηκαν συνεντεύξεις με εμπειρογνώμονες (ιατρούς-νοσηλευτές). Η γνώση, η οποία πάρθηκε από τα δεδομένα, τις συνεντεύξεις και την βιβλιογραφία αποτέλεσαν την πηγή για την παραγωγή των κανόνων του συστήματος. Η κατηγοριοποίηση των ασθενών, η οποία και στηρίζεται στο σύστημα διαλογής ESI, γίνεται σε κλάσεις εξόδου. Ο αριθμός των κλάσεων εξόδου, είναι 5πλάσιος του αριθμού των ιατρικών ειδικοτήτων. Η αποτελεσματικότητα του συστήματος, αξιολογείται με βάση διεθνώς χρησιμοποιούμενες μετρικές. / The screening (Triage) of patients attending the Emergency Department (ED) is a process which applies when the number of the arriving patients is greater than the ability of the staff and of the resources of each institution. In Greece, the economic downturn seems to have affected the traffic in ED, as there is a huge percentage of the population, who are uninsured and who for any health problem, addressed to the tertiary hospital. However, although needs require a more integrated system of ED, the results are unfavourable. The Emergency Medicine, although legally patented specialty in > 54 countries around the world and in 19/27 countries-members of the EU, in Greece is still not recognized as a specialty or specialization. In addition, the ED-Triage, is not organized and does not follow the guidelines. The only exception is the General Hospital ‘Papageorgiou’ at Thessaloniki, which uses for ED-Triage a 5-level system, using the algorithm ESI (Emergency Severity Index). The purpose of this work is on the one hand, the creation of an intelligent system for sorting and categorization of patients who come to the Emergency Department, and a comparison of various methods of creating the core of intelligent system. The aim of the system is to be a useful tool for better and faster triage of patients. Initially, the collection was a considerable quantity of data by patients who came to the ED of the Universal Hospital of Patras. These data, which were collected anonymously, include demographics, the main symptom of the patient, the evaluation of TRIAGE, how the patient arrival in the ED and a set of features for each separate organic system. At the same time, made interviews with experts (doctors-nurses). Knowledge, which was taken by the data, interviews and literature became the source for the production of the rules of the system. The categorization of patients, which is based on the sorting system, ESI is to output classes. The number of output classes, is 5 times the number of medical specialties. The effectiveness of the system, evaluated by internationally-used metrics.

Στην εργασία αυτή παρουσιάζεται η χρήση τεχνολογίας Έμπειρων Συστημάτων για την πρόβλεψη της επιτυχίας ενός μαθητή Τ.Ε.Ε. στις εισαγωγικές πανελλαδικές εξετάσεις στα Α.Τ.Ε.Ι. και η απόδοσή της συγκρίνεται με αυτή της Ανάλυσης Λογιστικής Παλλινδρόμησης και των Νευρωνικών Δικτύων. Είναι σημαντικό για τους καθηγητές, αλλά και τη διοίκηση του σχολείου, να είναι σε θέση να εντοπίζουν τους μαθητές με υψηλή πιθανότητα αποτυχίας ή χαμηλής απόδοσης ώστε να τους βοηθήσουν κατάλληλα. Για το σκοπό της παρούσας εργασίας αναπτύσσεται Έμπειρο Σύστημα βασισμένο σε κανόνες, το οποίο υλοποιείται σε δυο εκδοχές: η πρώτη χρησιμοποιεί τους συντελεστές βεβαιότητας του MYCIN και η δεύτερη μια γενικευμένη εκδοχή της σχέσης των συντελεστών αβεβαιότητας του MYCIN με τη βοήθεια αριθμητικών βαρών για κάθε συντελεστή βεβαιότητας (PASS). Ο σχεδιασμός του έμπειρου συστήματος σε κάθε περίπτωση, η ανάλυση Λογιστικής Παλινδρόμησης και η ανάπτυξη Νευρωνικού Δικτύου βασίζονται στην ανάλυση δημογραφικών και εκπαιδευτικών δεδομένων των μαθητών, κυρίως όμως στην ανάλυση δεδομένων της απόδοσής τους κατά τις σπουδές τους (Φύλο, Ηλικία, Ειδικότητα, Βαθμός Α (ο Γενικός Βαθμός της Α’ Τάξης), Βαθμός Β (Γενικός Βαθμός της Β’ τάξης) και Βαθμός ΑΓ (ο Μέσος Όρος των βαθμών στα τρία εξεταζόμενα μαθήματα κατά το Α’ τετράμηνο σπουδών). Με δεδομένο το ότι η πρόβλεψη της επιτυχίας ή μη ενός μαθητή στις εισαγωγικές εξετάσεις εμπεριέχει ένα μεγάλο βαθμό αβεβαιότητας, η αβεβαιότητα αυτή έχει καθοριστικό ρόλο στη σχεδίαση του έμπειρου συστήματος σε κάθε εκδοχή του. Το Έμπειρο Σύστημα PASS, η Ανάλυση Λογιστικής Παλινδρόμησης και τα Νευρωνικά Δίκτυα έχουν περίπου την ίδια ακρίβεια στην πρόβλεψή τους ενώ το MYCIN μικρότερη. Το MYCIN εμφανίζει την υψηλότερη ευαισθησία. Το Έμπειρο Σύστημα PASS, η Ανάλυση Λογιστικής Παλινδρόμησης και τα Νευρωνικά Δίκτυα έχουν περίπου την ίδια ειδικότητα, με το PASS να έχει ελαφρώς υψηλότερη τιμή ενώ το MYCIN έχει την χαμηλότερη τιμή. / In this paper, the use of the technology of the Expert Systems is presented in order to predict how certain is that a student of a specific type of high school in Greece will pass the national exams for entering a higher education institute, and the results are compared with that of Logistic Regression Analysis and Neural Networks. Predictions are based on various types of student’s student (sex, subject of studies, general degree of class A, general degree of class B, mean degree of the three basic lessons of class C). The aim is to use the predictions to provide suitable support to the students during their studies towards the national exams. The expert system is a rule-based system that uses a type of certainty factors and is developed based on two versions. The first one uses the MYCIN certainty factors combination to produce the final prediction based on rules with the same conclusion. The second one (PASS) introduces a parameterized linear formula for combining the certainty factors of two rules with the same conclusion. The values of the parameters (weights) are determined via training, before the system is used. Experimental results show that the accuracy of the predictions of the expert system PASS is comparable to that of Logistic Regression Analysis and Neural Networks approach. The accuracy of the predictions of the expert system MYCIN is lower than the accuracy of the other methods. The sensitivity of the MYCIN results is the highest and the specificity is the lowest. The specificity of the PASS, Logistic Regression Analysis and Neural Networks results are similar with the one of the PASS Expert System to be higher.

Distributed intelligence systems are starting to gain dominance in the field of large-scale complex systems. These systems are characterized by nonlinear behavior patterns that are only predicted through simulation-based engineering. In addition, the autonomy, intelligence, and reconfiguration capabilities required by certain systems introduce obstacles adding another layer of complexity. However, there exists no standard process for the design of such systems. This research presents a design methodology focusing on distributed control architectures while concurrently considering the systems design process. The methodology has two major components. First, it introduces a hybrid design process, based on the infusion of the control architecture and conceptual system design processes. The second component is the development of control architectures metamodel, placing a distinction between control configuration and control methods. This enables a standard representation of a wide spectrum of control architectures frameworks.

Una de las actuaciones posibles para la gestión de los residuos sólidos urbanos es la valorización energética, es decir la incineración con recuperación de energía. Sin embargo es muy importante controlar adecuadamente el proceso de incineración para evitar en lo posible la liberación de sustancias contaminantes a la atmósfera que puedan ocasionar problemas de contaminación industrial.Conseguir que tanto el proceso de incineración como el tratamiento de los gases se realice en condiciones óptimas presupone tener un buen conocimiento de las dependencias entre las variables de proceso. Se precisan métodos adecuados de medida de las variables más importantes y tratar los valores medidos con modelos adecuados para transformarlos en magnitudes de mando. Un modelo clásico para el control parece poco prometedor en este caso debido a la complejidad de los procesos, la falta de descripción cuantitativa y la necesidad de hacer los cálculos en tiempo real. Esto sólo se puede conseguir con la ayuda de las modernas técnicas de proceso de datos y métodos informáticos, tales como el empleo de técnicas de simulación, modelos matemáticos, sistemas basados en el conocimiento e interfases inteligentes. En [Ono, 1989] se describe un sistema de control basado en la lógica difusa aplicado al campo de la incineración de residuos urbanos. En el centro de investigación FZK de Karslruhe se están desarrollando aplicaciones que combinan la lógica difusa con las redes neuronales [Jaeschke, Keller, 1994] para el control de la planta piloto de incineración de residuos TAMARA.En esta tesis se plantea la aplicación de un método de adquisición de conocimiento para el control de sistemas complejos inspirado en el comportamiento humano. Cuando nos encontramos ante una situación desconocida al principio no sabemos como actuar, salvo por la extrapolación de experiencias anteriores que puedan ser útiles. Aplicando procedimientos de prueba y error, refuerzo de hipótesis, etc., vamos adquiriendo y refinando el conocimiento, y elaborando un modelo mental. Podemos diseñar un método análogo, que pueda ser implementado en un sistema informático, mediante el empleo de técnicas de Inteligencia Artificial.Así, en un proceso complejo muchas veces disponemos de un conjunto de datos del proceso que a priori no nos dan información suficientemente estructurada para que nos sea útil. Para la adquisición de conocimiento pasamos por una serie de etapas:- Hacemos una primera selección de cuales son las variables que nos interesa conocer.- Estado del sistema. En primer lugar podemos empezar por aplicar técnicas de clasificación (aprendizaje no supervisado) para agrupar los datos y obtener una representación del estado de la planta. Es posible establecer una clasificación, pero normalmente casi todos los datos están en una sola clase, que corresponde a la operación normal. Hecho esto y para refinar el conocimiento utilizamos métodos estadísticos clásicos para buscar correlaciones entre variables (análisis de componentes principales) y así poder simplificar y reducir la lista de variables.- Análisis de las señales. Para analizar y clasificar las señales (por ejemplo la temperatura del horno) es posible utilizar métodos capaces de describir mejor el comportamiento no lineal del sistema, como las redes neuronales. Otro paso más consiste en establecer relaciones causales entre las variables. Para ello nos sirven de ayuda los modelos analíticos- Como resultado final del proceso se pasa al diseño del sistema basado en el conocimiento.El objetivo principal es aplicar el método al caso concreto del control de una planta de tratamiento de residuos sólidos urbanos por valorización energética.En primer lugar, en el capítulo 2 Los residuos sólidos urbanos, se trata el problema global de la gestión de los residuos, dando una visión general de las diferentes alternativas existentes, y de la situación nacional e internacional en la actualidad. Se analiza con mayor detalle la problemática de la incineración de los residuos, poniendo especial interés en aquellas características de los residuos que tienen mayor importancia de cara al proceso de combustión.En el capítulo 3, Descripción del proceso, se hace una descripción general del proceso de incineración y de los distintos elementos de una planta incineradora: desde la recepción y almacenamiento de los residuos, pasando por los distintos tipos de hornos y las exigencias de los códigos de buena práctica de combustión, el sistema de aire de combustión y el sistema de humos. Se presentan también los distintos sistemas de depuración de los gases de combustión, y finalmente el sistema de evacuación de cenizas y escorias.El capítulo 4, La planta de tratamiento de residuos sólidos urbanos de Girona, describe los principales sistemas de la planta incineradora de Girona: la alimentación de residuos, el tipo de horno, el sistema de recuperación de energía, y el sistema de depuración de los gases de combustión Se describe también el sistema de control, la operación, los datos de funcionamiento de la planta, la instrumentación y las variables que son de interés para el control del proceso de combustión.En el capítulo 5, Técnicas utilizadas, se proporciona una visión global de los sistemas basados en el conocimiento y de los sistemas expertos. Se explican las diferentes técnicas utilizadas: redes neuronales, sistemas de clasificación, modelos cualitativos, y sistemas expertos, ilustradas con algunos ejemplos de aplicación.Con respecto a los sistemas basados en el conocimiento se analizan en primer lugar las condiciones para su aplicabilidad, y las formas de representación del conocimiento. A continuación se describen las distintas formas de razonamiento: redes neuronales, sistemas expertos y lógica difusa, y se realiza una comparación entre ellas. Se presenta una aplicación de las redes neuronales al análisis de series temporales de temperatura.Se trata también la problemática del análisis de los datos de operación mediante técnicas estadísticas y el empleo de técnicas de clasificación. Otro apartado está dedicado a los distintos tipos de modelos, incluyendo una discusión de los modelos cualitativos.Se describe el sistema de diseño asistido por ordenador para el diseño de sistemas de supervisión CASSD que se utiliza en esta tesis, y las herramientas de análisis para obtener información cualitativa del comportamiento del proceso: Abstractores y ALCMEN. Se incluye un ejemplo de aplicación de estas técnicas para hallar las relaciones entre la temperatura y las acciones del operador. Finalmente se analizan las principales características de los sistemas expertos en general, y del sistema experto CEES 2.0 que también forma parte del sistema CASSD que se ha utilizado.El capítulo 6, Resultados, muestra los resultados obtenidos mediante la aplicación de las diferentes técnicas, redes neuronales, clasificación, el desarrollo de la modelización del proceso de combustión, y la generación de reglas. Dentro del apartado de análisis de datos se emplea una red neuronal para la clasificación de una señal de temperatura. También se describe la utilización del método LINNEO+ para la clasificación de los estados de operación de la planta.En el apartado dedicado a la modelización se desarrolla un modelo de combustión que sirve de base para analizar el comportamiento del horno en régimen estacionario y dinámico. Se define un parámetro, la superficie de llama, relacionado con la extensión del fuego en la parrilla. Mediante un modelo linealizado se analiza la respuesta dinámica del proceso de incineración.Luego se pasa a la definición de relaciones cualitativas entre las variables que se utilizan en la elaboración de un modelo cualitativo. A continuación se desarrolla un nuevo modelo cualitativo, tomando como base el modelo dinámico analítico.Finalmente se aborda el desarrollo de la base de conocimiento del sistema experto, mediante la generación de reglasEn el capítulo 7, Sistema de control de una planta incineradora, se analizan los objetivos de un sistema de control de una planta incineradora, su diseño e implementación. Se describen los objetivos básicos del sistema de control de la combustión, su configuración y la implementación en Matlab/Simulink utilizando las distintas herramientas que se han desarrollado en el capítulo anterior.Por último para mostrar como pueden aplicarse los distintos métodos desarrollados en esta tesis se construye un sistema experto para mantener constante la temperatura del horno actuando sobre la alimentación de residuos.Finalmente en el capítulo Conclusiones, se presentan las conclusiones y resultados de esta tesis. / One of the possible alternatives for the management of the municipal solid waste is the energy recovery in waste-to- energy facilities, i.e. the incineration with energy recovery. However, it is very important to control the incineration process properly in order to avoid, as far as possible, the liberation of pollutants to the atmosphere that could occasion problems of industrial contamination. To achieve that, both the incineration process and the treatment of flue gases are carried out in good conditions it presupposes to have a good knowledge of the dependences between process variables. It is necessary to have adequate measuring methods of the most important variables and to treat the measured values with appropriate models in order to transform them in control magnitudes. A classical control model looks not very promising in this case due to the complexity of the processes, the lack of quantitative description and the necessity of performing real-time calculations. This can only be achieved with the help of the modern techniques of data processing and informatics methods, like the use of simulation techniques, mathematical models, knowledge based systems and intelligent interfaces. A control system based on fuzzy logic applied to the field of the incineration of municipal solid waste is described in [ Ono, 1989]. In the Karslruhe center of investigation FZK applications that combine fuzzy logic with neural networks [Jaeschke, Keller, 1994] are being developed for the control of the TAMARA pilot plant for waste incineration.In this thesis it is outlined the application of a method of knowledge acquisition for the control of complex systems inspired by the human behaviour. When we are placed in face of an unknown situation, at the beginning we don't know how to act, except for the extrapolation of previous experiences that could be useful. Applying procedures of trial and error, reinforcement of hypothesis, etc, one goes acquiring and refining the knowledge, and elaborating a mental model. We can design a similar method, which could be implemented in an informatics system, by means of the use of Artificial Intelligence techniques.So, in a complex process often we have a group of process data that a priori don't give us sufficiently structured information to be useful. For the knowledge acquisition we went by a series of steps:- We make a first selection of which are the variables that we are interested to know.- State of the system. In first place we could begin applying classification techniques (unsupervised learning) in order to group the data and obtain a representation of the state of the plant. It is possible to establish a classification, but normally almost all the data are in a single class, that corresponds to the normal operation. Done this and in order to refine the knowledge we use classical statistical methods in order to look for correlations between variables (principal components analysis) to simplify and reduce the list of variables.- Analysis of the signals. In order to analyse and classify the signals (for example the temperature of the furnace) it is possible to use methods capable to better describe the non-linear behaviour of the system, like the neural networks. Another step consists in to establish causal relationships between the variables. For this purpose the analytical models are helpful.- As final result of the process go over the design of the knowledge based system.The main objective is to apply the method to the concrete case of the control of a plant of treatment of municipal solid waste by waste-to- energy process.First, chapter 2 The municipal solid waste, treats the global problem of waste management, giving an overview of the several existent alternatives, and of the national and international situation at the present time. The problems of the waste incineration are analysed with more detail, putting special interest in those waste characteristics that have more importance for the combustion process.In the chapter 3, Description of the process, is made a general description of the incineration process and of the different elements of a incineration plant: from the reception and storage of the waste, going by the different types of furnaces and the demands of the codes of good combustion practice, the combustion air system and the exhaust system. The different systems for cleaning the combustion gases, and the system of evacuation of ash residues are presented.The chapter 4, The municipal solid waste treatment plant of Girona, describes the main systems of the Girona incineration plant: the feeding of waste, the type of furnace, the energy recovery system, and the flue gas cleaning system. Are also described in this chapter, the control system, the operation, the data of operation of the plant, the instrumentation and the variables that are of interest for the control of the combustion process.In the chapter 5, Used techniques, is provided a global vision of the knowledge-based systems and of the expert systems. The diverse techniques used are explained: neural networks, systems of classification, qualitative models, and expert systems, illustrated with some examples of application.With regard to the knowledge-based systems, in first place are analysed the conditions for their suitability, and the forms of representation of the knowledge. Next the different forms of reasoning are described: neural networks, expert systems and fuzzy logic, and a comparison between them it is carried out. An application of the neural networks to the analysis of time series of temperature is presented.It is also treated the problem of the analysis of the operation data by means of statistical techniques and the use of techniques of classification. Another paragraph is dedicated to the different types of models, including a discussion of the qualitative models.The Computer Aided Supervisory System Design CASSD that is used in this thesis is described, and the analysis tools employed to obtain qualitative information from the behaviour of the process: ors and ALCMEN. An example of application of these techniques is included in order to find the relationships between the temperature and the actions of the operator. Finally are analysed the main characteristics of expert systems in general, and of the system expert CEES 2.0 that also are part of the CASSD system that has been used.The chapter 6, Results, shows the results obtained by means of the application of the several techniques, neural networks, classification, the development of the model of the combustion process, and the generation of rules. Inside the paragraph of analysis of data a neural network is used for the classification of a temperature signal. The use of the LINNEO+ method is also described for the classification of the states of operation of the plant.In the paragraph dedicated to the modelling a model of combustion is developed that is used as base in order to analyse the behaviour of the furnace in stationary and dynamic conditions. It is defined a parameter, the surface of flame, related with the extension of the fire in the grate. By means of a liberalized model the dynamic answer of the incineration process is analysed.Then we go over to the definition of qualitative relationships between the variables that are used in the elaboration of a qualitative model. Next a new qualitative model is developed, taking as base the analytic dynamic model.Finally the development of the knowledge base of the expert system is approached, by means of the generation of rules.In the chapter 7, Control system of an incineration plant, the objectives of a control system of an incineration plant are analysed, their design and implementation. Are described the basic objectives of the combustion control system, their configuration and the implementation in MATLAB/ SIMULINK using the different tools that have been developed in the previous chapter.Lastly in order to show how the different methods developed in this thesis could be applied it is built an expert system to maintain constant the temperature of the furnace acting on the waste feeding.Finally in the chapter Conclusions, the conclusions and results of this thesis are presented.