No description available.

L'apprentissage de modèles temporels constitue l'une des grandes problématiques de l'Exploration de Données (Data Mining). Dans cette thèse, nous avons développé un nouveau modèle temporel appelé TITA Rules (Règle associative temporelle basé sur des arbres d'intervalles). Ce modèle permet de décrire des phénomènes ayant un certain degré d'incertitude et/ou d'imprécision. Ce modèle permet entre autres d'exprimer la synchronicité entre évènements, les contraintes temporelles disjonctives et la négation temporelle. De par leur nature, les TITA Rules peuvent êtes utilisées pour effectuer des prédictions avec une grande précision temporel. Nous avons aussi développé un algorithme capable de découvrir et d'extraire de manière efficace des TITA Rules dans de grandes bases de données temporelles. Le cœur de l'algorithme est basé sur des techniques de minimisation d'entropie, de filtrage par Apriori et par des analyses de co-dépendance. Note modèle temporelle et notre algorithme ont été appliqués et évalués sur plusieurs jeux de données issues de phénomènes réels et de phénomènes simulés. La seconde partie de cette thèse à consisté à étudier l'utilisation de notre modèle temporel sur la problématique de la Planification Automatique. Ces travaux ont mené au développement d'un algorithme de planification automatique. L'algorithme prend en entrée un ensemble de TITA Rules décrivant le fonctionnement d'un système quelconque, une description de l'état initial du système, et un but à atteindre. En retour, l'algorithme calcule un plan décrivant la meilleure façon d'atteindre le but donné. Par la nature même des TITA Rules, cet algorithme est capable de gérer l'incertain (probabilités), l'imprécision temporelle, les contraintes temporelles disjonctives, ainsi que les événements exogènes prédictibles mais imprécis. / The learning of temporal patterns is a major challenge of Data mining. We introduce a temporal pattern model called Temporal Interval Tree Association Rules (Tita rules or Titar). This pattern model can be used to express both uncertainty and temporal inaccuracy of temporal events. Among other things, Tita rules can express the usual time point operators, synchronicity, order, and chaining,disjunctive time constraints, as well as temporal negation. Tita rules are designed to allow predictions with optimum temporal precision. Using this representation, we present the Titar learner algorithm that can be used to extract Tita rules from large datasets expressed as Symbolic Time Sequences. This algorithm based on entropy minimization, apriori pruning and statistical dependence analysis. We evaluate our technique on simulated and real world datasets. The problem of temporal planning with Tita rules is studied. We use Tita rules as world description models for a Planning and Scheduling task. We present an efficient temporal planning algorithm able to deal with uncertainty, temporal inaccuracy, discontinuous (or disjunctive) time constraints and predictable but imprecisely time located exogenous events. We evaluate our technique by joining a learning algorithm and our planning algorithm into a simple reactive cognitive architecture that we apply to control a robot in a virtual world.

Cette thèse propose une méthodologie de pilotage d'organisations complexes, ens'intéressant à de nouvelles méthodes de planification collaborative et d'optimisation d'interventions en environnements soumis à des rayonnements ionisants. En nous basant sur l'étude d'installations scientifiques et technologiques complexes tels que celles du CERN à Genève (Suisse) et de la GSI à Darmstadt (Allemagne), nous y analysons les besoins et contraintes de planification imposés par les environnements à risques en général, et par lesrayonnements ionisants en particulier. Les implications liées à la collaboration sont ensuite détaillées, et un modèle ontologique d'intervention est proposé afin de sélectionner les méthodes les plus adaptées au problème étudié. La méthode proposée dans cette thèse repose sur des techniques éprouvées en planification de projets ainsi qu'en conception de produits comme la Design Structure Matrix (DSM). Elle introduit en revanche dans ces domaines des méthodes habituellement rencontrées en intelligence artificielle : les algèbres temporelles qualitatives et la propagation des contraintes temporelles, ainsi que la recherche de compromis en cas de conflit. Cette « DSM Collaborative » a été implémentée dans une application prototype testée sur des cas pratiques au CERN et à la GSI, dont le premier est décrit dans l'ultime chapitre de cette thèse. C'est une approche qui place la ressource(essentiellement humaine) et les contraintes temporelles au coeur du processus de planification. Elle met l'accent sur la collaboration entre les différents participants, ainsi que sur la simulation et la comparaison multicritère de multiples scenarii plutôt que sur la recherche d'un unique optimum souvent irréalisable sur le plan pratique. / This work proposes a methodology to handle complexity in organizations byfocusing on innovative and collaborative planning and scheduling methods dedicated to the optimization of interventions in environments emitting ionizing radiations. By taking as work environment highly complex and technological scientific facilities such as the ones of CERN in Geneva (Switzerland) and GSI in Darmstadt (Germany), we analyze the needs and requirements induced in intervention planning and scheduling by hazardous environments in general, and then more specifically by ionizing radiations. The implications of collaborative work are then scrutinized, and an ontological model for interventions is designed in order to select the methods best suited to our problem. The framework we present in this work relies on methods sucessfully used in project planning and scheduling and innovative product design like the Design Structure Matrix (DSM). It also introduces in these fields methods borrowed to artificial intelligence planning and scheduling such as the temporal qualitative algebras, constraint propagation, and the search of compromises in case of conflicts. This so called “Collaborative DSM” has been implemented in a prototype software application tested at CERN and GSI on practical applications. The very first one and its results are presented in the final chapter of this thesis. This framework aims at placing resources (mostly human resources) and temporal constraints at the heart of the planning and scheduling process. It focuses on collaboration between the different actors involved, from coordinators to technicians, and on simulation and multiple-criteria comparison of several scenarios, rather than searching for a unique optimum, which often tends to be non-practical, should one even be found.

The main motivation for the business is making profits. For the creation of profit is the need to have a business plan. In order to have a successful business plan, we have to prepare it correctly, and then drive. The entire work is focused on the production, placing on the market and the management of the business plan. At the beginning of the introduction into the environment, and then everything is shown in a particular case. The aim is to show how to do this when you create a business plan, what pitfalls can occur and, above all, from the complex situation do the advantage.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第18408号 / 情博第523号 / 新制||情||92(附属図書館) / 31266 / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 多々納 裕一, 教授 石田 亨, 准教授 畑山 満則 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

The aim of this study is to investigate the optimisation of production planning- and scheduling in a pharmaceutical facility using DES.Research questions: “How can DES be used to achieve flexibility and efficiency in a pharmaceutical facility?” and “How can DES be used to increase efficiency of the resource allocation in a pharmaceutical facility?”Methodology: This study has been compared to a deductive- and a quantitative research approach where a process simulation has been modelled. The theoretical framework was based on books and scientific publications. Empirical data was collected through unstructured observations at the production site, frequent meetings together with the company and through the company’s database Discoverant. Based on the results from the simulation model conclusions could be drawn.Conclusion: The study concluded that there are bottlenecks at the beginning of the processes in all three production flows for Medicine A, Medicine B and Medicine C. If these are raised it would generate greater flexibility and efficiency in the production. There were also indications of a new allocation of resources that would raise efficiency in the production, thus making it possible to increase the output from the production. / Syftet med studien är att undersöka optimering av produktionsplanering- och schemaläggning inom en läkemedelsproduktion med användning av DES.Frågeställningar: ”Hur kan DES användas för att uppnå flexibilitet och effektivitet i en läkemedelsproiduktion?” och ”Hur kan DES användas för att öka effektiviteten kring användandet av resurser i en läkemedelsproduktion?”Metod: Denna studie har liknats vid en deduktiv- och en kvantitativ forskningsansats där en processimulering utformats. Den teoretiska referensramen baserades på böcker och vetenskapliga publikationer. Empirisk data samlades in genom ostrukturerade observationer i produktionen, regelbundna möten tillsammans med företaget och genom företagets databas Discoverant. Baserat på resultaten från simuleringsmodellen kunde slutsatser dras.Slutsats: Studiens slutsats landade i att det finns flaskhalsar i början av alla tre produktionsflöden för Medicin A, Medicin B och Medicin C. Om dessa kan höjas skulle det generera en högre flexibilitet och effektivitet i produktionen. Det finns också tecken som visar på att en ny resursfördelning hade höjt effektiviteten i produktionen, därmed gjort det möjligt att producera mer produkter.

Le besoin croissant de réactivité dans les différents secteurs industriels face à la volatilité des marchés soulève une forte demande de la flexibilité dans leur organisation. Cette flexibilité peut être utilisée pour améliorer la robustesse du planning de référence d’un programme d’activités donné. Les ressources humaines de l’entreprise étant de plus en plus considérées comme le coeur des structures organisationnelles, elles représentent une source de flexibilité renouvelable et viable. Tout d’abord, ce travail a été mis en oeuvre pour modéliser le problème d’affectation multi-périodes des effectifs sur les activités industrielles en considérant deux dimensions de la flexibilité: L’annualisation du temps de travail, qui concerne les politiques de modulation d’horaires, individuels ou collectifs, et la polyvalence des opérateurs, qui induit une vision dynamique de leurs compétences et la nécessité de prévoir les évolutions des performances individuelles en fonction des affectations successives. La nature dynamique de l’efficacité des effectifs a été modélisée en fonction de l’apprentissage par la pratique et de la perte de compétence pendant les périodes d’interruption du travail. En conséquence, nous sommes résolument placés dans un contexte où la durée prévue des activités n’est plus déterministe, mais résulte du nombre des acteurs choisis pour les exécuter, en plus des niveaux de leur expérience. Ensuite, la recherche a été orientée pour répondre à la question : « quelle genre, ou quelle taille, de problème pose le projet que nous devons planifier? ». Par conséquent, les différentes dimensions du problème posé sont classées et analysés pour être évaluées et mesurées. Pour chaque dimension, la méthode d’évaluation la plus pertinente a été proposée : le travail a ensuite consisté à réduire les paramètres résultants en composantes principales en procédant à une analyse factorielle. En résultat, la complexité (ou la simplicité) de la recherche de solution (c’est-à-dire de l’élaboration d’un planning satisfaisant pour un problème donné) peut être évaluée. Pour ce faire, nous avons développé une plate-forme logicielle destinée à résoudre le problème et construire le planning de référence du projet avec l’affectation des ressources associées, plate-forme basée sur les algorithmes génétiques. Le modèle a été validé, et ses paramètres ont été affinés via des plans d’expériences pour garantir la meilleure performance. De plus, la robustesse de ces performances a été étudiée sur la résolution complète d’un échantillon de quatre cents projets, classés selon le nombre de leurs tâches. En raison de l’aspect dynamique de l’efficacité des opérateurs, le présent travail examine un ensemble de facteurs qui influencent le développement de leur polyvalence. Les résultats concluent logiquement qu’une entreprise en quête de flexibilité doit accepter des coûts supplémentaires pour développer la polyvalence de ses opérateurs. Afin de maîtriser ces surcoûts, le nombre des opérateurs qui suivent un programme de développement des compétences doit être optimisé, ainsi que, pour chacun d’eux, le degré de ressemblance entre les nouvelles compétences développées et les compétences initiales, ou le nombre de ces compétences complémentaires (toujours pour chacun d’eux), ainsi enfin que la façon dont les heures de travail des opérateurs doivent être réparties sur la période d’acquisition des compétences. Enfin, ce travail ouvre la porte pour la prise en compte future des facteurs humains et de la flexibilité des effectifs pendant l’élaboration d’un planning de référence. / The growing need of responsiveness for manufacturing companies facing the market volatility raises a strong demand for flexibility in their organization. This flexibility can be used to enhance the robustness of a baseline schedule for a given programme of activities. Since the company personnel are increasingly seen as the core of the organizational structures, they provide the decision-makers with a source of renewable and viable flexibility. First, this work was implemented to model the problem of multi-period workforce allocation on industrial activities with two degrees of flexibility: the annualizing of the working time, which offers opportunities of changing the schedules, individually as well as collectively. The second degree of flexibility is the versatility of operators, which induces a dynamic view of their skills and the need to predict changes in individual performances as a result of successive assignments. The dynamic nature of workforce’s experience was modelled in function of learning-by-doing and of oblivion phenomenon during the work interruption periods. We firmly set ourselves in a context where the expected durations of activities are no longer deterministic, but result from the number and levels of experience of the workers assigned to perform them. After that, the research was oriented to answer the question “What kind of problem is raises the project we are facing to schedule?”: therefore the different dimensions of the project are inventoried and analysed to be measured. For each of these dimensions, the related sensitive assessment methods have been proposed. Relying on the produced correlated measures, the research proposes to aggregate them through a factor analysis in order to produce the main principal components of an instance. Consequently, the complexity or the easiness of solving or realising a given scheduling problem can be evaluated. In that view, we developed a platform software to solve the problem and construct the project baseline schedule with the associated resources allocation. This platform relies on a genetic algorithm. The model has been validated, moreover, its parameters has been tuned to give the best performance, relying on an experimental design procedure. The robustness of its performance was also investigated, by a comprehensive solving of four hundred instances of projects, ranked according to the number of their tasks. Due to the dynamic aspect of the workforce’s experience, this research work investigates a set of different parameters affecting the development of their versatility. The results recommend that the firms seeking for flexibility should accept an amount of extra cost to develop the operators’ multi functionality. In order to control these over-costs, the number of operators who attend a skill development program should be optimised, as well as the similarity of the new developed skills relative to the principal ones, or the number of the additional skills an operator may be trained to, or finally the way the operators’ working hours should be distributed along the period of skill acquisition: this is the field of investigations of the present work which will, in the end, open the door for considering human factors and workforce’s flexibility in generating a work baseline program.

Made available in DSpace on 2016-06-02T19:53:32Z (GMT). No. of bitstreams: 1 PEREZ_MARTINEZ_Karim_2013.pdf: 1435441 bytes, checksum: dc4551ff55ece881790f51193596d2bd (MD5) Previous issue date: 2013-09-27 / Financiadora de Estudos e Projetos / This research deals with the production planning and scheduling problem in the molded pulp packing industry, studying particularly a plant of molded pulp packages for eggs. The production process can be subdivided into two processes: molding process and printing process. The main challenge for production planning activities is on the molding process, where products are produced through tooling that have several molds. These tooling are called "Molding Patterns" or " Conformation Patterns". Each one of the molding patterns can contain one, two, until three kind of molds, allowing to produce several products simultaneously. Producing several products at the time can generate large inventory for low demand products and also null inventory for high demand products. Thus, different inventory levels are defined for each product based on their demand behavior, in order to control inventory quantities. In this way, decisions related to the production planning and scheduling in this production process involve deciding which molding patterns should used, how much time they should be used, and how they should be sequenced. All these should be make taking into account a parallel machine system and sequenced-dependent setups time and costs, in order to minimize inventory and setups costs, as well as penalties associated to inventory out of the specified inventory levels of each product. To represent this problem we proposed two formulations: the first one based on the Capacitated Lot Sizing and Scheduling Problem (CLSP), and the second one based on the General Lot Sizing and Scheduling Problem (GLSP). The results from the models were compared in a set of real word instances of a plant, in order to check the adequacy to represent the decisions involved in the studied production process, as well as the main differences between their production plans and performance of the models. The proposed formulations were also adapted for a particular instance, in order to compare their productions plans against the production plan implement by the studied plant. Results show that the proposed models represent rightly decisions involved in the production planning and scheduling in the molded pulp. Furthermore, the solutions obtained by the proposed models represent production plans with costs significantly lower than the schedule implemented by a real plant in this kind of industry. / Este trabalho aborda o problema de planejamento e programação da produção na indústria de embalagens em polpa moldada, considerando particularmente uma fábrica de embalagens para acondicionamento de ovos. O processo de produção pode ser subdividido em dois processos: processo de moldagem e processo de estampagem. O principal desafio para as atividades de planejamento encontra-se no processo de moldagem, em que a obtenção dos produtos depende da utilização de diferentes ferramentais, formados por um conjunto de moldes. Estes ferramentais são chamados de padrões de conformação ou padrões de moldagem , e podem conter um, dois ou até três tipos de moldes, permitindo a produção simultânea de produtos diferentes. Esta produção simultânea de itens pode gerar grandes níveis de estoque de produtos de baixa demanda e estoques nulos para produtos de alta demanda, desta forma, são definidos diferentes níveis de estoque para cada produto com base no comportamento da sua demanda. As decisões envolvidas no planejamento e programação da produção neste tipo de processo envolve a escolha dos padrões de moldagem a serem utilizados, o tempo de produção de cada padrão, e a sequência em que estes devem ser programados, considerando um sistema de linhas paralelas idênticas e tempos e custos de preparação dependentes da sequência. Estas decisões devem ser definidas de modo a minimizar os custos de estocagem, preparação, e penalidades associadas ao desvio do volume do estoque em relação aos níveis estabelecidos para cada produto. Para representar o problema são propostas dois tipos de formulações: a primeira baseada no Problema de Dimensionamento de Lotes Capacitado (CLSP), e a segunda baseada no Problema de Dimensionamento e Sequenciamento de Lotes Geral (GLSP). Os resultados da resolução dos modelos são comparados com base em exemplares reais da fábrica em estudo, a fim de verificar sua adequação para representar as decisões envolvidas no sistema de produção, as principais diferenças nos planos de produção gerados, e o desempenho destes modelos. Os resultados obtidos demonstram que os modelos propostos representam adequadamente as decisões no sistema de produção estudado, e geram planos de produção significativamente melhores que os planos praticados pela fábrica.

<p>  </p> <p>Available literature indicated that construction projects have been experiencing significant time overruns from their planned duration. In many cases, the primary reasons for project delays were ineffective planning and scheduling methods, poor communication and collaboration between the key stakeholders, and the construction operations and task requirements have been overlooked.</p> <p>Construction project planning and scheduling are extensively studied topics, and several techniques have been developed to solve construction project scheduling problems. Traditional production planning and scheduling techniques are based on the push planning strategy, such as linear and network scheduling techniques. In the traditional method, the project scheduler calculates activity durations and then sequences them to determine when to complete the work. These techniques and planning methods have been criticized for lacking collaboration between project workers and realistic integration of the project time, location, and other essential resources to create a reliable work schedule. Furthermore, the inability to account for site operations, tasks, and workflow leads to waste and delay. </p> <p>Consequently, Ballard and Howell (1990) proposed the last planner system, and then Ballard et al. (2000) further developed the method. In the last planner system, all key stakeholders and the project management team actively communicate and coordinate to accomplish the project’s planned milestones. The last planner system and pull planning scheduling objective is improving workflow and increasing plan reliability. However, the pull planning scheduling method has some limitations. For instance, this method cannot be used to determine the available work capacity in each working space and show how much work can be completed at a given time. In addition, the pull planning and LPS system are highly descriptive and experienced-based, relying on the decision and experiences of the site supervisors. </p> <p>Available literature concerning construction project delay also indicated that ineffective planning and scheduling, slow decision-making, and poor communication and coordination had been the top critical causes of construction project delay.</p> <p>Therefore, this research was conducted to minimize construction project time and cost overrun due to poor scheduling and production planning. The study has been conducted in two main parts. In the first part of this study, critical causes of project delay have been analyzed, and the contribution of poor planning and scheduling to construction project delays in different environments has been assessed. The relative importance index and Spearman’s coefficient techniques have been utilized to analyze the collected data.  The second section of this research work was conducted to investigate the construction scheduling reliability and production efficiency and developed the enhanced production planning and scheduling method to improve schedule reliability and production plan efficiency.  The reason for developing the enhanced production planning and scheduling method was to find the best work option to optimize work duration and efficiently plan required resources per category of the identified activities. In addition, this study has automated the scheduling input data capturing from the project BIM model by utilizing the developed visual program.</p> <p>The study finding in the first section indicated that the top ten critical causes of identified causes of project delay in specified environments were significantly different. However, Ineffective project planning and scheduling had been among the most critical causes in all three conditions. Ineffective planning and scheduling were ranked number one in developed environment conditions, second in developing countries, and fifth in high-risk environments.</p> <p>Study results in the second section have shown that the case study's executed schedule had experienced significant changes in the planned dates of individual tasks, project milestones, and resource allocation. The project schedule critical path and critical activities were changed repeatedly after each update, and the project structure work was delayed for 30 days from its initial plan, as illustrated in figures 33 to 35. Subsequently, the enhanced planning methodology has been applied in the selected case study to validate the developed method and evaluate the result of the case study. The case study implemented work plan has been compared with the enhanced planning-based developed schedule. The total duration of the enhanced planning-based method has been calculated to be 240 work days, which shows 30 days less time from implemented case study plan and 50 days from the project base plan in the construction document, as illustrated in figures 39 to 41. </p> <p>Furthermore, the production schedule sensitivity analysis has shown that the production schedule and the case study base plan tasks duration have not been significantly different since both schedules were created based on the similar size of the work crew, but in terms of the number of the planned task, the production schedule had been created based on the most suitable work option. Another advantage of the production schedule is that it is more reliable because the schedule is created for a shorter duration, not long before the project work starts, and it is created after multiple collaborations and assessment steps. In addition, the developed program in this study using Revit dynamo automated the extraction of input data from the BIM model to create the project schedule. </p> <p>In conclusion, based on the case study results, the enhanced production planning methodology and developed metrics and indices can be applied to various building construction projects to find the most suitable work option and create a reliable and resource-efficient work schedule. </p>

No description available.