Produktionslinjer som har fått ett slutdatum för att producera sista produkten har nyautmaningar jämfört med nya eller etablerade produktionslinjer. Med ett slutdatum blirinvesteringar på utrustningen mer restriktiva och med färre tillverkade produkter blir det färreenheter att slå ut kostnaderna på. När Scania då väljer att sluta producera på den gamlaproduktionslinjen för att istället producera raka motorer på den nya produktionslinjen uppstårvissa frågeställningar. Hur kan produktionen övervakas trots att färre motorer tillverkas pålinjen? Hur väljs rätt investering för maskinerna när det finns ett slutdatum? Hur säkerställs attproduktionen fortfarande har relevanta nyckeltal? Syftet med studien var att se hur produktionen påverkas av att ha längre takttid ochmöjligheterna till att implementera statistisk processtyrning (SPS) i produktionen. För att uppnåsyftet användes kvalitativ och kvantitativ datainsamling. Den kvalitativa datainsamlingenanvände intervjuer och fokusgrupper för att ge en lägesbild över produktionen. Den kvantitativadatainsamlingen kom från programvaror som övervakar produktionen. En station som ärhelautomatiserad valdes för att implementera styrdiagram på. Data från ett år bakåt i tidensamlades in för att få en bättre förståelse över hur den presterat det senaste året. Under analysenframkom det att den data som samlats in var autokorrelerad, därför användes en moving average(MA(1)) modell för att övervaka processen. Resultatet visar på att det finns fördelar med att implementera styrdiagram på fler stationer änden som utfördes under examensarbetet. Arbetet kan användas som en grund till en eventuellutökning av styrdiagram längs hela produktionslinan. Från intervjuer framkom det att underlägre produktionstakt blir det lägre stopptid och mer tid för annat för montörer och team leaders.Rekommendationerna blev därför att införa styrdiagram på stationen som undersöks underarbetet. För att få en bättre bild över prestationen över tid och kunna se resultatet av eventuellaförbättringar. Andra rekommendationen är gällande övervakning av produktionen, där antalstörningar ska dokumenteras istället för stopptiden på linjen. / Production lines with a decided end date to stop production have new challenges associated tothem compared to new or already established production lines. With an end date, investmentsin equipment become more restrictive and with fewer manufactured products, there will befewer units to cover the costs. When Scania finalizes the decision to close the old productionline of in line engines and move them to the new production line some questions arises. Howare they planning on monitoring production even though fewer engines are beingmanufactured? How to choose the right investment for the machines when there is an end date? The purpose of the study was to see how production is affected by having a longer cycle timeand the possibilities of implementing statistical process control (SPC) in production. To achievethe purpose, focus groups, observations, qualitative and quantitative data collection were used.A station that is fully automated was chosen to implement control charts on. Data from over ayear back in time were collected to get a better understanding of how it has performed in thepast year. During the analysis, it emerged that the data collected was autocorrelated, thereforea moving average (MA (1)) model was used to monitor the process. The results show that there are advantages to implementing control charts at multiple stationsrather than just the one performed during the degree project. This thesis is aimed at working asa basis for possible future expansion for other machines on the production line. Frominterviews, it emerged that during lower production, there will be less downtime and more timefor other things for operators and team leaders to do. The recommendations were therefore tointroduce control charts at the station that are examined within the thesis. These charts canenable production to get a better picture of the performance over time and be able to see theresult of any improvements. The second recommendation is regarding monitoring ofproduction, where the number of disturbances in production should be documented instead ofthe stop time on the line.

Accurate cardinality estimation is critically important to high-quality query optimization. It is well known that conventional cardinality estimation based on histograms or similar statistics may produce extremely poor estimates in a variety of situations, for example, queries with complex predicates, correlation among columns, or predicates containing user-defined functions. In this paper, we propose a new, general cardinality estimation technique that combines random sampling and materialized view technology to produce accurate estimates even in these situations. As a major innovation, we exploit feedback information from query execution and process control techniques to assure that estimates remain statistically valid when the underlying data changes. Experimental results based on a prototype implementation in Microsoft SQL Server demonstrate the practicality of the approach and illustrate the dramatic effects improved cardinality estimates may have.

Good cardinality estimates are critical for generating good execution plans during query optimization. Complex predicates, correlations between columns, and user-defined functions are extremely hard to handle when using the traditional histogram approach. This demo illustrates the use of sample views for cardinality estimations as prototyped in Microsoft SQL Server. We show the creation of sample views, discuss how they are exploited during query optimization, and explain their potential effect on query plans. In addition, we also show our implementation of maintenance policies using statistical quality control techniques based on query feedback.

Statistical quality control is the application of statistical methods to problems for which it is of interest to evaluate, establish, or verify the quality of a product. The two basic areas of statistical quality control that have received both the greatest attention in the literature and the widest acceptance in industry are acceptance sampling and statistical process control. In the majority of such techniques, a single characteristic of an item is used to describe its quality. In such cases, one of two basic types of product quality measures is typically used: attributes product quality measures and variables product quality measures. Variables product quality measures evaluate an item’s quality by measuring its quality characteristic on a continuous scale. Attributes product quality measures assign a 0 to an item if its characteristic is conforming to some specification, and 1 if its characteristic is nonconforming. Although attributes and variables product quality measures have many appropriate applications, there are many situations m which product quality is best described by classifying a single characteristic of the item using three or more discrete levels. A multilevel discrete product quality measure is a function that assigns a numerical value to such an item corresponding to the level in which it is classified. Several acceptance sampling plans and control charts that incorporate the use of multilevel discrete product quality measures are defined here. In addition to the multilevel discrete product quality measure, each of the defined methods utilizes a quality value function. A quality value function assigns a numerical value to an item based on the classification it receives from the multilevel discrete product quality measure. Each of the defined multilevel acceptance sampling plans and multilevel control charts is evaluated with respect to its probabilistic behavior. In addition, the problem of parameter selection and quality value function specification is addressed for each of the defined techniques. The cases considered are the 3-level case, the 4-level case, and the general j-level case. / Ph. D.

A competitividade é um fator de extrema importância para o sucesso das organizações. Os expressivos resultados alcançados pela Motorola e General Electric (GE), por meio do programa Seis Sigma, tem sido uma fonte de inspiração para muitas empresas seguirem o seu exemplo e conseguir maior competitividade. O programa Seis Sigma foi criado e evoluiu em ambiente de manufatura, mas também pode ser aplicado em processos de serviços. Entretanto a aplicação em serviços tem sido feita de forma mais modesta, com menor participação de empresas, e conseqüentemente menor número de casos e relatos divulgados. A literatura menciona que de forma geral o desempenho dos processos de serviços é inferior aos processos de manufatura, e isso pode ser um indicativo de boa oportunidade para a aplicação do programa Seis Sigma. Este trabalho tem como objetivo a análise comparativa da aplicação do programa Seis Sigma em processos de manufatura e serviços, por meio de revisão da literatura e pesquisa com empresas que aplicam o programa, visando entender as diferenças da aplicação em benefício da aplicação em serviços. Os resultados obtidos sugerem indícios de similaridades e diferenças significativas, tais como \"no perfil do Black Belt, nas equipes de projeto, no tempo de execução de um projeto, no uso da CTQ, na disponibilidade e natureza dos dados e na aplicação de técnicas e ferramentas\" que podem ajudar na expansão do programa em serviços, e assim, espera-se que possa motivar mais pesquisas com esse tema de trabalho. / Competitiveness is an important factor for any organization success. The Six Sigma program, which has been used by companies like Motorola and GE since the 1980\'s, has proved to be a successful way to make any company improve all areas of business and therefore, become more competitive. Although it was created and has been growing in manufacturing successfully, its implementation can reach a much wider field of application. In the last few years, some service corporations also been benefited by the use of this program. However, different from manufacturing, its application is less popular and still restricted to few companies that have already implemented it, which explains limited case studies and projects published in the literature. This paper has the goal to perform a comparative analysis of Six Sigma program implementation in manufacturing as well as in services process and consequently, comprehend the differences and advantages of its application in these different fields. The results of this study, which are based on literature review and also a survey with service companies, have led to some significant similarities and differences like the profile of the Black Belt, project time execution, CTQ use, the nature and availability of the data and application of techniques and tools. Further research, can certainly contribute to the expansion of the Six Sigma methodology improvement in service quality.

A competitividade é um fator de extrema importância para o sucesso das organizações. Os expressivos resultados alcançados pela Motorola e General Electric (GE), por meio do programa Seis Sigma, tem sido uma fonte de inspiração para muitas empresas seguirem o seu exemplo e conseguir maior competitividade. O programa Seis Sigma foi criado e evoluiu em ambiente de manufatura, mas também pode ser aplicado em processos de serviços. Entretanto a aplicação em serviços tem sido feita de forma mais modesta, com menor participação de empresas, e conseqüentemente menor número de casos e relatos divulgados. A literatura menciona que de forma geral o desempenho dos processos de serviços é inferior aos processos de manufatura, e isso pode ser um indicativo de boa oportunidade para a aplicação do programa Seis Sigma. Este trabalho tem como objetivo a análise comparativa da aplicação do programa Seis Sigma em processos de manufatura e serviços, por meio de revisão da literatura e pesquisa com empresas que aplicam o programa, visando entender as diferenças da aplicação em benefício da aplicação em serviços. Os resultados obtidos sugerem indícios de similaridades e diferenças significativas, tais como \"no perfil do Black Belt, nas equipes de projeto, no tempo de execução de um projeto, no uso da CTQ, na disponibilidade e natureza dos dados e na aplicação de técnicas e ferramentas\" que podem ajudar na expansão do programa em serviços, e assim, espera-se que possa motivar mais pesquisas com esse tema de trabalho. / Competitiveness is an important factor for any organization success. The Six Sigma program, which has been used by companies like Motorola and GE since the 1980\'s, has proved to be a successful way to make any company improve all areas of business and therefore, become more competitive. Although it was created and has been growing in manufacturing successfully, its implementation can reach a much wider field of application. In the last few years, some service corporations also been benefited by the use of this program. However, different from manufacturing, its application is less popular and still restricted to few companies that have already implemented it, which explains limited case studies and projects published in the literature. This paper has the goal to perform a comparative analysis of Six Sigma program implementation in manufacturing as well as in services process and consequently, comprehend the differences and advantages of its application in these different fields. The results of this study, which are based on literature review and also a survey with service companies, have led to some significant similarities and differences like the profile of the Black Belt, project time execution, CTQ use, the nature and availability of the data and application of techniques and tools. Further research, can certainly contribute to the expansion of the Six Sigma methodology improvement in service quality.

Made available in DSpace on 2015-05-08T14:53:25Z (GMT). No. of bitstreams: 1 ArquivoTotalJoseAlmeida.pdf: 1891145 bytes, checksum: 15212c0ee3aea31416abaeb33cac710c (MD5) Previous issue date: 2013-08-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / The research project studied, aimed to apply a forward search algorithm to aid decision making in multivariate statistical process control in the manufacture of crates in a company of plastic products. Besides, the use of principal components analysis (PCA) and the Hotelling T square chart can summarize relevant information of this process. Thus, they were produced two results of considerable importance: the scores of the principal components and an adapted Hotelling T square chart, highlighting the relationship between the ten variables analyzed. The forward search algorithm detects discordant points of the data clustering rest that, when are too far away or have very different characteristics, are called outliers. The BACON algorithm was used for the detection of such occurrences, which part of a small subset demonstrably free of the original data outliers and it goes adding new information, which is not outliers, to this initial subset until no information can more be absorbed. One of the advantages of using this algorithm is that it combats the masking and swamping phenomena that alter the mean and covariance estimates. The research results showed that, for the dataset studied, the BACON algorithm did not detected no dissenting point. A simulation was then developed, using a uniform distribution by obtaining random numbers within a range for modifying the mean and standard deviation values, in order to show that this method is effective in detecting these outliers. For this simulation, they were randomly changed 5% of the mean and the standard deviation values of the original data. The result of this simulation showed that the BACON algorithm is perfectly applicable to this case study, being indicated its use in other processes that simultaneously depend on several variables. / O projeto de pesquisa estudado teve o objetivo de aplicar um algoritmo de busca sucessiva para o auxílio à tomada de decisão no controle estatístico do processo multivariado, na fabricação de garrafeiras em uma empresa de produtos plásticos. Além disso, a utilização das técnicas de análise de componentes principais (ACP) e da carta T² de Hotelling pode sumarizar parte das informações relevantes desse processo. Produziram-se então dois resultados de considerável importância: os escores dos componentes principais e um gráfico T² de Hotelling adaptado, evidenciando a relação entre as dez variáveis analisadas. O algoritmo de busca sucessiva detecta pontos discordantes do restante do agrupamento de dados que, quando se encontram muito distantes ou têm características muito diferentes, são denominados outliers. O algoritmo BACON foi utilizado para a detecção de tais ocorrências, o qual parte de um pequeno subconjunto, comprovadamente livre de outliers, dos dados originais e vai adicionando novas informações, que também não são outliers, a esse subconjunto inicial até que nenhuma informação possa mais ser absorvida. Uma das vantagens da utilização desse algoritmo é que ele combate os fenômenos do mascaramento e do esmagamento que alteram as estimativas da média e da covariância. Os resultados da pesquisa mostraram que, para a o conjunto de dados estudados, o algoritmo BACON não detectou nenhum ponto discordante. Uma simulação foi então desenvolvida, utilizando uma distribuição uniforme através da obtenção de números aleatórios dentro de um intervalo para a modificação dos valores da média e do desvio-padrão, a fim de mostrar que tal método é eficaz na detecção desses pontos aberrantes. Para essa simulação, foram alterados aleatoriamente os valores da média e do desvio-padrão de 5% dos dados originais. O resultado dessa simulação mostrou que o algoritmo BACON é perfeitamente aplicável ao caso estudado, sendo indicada a sua utilização em outros processos produtivos que dependam simultaneamente de diversas variáveis.

Orientador: Carlos Eduardo Angeli Furlani / Resumo: As propriedades que atuam no deslizamento lateral de um equipamento de arrasto em áreas agrícolas, variam amplamente, indo desde as relacionadas ao solo até aos parâmetros envolvidos no sistema trator-equipamento que podem afetar o deslocamento lateral. O objetivo com o estudo foi mensurar o erro de paralelismo do conjunto trator-protótipo em função de diferentes raios de curvatura, larguras de bitola e comprimentos do cabeçalho de um protótipo de arrasto, além de avaliar a variabilidade do processo por meio do Controle Estatístico do Processo. Os testes foram realizados em área experimental da Universidade Estadual Paulista (Unesp), Faculdade de Ciências Agrárias e Veterinárias, Câmpus de Jaboticabal. Foi adaptado o chassi de uma semeadora-adubadora, que possibilitasse mudança no comprimento do cabeçalho e variação na largura da bitola do equipamento, o qual denominamos protótipo de arrasto. O delineamento experimental foi o inteiramente casualizado, em esquema fatorial 5x4x15, com cinco comprimentos do cabeçalho e quatro larguras de bitola do protótipo em quinze raios de curvatura médio. A medição do paralelismo entre as passadas do conjunto trator-protótipo foi obtida por meio de um instrumento desenvolvido que denominamos “pirulito” e com o auxílio de uma trena. Nos raios de 16,4 m e de 20 m os erros de paralelismo são maiores, em todas as bitolas e vão diminuindo à medida que se aumenta a circunferência do raio. O comprimento do cabeçalho de 2,40 m, quando comparado com ... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: The properties that act on the lateral sliding of a trailed equipment in agricultural areas, change widely, ranging from those related to the soil to the parameters involved in the tractor-equipment system that can affect lateral displacement. The objective of the study was to measure the parallelism error of the tractor-prototype set as a function of different curvature radius, the widths of the gauge and the lengths of the header of a drag prototype, in addition, the evaluating process of the variability through the Statistical Process Control. The tests were carried out in an experimental area at the São Paulo State University (Unesp), School of Agricultural and Veterinary Sciences, Campus of Jaboticabal. The chassis of a seeder-fertilizer was adopted, so that it would allow a change in the length of the header and a variation in the width of the gauge of the equipment, which we call the trailed prototype. The experimental design was entirely randomized, in a 5x4x15 factorial scheme, with five header lengths and four widths of gauge of the prototype in fifteen average curvature radius. The measurement of the parallelism between the steps of the tractor-prototype set was obtained by using an instrument that we call “lollipop” and with the help of a measuring tape. In the 16.4 m and 20 m radius the parallelism errors were greater than the other gauges, and it decreased as the radius circumference increased. The header length of 2.40 m, when compared to the others, obtained t... (Complete abstract click electronic access below) / Doutor