Computer vision in aseptic pharmaceutical manufacturing: a deep learning-based approach to vial inspection and pack formation during a lyophilizer loading cycle

Vision systems are powerful tools playing an increasingly important role in modern industry, to detect errors and maintain product standards. With the enlarged availability of affordable industrial cameras, computer vision algorithms have been increasingly applied in industrial manufacturing processes monitoring. Until a few years ago, industrial computer vision applications relied only on ad-hoc algorithms designed for the specific object and acquisition setup being monitored, with a strong focus on co-designing the acquisition and processing pipeline. Deep learning has overcome these limits providing greater flexibility and faster re-configuration. In this work, the process to be inspected consists in vials’ pack formation entering a freeze-dryer, which is a common scenario in pharmaceutical active ingredient packaging lines. To ensure that the machine produces proper packs, a vision system is installed at the entrance of the freeze-dryer to detect eventual anomalies with execution times compatible with the production specifications. Other constraints come from sterility and safety standards required in pharmaceutical manufacturing. This work presents an overview about the production line, with particular focus on the vision system designed, and about all trials conducted to obtain the final performance. Transfer learning, alleviating the requirement for a large number of training data, combined with data augmentation methods, consisting in the generation of synthetic images, were used to effectively increase the performances while reducing the cost of data acquisition and annotation. The proposed vision algorithm is composed by two main subtasks, designed respectively to vials counting and discrepancy detection. The first one was trained on more than 23k vials (about 300 images) and tested on 5k more (about 75 images), whereas 60 training images and 52 testing images were used for the second one.

Mechanical properties of concrete produced with a composite of water treatment sludge and sawdust

In developing countries such as Brazil, the wastes generated in the decanters and filters of water treatment plants are discharged directly into the same rivers and streams that supply water for treatment. Another environmental problem is the unregulated discard of wood wastes. The lumber and wood products industry generates large quantities of this waste, from logging to the manufacture of the end product. Brazil has few biomass plants and therefore only a minor part of these wastes are reused. This paper presents the results of the first study involving a novel scientific and technological approach to evaluate the possibility of combining these two types of wastes in the production of a light-weight composite for concrete. The concrete produced with cement:sand:composite:water mass ratios of 1:2.5:0.67:0.6 displayed an axial compressive strength of 11.1 MPa, a compressive and diametral tensile strength of 1.2 MPa, water absorption of 8.8%, and a specific mass of 1.847 kg/m(3). The mechanical properties obtained with this concrete render it suitable for application in non-structural elements. (C) 2010 Elsevier Ltd. All rights reserved.

Roadmapping for technology push and partnership: A contribution for open innovation environments

There are several tools in the literature that support innovation in organizations. Some of the most cited are the so-called technology roadmapping methods, also known as TRM. However, these methods are designed primarily for organizations that adopt the market pull strategy of technology-product integration. Organizations that adopt the technology push integration strategy are neglected in the literature. Furthermore, with the advent of open innovation, it is possible to note the need to consider the adoption of partnerships in the innovation process. Thus, this study proposes a method of technology roadmapping, identified as method for technology push (MTP), applicable to organizations that adopt the technology push integration strategy, such as SMEs and independent research centers in an open-innovation environment. The method was developed through action-research and was assessed from two analytical standpoints: externally, via a specific literature review on its theoretical contributions, and internally, through the analysis of potential users` perceptions on the feasibility of applying MTP. The results indicate both the unique character of the method and its perceived implementation feasibility. Future research is suggested in order to validate the method in different types of organizations (C) 2011 Elsevier Ltd. All rights reserved.

Structural ceramics made with clay and steel dust pollutants

Electric arc furnace steel dust is a by-product of the steelmaking process and contains high amounts of the iron and zinc and significant amounts of lead, chromium, and cadmium. Metal recycling however, is not always economically feasible, especially due to the complex mineralogical composition of this material. In this study an application of this material is presented. Ceramics were produced with clay and variable amounts of steel dust. The bulk material was fired between 800 and 1100 degrees C. The influence of the composition and the processing temperature on the mechanical strength, linear shrinkage, water absorption, apparent density and bending strength and metal leaching of the ceramic samples was investigated. A blend of clay with up to 20% dust yielded ceramics with limited metal contamination risk and may thus be used for structural ceramics production. (C) 2011 Elsevier B.V. All rights reserved.

A technological and organisational explanation for the size distribution of firms

This paper combines insights from the literature on the economics of organisation with traditional models of market structure to construct a theory of equilibrium firm size heterogeneity under the assumption of a homogenous product industry. It is possible that configurations consisting entirely of small firms (run by entrepreneurs with limited attention) and with larger firms (using managerial techniques to substitute away these limits to allow increasing returns technologies to become profitable) can arise in equilibrium. However, there also exist equilibrium configurations with the co-existence of large and small firms. The efficiency properties of these respective equilibria are discussed. Finally, the implications of an expanding market size are considered.

Testing for Market Power in Multiple-Input, Multiple-Output Industries: The Australian Grains and Oilseeds Industries

Recent empirical studies have found significant evidence of departures from competition in the input side of the Australian bread, breakfast cereal and margarine end-product markets. For example, Griffith (2000) found that firms in some parts of the processing and marketing sector exerted market power when purchasing grains and oilseeds from farmers. As noted at the time, this result accorded well with the views of previous regulatory authorities (p.358). In the mid-1990s, the Prices Surveillence Authority (PSA 1994) determined that the markets for products contained in the Breakfast Cereals and Cooking Oils and Fats indexes were "not effectively competitive" (p.14). The PSA consequently maintained price surveillence on the major firms in this product group. The Griffith result is also consistent with the large number of legal judgements against firms in this sector over the past decade for price fixing or other types of non-competitive behaviour. For example, bread manufacturer George Weston was fined twice during 2000 for non-competitive conduct and the ACCC has also recently pursued and won cases against retailer Safeway in grains and oilseeds product lines.

Protein folding, metal ions and conformational states: the case of a di-cluster ferredoxin

Dissertation presented to obtain the PhD degree in Biochemistry at the Instituto de Tecnologia Química e Biológica, Universidade Nova de Lisboa

Acqusition and data analysis of the eco-efficiency for the establishment of indicators parameters for industrial environmental sustainability

The industrial activity is inevitably associated with a certain degradation of the environmental quality, because is not possible to guarantee that a manufacturing process can be totally innocuous. The eco-efficiency concept is globally accepted as a philosophy of entreprise management, that encourages the companies to become more competitive, innovative and environmentally responsible by promoting the link between its companies objectives for excellence and its objectives of environmental excellence issues. This link imposes the creation of an organizational methodology where the performance of the company is concordant with the sustainable development. The main propose of this project is to apply the concept of eco-efficiency to the particular case of the metallurgical and metal workshop industries through the development of the particular indicators needed and to produce a manual of procedures for implementation of the accurate solution.

Desenvolvimento de sistema de apoio dinâmico da chapa no corte em guilhotina

Guilhotinas são máquinas robustas, de corte rectilíneo, normalmente associadas a equipamentos de baixo custo, devido à pequena quantidade de dispositivos tecnológicos incorporados. No entanto, esta situação pode ser alterada através da criatividade dos projetistas deste tipo de equipamento. Analisando algumas operações específicas, pode-se observar que algumas ferramentas, quando associadas ao equipamento, podem aumentar substancialmente a produtividade do processo de corte e a qualidade do produto final. Em relação ao processo de corte de chapas finas de metal, pode-se observar que na fase final de corte, o peso do material a cortar é suspenso por uma pequena porção de material que ainda não foi sujeita ao corte. Este facto leva a uma deformação plástica nesta última zona, causando problemas de qualidade no produto final, que não ficará completamente plano. Este trabalho foi desenvolvido em torno deste problema, estudando a melhor solução para desenvolver uma nova ferramenta, capaz de evitar a falta de nivelamento da placa, após corte. Um novo equipamento foi concebido, capaz de ser facilmente incorporado na guilhotina, permitindo o acompanhamento da inclinação da lâmina durante a operação de corte. O sistema é totalmente automatizado, sendo operado por uma única instrução de corte dada pelo operador da máquina. Este sistema permite à empresa fabricante aumentar o valor agregado de cada máquina, oferecendo aos clientes soluções avançadas, contribuindo desta forma para a sustentabilidade do negócio da empresa.

Recommending media content based on machine learning methods

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Revisão dos tempos-padrão no setor de construção de pneus

Este relatório de estágio foi desenvolvido no âmbito do estágio de final de curso, em ambiente industrial, do Mestrado em Engenharia e Gestão Industrial da ESEIG. O estágio foi realizado na Continental Mabor S.A., situada em Vila Nova de Famalicão, mais especificamente no Departamento de Engenharia Industrial. A indústria dos pneus está inserida num mercado cada vez mais competitivo e exigente, em que os custos e os prazos de entrega devem ser cada vez menores e a qualidade do produto cada vez maior. Por esses motivos, é necessária uma constante melhoria dos processos produtivos. Para que este esforço de melhoria contínua seja bem-sucedido é necessário recorrer por vezes a prémios de produção, para incentivar uma maior produtividade. Contudo cada pneu tem tempos de produção diferentes de máquina para máquina e é preciso corrigir esses tempos em prol de uma justa atribuição de prémios. O presente trabalho teve como principal objetivo atualizar as perturbações e atualizar os tempos-máquina no setor de construção de pneus. Inicialmente foi recolhido o tempo de aplicação do capply (material que pertence ao pneu) para futuramente verificar se será possível prever o tempo de aplicação de capply, consoante os metros de aplicação. Como não foi possível estabelecer uma correlação, não será exposta a análise até se chegar a essa conclusão. Depois fez-se o estudo das perturbações, com recurso à cronometragem, na maior das cinco divisões da fábrica - a construção. Por último fez-se a recolha dos tempos-máquina de vários tipos de construção de pneus em todos os módulos de construção de pneus (KM e PU), através do método filmagem. Conseguiu-se singularizar os tempos para cada máquina de forma a tornar, mais justo os prémios de produção atribuídos aos operadores, no curto prazo, e optimizar a produção e o tempo-padrão.

Optimal design and operation of compact simulated moving bed processes for enantioseparations

Simulated moving bed (SMB) chromatography is attracting more and more attention since it is a powerful technique for complex separation tasks. Nowadays, more than 60% of preparative SMB units are installed in the pharmaceutical and in the food in- dustry [SDI, Preparative and Process Liquid Chromatography: The Future of Process Separations, International Strategic Directions, Los Angeles, USA, 2002. http://www. strategicdirections.com]. Chromatography is the method of choice in these ¯elds, be- cause often pharmaceuticals and ¯ne-chemicals have physico-chemical properties which di®er little from those of the by-products, and they may be thermally instable. In these cases, standard separation techniques as distillation and extraction are not applicable. The noteworthiness of preparative chromatography, particulary SMB process, as a sep- aration and puri¯cation process in the above mentioned industries has been increasing, due to its °exibility, energy e±ciency and higher product purity performance. Consequently, a new SMB paradigm is requested by the large number of potential small- scale applications of the SMB technology, which exploits the °exibility and versatility of the technology. In this new SMB paradigm, a number of possibilities for improving SMB performance through variation of parameters during a switching interval, are pushing the trend toward the use of units with smaller number of columns because less stationary phase is used and the setup is more economical. This is especially important for the phar- maceutical industry, where SMBs are seen as multipurpose units that can be applied to di®erent separations in all stages of the drug-development cycle. In order to reduce the experimental e®ort and accordingly the coast associated with the development of separation processes, simulation models are intensively used. One impor- tant aspect in this context refers to the determination of the adsorption isotherms in SMB chromatography, where separations are usually carried out under strongly nonlinear conditions in order to achieve higher productivities. The accurate determination of the competitive adsorption equilibrium of the enantiomeric species is thus of fundamental importance to allow computer-assisted optimization or process scale-up. Two major SMB operating problems are apparent at production scale: the assessment of product quality and the maintenance of long-term stable and controlled operation. Constraints regarding product purity, dictated by pharmaceutical and food regulatory organizations, have drastically increased the demand for product quality control. The strict imposed regulations are increasing the need for developing optically pure drugs.(...)

Modeling and optimization of extracellular polysaccharides production by Enterobacter A47

Polysaccharides are gaining increasing attention as potential environmental friendly and sustainable building blocks in many fields of the (bio)chemical industry. The microbial production of polysaccharides is envisioned as a promising path, since higher biomass growth rates are possible and therefore higher productivities may be achieved compared to vegetable or animal polysaccharides sources. This Ph.D. thesis focuses on the modeling and optimization of a particular microbial polysaccharide, namely the production of extracellular polysaccharides (EPS) by the bacterial strain Enterobacter A47. Enterobacter A47 was found to be a metabolically versatile organism in terms of its adaptability to complex media, notably capable of achieving high growth rates in media containing glycerol byproduct from the biodiesel industry. However, the industrial implementation of this production process is still hampered due to a largely unoptimized process. Kinetic rates from the bioreactor operation are heavily dependent on operational parameters such as temperature, pH, stirring and aeration rate. The increase of culture broth viscosity is a common feature of this culture and has a major impact on the overall performance. This fact complicates the mathematical modeling of the process, limiting the possibility to understand, control and optimize productivity. In order to tackle this difficulty, data-driven mathematical methodologies such as Artificial Neural Networks can be employed to incorporate additional process data to complement the known mathematical description of the fermentation kinetics. In this Ph.D. thesis, we have adopted such an hybrid modeling framework that enabled the incorporation of temperature, pH and viscosity effects on the fermentation kinetics in order to improve the dynamical modeling and optimization of the process. A model-based optimization method was implemented that enabled to design bioreactor optimal control strategies in the sense of EPS productivity maximization. It is also critical to understand EPS synthesis at the level of the bacterial metabolism, since the production of EPS is a tightly regulated process. Methods of pathway analysis provide a means to unravel the fundamental pathways and their controls in bioprocesses. In the present Ph.D. thesis, a novel methodology called Principal Elementary Mode Analysis (PEMA) was developed and implemented that enabled to identify which cellular fluxes are activated under different conditions of temperature and pH. It is shown that differences in these two parameters affect the chemical composition of EPS, hence they are critical for the regulation of the product synthesis. In future studies, the knowledge provided by PEMA could foster the development of metabolically meaningful control strategies that target the EPS sugar content and oder product quality parameters.

The role of automatic shape and position recognitionin streamlining manufacturing

The main features of most components consist of simple basic functional geometries: planes, cylinders, spheres and cones. Shape and position recognition of these geometries is essential for dimensional characterization of components, and represent an important contribution in the life cycle of the product, concerning in particular the manufacturing and inspection processes of the final product. This work aims to establish an algorithm to automatically recognize such geometries, without operator intervention. Using differential geometry large volumes of data can be treated and the basic functional geometries to be dealt recognized. The original data can be obtained by rapid acquisition methods, such as 3D survey or photography, and then converted into Cartesian coordinates. The satisfaction of intrinsic decision conditions allows different geometries to be fast identified, without operator intervention. Since inspection is generally a time consuming task, this method reduces operator intervention in the process. The algorithm was first tested using geometric data generated in MATLAB and then through a set of data points acquired by measuring with a coordinate measuring machine and a 3D scan on real physical surfaces. Comparison time spent in measuring is presented to show the advantage of the method. The results validated the suitability and potential of the algorithm hereby proposed

Aplicação de celulases e xilanases na reciclagem de fibras de papel

Tese de Doutoramento em Engenharia Química e Biológica (área de conhecimento em Engenharia Enzimática e das Fermentações)