An Intelligent System for Petroleum Well Drilling Cutting Analysis

Cutting analysis is a important and crucial task task to detect and prevent problems during the petroleum well drilling process. Several studies have been developed for drilling inspection, but none of them takes care about analysing the generated cutting at the vibrating shale shakers. Here we proposed a system to analyse the cutting's concentration at the vibrating shale shakers, which can indicate problems during the petroleum well drilling process, such that the collapse of the well borehole walls. Cutting's images are acquired and sent to the data analysis module, which has as the main goal to extract features and to classify frames according to one of three previously classes of cutting's volume. A collection of supervised classifiers were applied in order to allow comparisons about their accuracy and efficiency. We used the Optimum-Path Forest (OPF), Artificial Neural Network using Multi layer Perceptrons (ANN-MLP), Support Vector Machines (SVM) and a Bayesian Classifier (BC) for this task. The first one outperformed all the remaining classifiers. Recall that we are also the first to introduce the OPF classifier in this field of knowledge. Very good results show the robustness of the proposed system, which can be also integrated with other commonly system (Mud-Logging) in order to improve the last one's efficiency.

Artificial neural networks for load flow and external equivalents studies

In this paper an artificial neural network (ANN) based methodology is proposed for (a) solving the basic load flow, (b) solving the load flow considering the reactive power limits of generation (PV) buses, (c) determining a good quality load flow starting point for ill-conditioned systems, and (d) computing static external equivalent circuits. An analysis of the input data required as well as the ANN architecture is presented. A multilayer perceptron trained with the Levenberg-Marquardt second order method is used. The proposed methodology was tested with the IEEE 30- and 57-bus, and an ill-conditioned 11-bus system. Normal operating conditions (base case) and several contingency situations including different load and generation scenarios have been considered. Simulation results show the excellent performance of the ANN for solving problems (a)-(d). (C) 2010 Elsevier B.V. All rights reserved.

New contributions to the determination of resonance frequencies of rectangular microstrip antennas by neural networks

This paper uses artificial neural networks (ANN) to compute the resonance frequencies of rectangular microstrip antennas (MSA), used in mobile communications. Perceptron Multi-layers (PML) networks were used, with the Quasi-Newton method proposed by Broyden, Fletcher, Goldfarb and Shanno (BFGS). Due to the nature of the problem, two hundred and fifty networks were trained, and the resonance frequency for each test antenna was calculated by statistical methods. The estimate resonance frequencies for six test antennas were compared with others results obtained by deterministic and ANN based empirical models from the literature, and presented a better agreement with the experimental values.

An intelligent system to detect drilling problems through drilled cuttings return analysis

Cuttings return analysis is an important tool to detect and prevent problems during the petroleum well drilling process. Several measurements and tools have been developed for drilling problems detection, including mud logging, PWD and downhole torque information. Cuttings flow meters were developed in the past to provide information regarding cuttings return at the shale shakers. Their use, however, significantly impact the operation including rig space issues, interferences in geological analysis besides, additional personel required. This article proposes a non intrusive system to analyze the cuttings concentration at the shale shakers, which can indicate problems during drilling process, such as landslide, the collapse of the well borehole walls. Cuttings images are acquired by a high definition camera installed above the shakers and sent to a computer coupled with a data analysis system which aims the quantification and closure of a cuttings material balance in the well surface system domain. No additional people at the rigsite are required to operate the system. Modern Artificial intelligence techniques are used for pattern recognition and data analysis. Techniques include the Optimum-Path Forest (OPF), Artificial Neural Network using Multilayer Perceptrons (ANN-MLP), Support Vector Machines (SVM) and a Bayesian Classifier (BC). Field test results conducted on offshore floating vessels are presented. Results show the robustness of the proposed system, which can be also integrated with other data to improve the efficiency of drilling problems detection. Copyright 2010, IADC/SPE Drilling Conference and Exhibition.

Fast petroleum well drilling monitoring through optimum-path forest

Automatic inspection of petroleum well drilling has became paramount in the last years, mainly because of the crucial importance of saving time and operations during the drilling process in order to avoid some problems, such as the collapse of the well borehole walls. In this paper, we extended another work by proposing a fast petroleum well drilling monitoring through a modified version of the Optimum-Path Forest classifier. Given that the cutting's volume at the vibrating shale shaker can provide several information about drilling, we used computer vision techniques to extract texture informations from cutting images acquired by a digital camera. A collection of supervised classifiers were applied in order to allow comparisons about their accuracy and effciency. We used the Optimum-Path Forest (OPF), EOPF (Efficient OPF), Artificial Neural Network using Multilayer Perceptrons (ANN-MLP) Support Vector Machines (SVM), and a Bayesian Classifier (BC) to assess the robustness of our proposed schema for petroleum well drilling monitoring through cutting image analysis.

SIRCo: uma arquitetura para Sensoriamento Inteligente de Rádios Cognitivos

The increased demand for using the Industrial, Scientific and Medical (ISM) unlicensed frequency spectrum has caused interference problems and lack of resource availability for wireless networks. Cognitive radio (CR) have emerged as an alternative to reduce interference and intelligently use the spectrum. Several protocols were proposed aiming to mitigate these problems, but most have not been implemented in real devices. This work presents an architecture for Intelligent Sensing for Cognitive Radios (ISCRa), and a spectrum decision model (SDM) based on Artificial Neural Networks (ANN), which uses as input a database with local spectrum behavior and a database with primary users information. For comparison, a spectrum decision model based on AHP, which employs advanced techniques in its spectrum decision method was implemented. Another spectrum decision model that considers only a physical parameter for channel classification was also implemented. Spectrum decision models evaluated, as well as ISCRa's architecture were developed in GNU-Radio framework and implemented on real nodes. Evaluation of SDMs considered metrics of: delivery rate, latency (Round Trip Time - RTT) and handoff. Experiments on real nodes showed that ISCRa architecture with ANN based SDM increased packet delivery rate and presented fewer frequency variation (handoff) while maintaining latency. Considering higher bandwidth as application's Quality of Service requirement, ANN-SDM obtained the best results when compared to other SDM for cognitive radio networks (CRN).

Analysis of postprandial lipemia as a Cardiovascular Disease risk factor using genetic and clinical information: an Artificial Neural Network perspective

Clinical studies indicate that exaggerated postprandial lipemia is linked to the progression of atherosclerosis, leading cause of Cardiovascular Diseases (CVD). CVD is a multi-factorial disease with complex etiology and according to the literature postprandial Triglycerides (TG) can be used as an independent CVD risk factor. Aim of the current study is to construct an Artificial Neural Network (ANN) based system for the identification of the most important gene-gene and/or gene-environmental interactions that contribute to a fast or slow postprandial metabolism of TG in blood and consequently to investigate the causality of postprandial TG response. The design and development of the system is based on a dataset of 213 subjects who underwent a two meals fatty prandial protocol. For each of the subjects a total of 30 input variables corresponding to genetic variations, sex, age and fasting levels of clinical measurements were known. Those variables provide input to the system, which is based on the combined use of Parameter Decreasing Method (PDM) and an ANN. The system was able to identify the ten (10) most informative variables and achieve a mean accuracy equal to 85.21%.

Project Management Learning in a Collaborative Distant Learning Context - An Actual On-going Experience

The goal of this paper is to show the results of an on-going experience on teaching project management to grade students by following a development scheme of management related competencies on an individual basis. In order to achieve that goal, the students are organized in teams that must solve a problem and manage the development of a feasible solution to satisfy the needs of a client. The innovative component advocated in this paper is the formal introduction of negotiating and virtual team management aspects, as different teams from different universities at different locations and comprising students with different backgrounds must collaborate and compete amongst them. The different learning aspects are identified and the improvement levels are reflected in a rubric that has been designed ad hoc for this experience. Finally, the effort frameworks for the student and instructor have been established according to the requirements of the Bologna paradigms. This experience is developed through a software-based support system allowing blended learning for the theoretical and individual?s work aspects, blogs, wikis, etc., as well as project management tools based on WWW that allow the monitoring of not only the expected deliverables and the achievement of the goals but also the progress made on learning as established in the defined rubric

Prototype of EN 301 549 Decision tree

The new European Standard EN 301 549 “Accessibility requirements suitable for public procurement of ICT products and services in Europe” is the response by CEN, CENELEC and ETSI to the European Commission’s Mandate 376. Today, ICT products and services are converging, and the boundaries between product categories are being constantly blurred. For that reason EN 301 549 has been drafted using a feature-based approach, instead of being based on product categories. The result is a standard that can be applied to any ICT product and service, by identifying applicable requirements depending on the features of the ICT. This demonstration presents ongoing work at the research group CETTICO of the Technical University of Madrid. CETTICO is developing a workgroup-based support tool where teams of people can annotate the result of performing a conformity assessment of a given ICT product or service according to the requirements of the EN. One of the functions of the tool is creating evaluation projects. During that task the user defines the features of the corresponding ICT product or service by answering questions presented by the tool. As a result of this process, the tool will create a list of applicable requirements and recommendations.

Estudio de los parámetros necesarios para establecer las medidas de actuación por tipos de buques en situaciones de emergencia después de un accidente

La “Actuación en la Crisis”, objetivo principal de esta tesis, trata de establecer y concretar los procedimientos y apoyos desde tierra y a bordo de los buques, tanto técnicos como operacionales, a seguir por el Capitán y tripulación de un buque después de un accidente, en especial cuando el buque tiene un riesgo importante de hundimiento o necesidad de abandono. La aparición de este concepto es relativamente reciente, es decir desde el año 1995, después de los estudios y propuestas realizados, por el Panel de Expertos de IMO, como consecuencia del hundimiento del buque de pasaje y carga rodada, Estonia, en el que perdieron la vida más de 850 personas a finales de Septiembre de 1994. Entre las propuestas recomendadas y aceptadas por los gobiernos en la Conferencia Internacional SOLAS 1995, figuraba este concepto novedoso, que luego fue adoptado de una forma generalizada para todos los tipos de buques, que hasta entonces sólo disponían de documentos dispersos y a veces contradictorios para la actuación en estos momentos de peligro, que dio lugar a un profundo tratamiento de este problema, que iba a afectar a los buques, tanto en los conceptos y parámetros de proyecto, como a la propia operación del buque. La tesis desarrolla los fundamentos, estado del arte, implantación y consecuencias sobre la configuración y explotación del buque, que han dado lugar a una serie de documentos, que se han incluido en diversos Convenios Internacionales, Códigos y otros documentos de obligada aplicación en la industria naval generados en IMO (SOLAS, Retorno Seguro a Puerto, Plano y Libro de Control de Averías, ISM). La consecuencia más novedosa e interesante de este concepto ha sido la necesidad de disponer cada compañía explotadora del buque, de un servicio importante de “apoyo en la crisis”, que ha dado lugar a implantar un “servicio de emergencia especial”, disponible las 24 horas del día y 365 de año que ofrecen las Sociedades de Clasificación. El know-how de los accidentes que tratan estos servicios, hacen que se puedan establecer ciertas recomendaciones, que se centran, en que el buque tenga, por sus propios medios, una posibilidad de aumentar el KM después de una avería, la garantía de la resistencia estructural adecuada y el aumento del tiempo de hundimiento o el tiempo de mantenimiento a flote (otro tipo de averías vinculadas con la maquinaria, equipo o protección y lucha contra incendios, no son objeto de tesis). Las conclusiones obtenidas, son objeto de discusión especialmente en IACS e IMO, con el fin de establecer las aplicaciones pertinentes, que permitan dar al buque una mayor seguridad. Como objetivo principal de esta tesis es establecer estos puntos de mejora consecuencia de esta actuación en la crisis, con la aportación de varias soluciones que mejorarían los problemas mencionados para los tres tipos de buques que consideramos más importantes (pasaje, petroleros y bulkcarriers) La tesis recorre, desde el principio en 1995, la evolución de esta actuación en la crisis, hasta el momento actual., los puntos básicos que se establecen, que van muy de la mano de la llamada “cultura de seguridad”, objetivo nacido durante los años 90, con el fin de implantar una filosofía distinta para abordar el tratamiento de la seguridad del buque, a la que se venía aplicando hasta el momento, en donde se contemplaba tratar el tema de forma singular y específica para cada caso. La nueva filosofía, trataba de analizar el problema, desde un aspecto global y por tanto horizontal, realizando un estudio exhaustivo de las consecuencias que tendría la aplicación de una nueva medida correctora, en los restantes equipos y sistemas del buque., relativos al proyecto, configuración, operación y explotación del buque. Se describen de manera sucinta las profundas investigaciones a que dio lugar todo lo anterior, estando muchas de ellas, vinculadas a grandes proyectos europeos. La mayor parte de estos proyectos fueron subvencionados por la Comunidad Económica Europea durante la primera década del siglo actual. Dentro de estas investigaciones, donde hay que destacar la participación de todos los agentes del sector marítimo europeo, se hacen imprescindibles la utilización de dos herramientas novedosas para nuestro sector, como son el “Estudio de Riesgos” y la “Evaluación de la Seguridad”, más conocida técnicamente por su nombre ingles “Safety Assessment”, cuyos principios también son incluidos en la tesis. Además se especifican las bases sobre las que se establecen la estabilidad intacta y en averías, con nuevos conceptos, no tratados nunca hasta entonces, como la “altura crítica de agua en cubierta” para la cual el buque se hundiría sin remisión, “estado de la mar” en la que se puede encontrar el buque averiado, el cálculo del tiempo de hundimiento, u otros aspectos como el corrimiento de la carga, o bien el tratamiento de los problemas dinámicos en el nuevo “Código de Estabilidad Intacta”. Con respecto a la resistencia estructural, especialmente el estudio de la “resistencia estructural después de la avería”, que tiene en cuenta el estado de la mar en la que se encontraría el buque afectado. Se analizan los tipos de buques mencionados uno por uno y se sacan, como aportación fundamental de esta tesis, separadamente, las acciones y propuestas a aplicar a estos buques. En primer lugar, las relativas al proyecto y configuración del buque y en segundo lugar, las de operación, explotación y mantenimiento, con el fin de acometer, con garantías de éxito, la respuesta a la ayuda en emergencia y la solución a la difícil situación que pueden tener lugar en condiciones extremas. Para ver el efecto de algunas de las propuestas que se incluyen, se realizan y aplican concretamente, a un buque de pasaje de carga rodada, a un petrolero y a un bulkcarrier, para demostrar el mejor comportamiento de estos buques en situación de emergencia. Para ello se han elegido un buque ejemplo para cada tipo, efectuándose los cálculos de estabilidad y resistencia longitudinal y comparar la situación, en la que quedaría el buque averiado, antes y después de la avería. La tesis se completa con una estadística real de buques averiados de cada uno de estos tres tipos, distinguiendo el tipo de incidente y el número de los buques que lo han sufrido, considerándose como más importantes los incidentes relacionados con varadas, colisiones y fuego resumiéndose lo más relevante de esta aportación también importante de esta tesis. ABSTRACT The "Response in an emergency" is the main objective of this thesis, it seeks to establish and define procedures for technical and operational support onboard and shore, to be followed by the captain and crew on of a ship after an accident, especially when the ship has a significant risk of sinking or a need to abandon it. The emergence of this concept is relatively recent, in 1995, after studies and proposals made by the Panel of Experts IMO, following the sinking of the “Estonia” vessel, where more than 850 people died in late September 1994. In the International Convention SOLAS 1995, among the recommended proposals and accepted regulations, this new concept was included, which was later adopted for all types of ships which until then had only scattered some documents, sometimes including contradictory actions in emergency situations. This led to a profound treatment of this problem, which would affect the vessels in both the concepts and design parameters, as to the proper operation of the vessel. The thesis develops the foundations, state of the art, implementation and consequences on the design and operation of the vessel, this has led to a series of Circulars and Regulations included in several International Codes and Conventions issued by IMO which are required to be complied with (SOLAS Safe Return to Port, Damage Control Plan and Booklet, ISM). The most novel and interesting consequence of this concept has been the need for every company operating the ship to have a shore based support service in emergency situations which has led to implement special emergency services offered by Class Societies which are available 24 hours a day, 365 days per year. The know-how of these services dealing with all types of accidents can establish certain recommendations, which focus on the ship capability to increase the KM after damage. It can also be determined adequate structural strength and the increase of the capsizing time or time afloat (other types of damages associated with the machinery, equipment or firefighting, are not the subject of this thesis). The conclusions are discussed especially in IACS and IMO, in order to establish appropriate applications to improve the security of the vessels. The main objective of this thesis is to establish actions to improve emergency actions, resulting from different responses in the crisis, with the contribution of several solutions that improve the problems mentioned for three types of ships that we consider most important (passenger vessels, tankers and bulk carriers) The thesis runs from the beginning in 1995 to date, the evolution of the response on the crisis. The basics established during the 90s with the "safety culture" in order to implement a different philosophy to address the treatment of the safety of the ship, which was being previously implemented, as something singular and specific to each case. The new philosophy tried to analyse the problem from a global perspective, doing an exhaustive study of the consequences of the implementation of the new regulation in the ship systems and equipment related to the design, configuration and operation of the vessel. Extensive investigations which led to the above are described, many of them being linked to major European projects. Most of these projects were funded by the European Union during the first decade of this century. Within these investigations, which it must be highlighted the participation of all players in the European maritime sector, a necessity to use two new tools for our industry, such as the "Risk Assessment" and "Safety Assessment" whose principles are also included in the thesis. The intact and damage stability principles are established including new concepts, never treated before, as the "critical height of water on deck" for which the ship would sink without remission, "sea state" where the damaged vessel can be found, calculation of capsizing time, or other aspects such cargo shifting or treatment of dynamic problems in the new Intact Stability Code in development. Regarding the structural strength, it has to be especially considered the study of the "residual strength after damage", which takes into account the state of the sea where the vessel damaged can be found. Ship types mentioned are analysed one by one, as a fundamental contribution of this thesis, different actions and proposals are established to apply to these types of vessels. First, those ones relating to the design and configuration of the vessel and also the ones related to the operation and maintenance in order to support successfully responses to emergency situations which may occur in extreme situations. Some of the proposals are applied specifically to a RoRo passenger ship, an oil tanker and a bulkcarrier, to demonstrate the improved performance of these vessels damaged. An example for each type vessel has been chosen, carrying out stability and longitudinal strength calculations comparing the situation of the ship before and after damage. The thesis is completed with incidents statics for each of these three types, distinguishing the type of incident and the number of ships having it. The most important incidents considered are the ones related to groundings, collisions and fire being this other relevant contribution of this thesis.

Uncovering changes in the redox protein interactome of PTEN

Phosphatase and tensin homolog (PTEN) is a redox-sensitive, dual-specificity protein phosphatase involved in regulating a number of cellular processes including metabolism, apoptosis, cell proliferation and survival. It acts as a tumor suppressor by negatively regulating the PI3K/Akt pathway. While direct evidence of a redox regulation of PTEN downstream signaling has been reported, the effect of cellular oxidative stress or direct PTEN oxidation on the PTEN interactome is still poorly defined. To investigate this, PTEN-GST fusion protein was prepared in its reduced form and an H2O2-oxidized form that was reversible by DTT treatment, and these were immobilized on a glutathione-sepharose-based support. The immobilized protein was incubated with cell lysate to capture interacting proteins. Captured proteins were eluted from the beads, analyzed by LC-MSMS and comparatively quantified using label-free methods. After subtraction of interactors that were also present in the resin and GST controls, 97 individual protein interactors were identified, including several that are novel. Fourteen interactors that varied significantly with the redox status of PTEN were identified, including thioredoxin and peroxiredoxin-1. Except for one interactor, their binding was higher for oxidized PTEN. Using western blotting, altered binding to PTEN was confirmed for 3 selected interactors (Prdx1, Trx, and Anxa2) and DDB1 was validated as a novel interactor with unaltered binding. Our results suggest that the redox status of PTEN causes a functional variation in the PTEN interactome which is important for the cellular function of PTEN. The resin capture method developed had distinct advantages in that the redox status of PTEN could be directly controlled and measured.

Predicting delay reductions from freeway traffic diversion for incident management

Traffic incidents are a major source of traffic congestion on freeways. Freeway traffic diversion using pre-planned alternate routes has been used as a strategy to reduce traffic delays due to major traffic incidents. However, it is not always beneficial to divert traffic when an incident occurs. Route diversion may adversely impact traffic on the alternate routes and may not result in an overall benefit. This dissertation research attempts to apply Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques to predict the percent of delay reduction from route diversion to help determine whether traffic should be diverted under given conditions. The DYNASMART-P mesoscopic traffic simulation model was applied to generate simulated data that were used to develop the ANN and SVR models. A sample network that comes with the DYNASMART-P package was used as the base simulation network. A combination of different levels of incident duration, capacity lost, percent of drivers diverted, VMS (variable message sign) messaging duration, and network congestion was simulated to represent different incident scenarios. The resulting percent of delay reduction, average speed, and queue length from each scenario were extracted from the simulation output. The ANN and SVR models were then calibrated for percent of delay reduction as a function of all of the simulated input and output variables. The results show that both the calibrated ANN and SVR models, when applied to the same location used to generate the calibration data, were able to predict delay reduction with a relatively high accuracy in terms of mean square error (MSE) and regression correlation. It was also found that the performance of the ANN model was superior to that of the SVR model. Likewise, when the models were applied to a new location, only the ANN model could produce comparatively good delay reduction predictions under high network congestion level.

Predicting delay reductions from freeway traffic diversion for incident management

Traffic incidents are a major source of traffic congestion on freeways. Freeway traffic diversion using pre-planned alternate routes has been used as a strategy to reduce traffic delays due to major traffic incidents. However, it is not always beneficial to divert traffic when an incident occurs. Route diversion may adversely impact traffic on the alternate routes and may not result in an overall benefit. This dissertation research attempts to apply Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques to predict the percent of delay reduction from route diversion to help determine whether traffic should be diverted under given conditions. The DYNASMART-P mesoscopic traffic simulation model was applied to generate simulated data that were used to develop the ANN and SVR models. A sample network that comes with the DYNASMART-P package was used as the base simulation network. A combination of different levels of incident duration, capacity lost, percent of drivers diverted, VMS (variable message sign) messaging duration, and network congestion was simulated to represent different incident scenarios. The resulting percent of delay reduction, average speed, and queue length from each scenario were extracted from the simulation output. The ANN and SVR models were then calibrated for percent of delay reduction as a function of all of the simulated input and output variables. The results show that both the calibrated ANN and SVR models, when applied to the same location used to generate the calibration data, were able to predict delay reduction with a relatively high accuracy in terms of mean square error (MSE) and regression correlation. It was also found that the performance of the ANN model was superior to that of the SVR model. Likewise, when the models were applied to a new location, only the ANN model could produce comparatively good delay reduction predictions under high network congestion level.

Artificial neural network nonlinear equalizer for coherent optical OFDM

We propose a novel low-complexity artificial neural network (ANN)-based nonlinear equalizer (NLE) for coherent optical orthogonal frequency-division multiplexing (CO-OFDM) and compare it with the recent inverse Volterra-series transfer function (IVSTF)-based NLE over up to 1000 km of uncompensated links. Demonstration of ANN-NLE at 80-Gb/s CO-OFDM using 16-quadrature amplitude modulation reveals a Q-factor improvement after 1000-km transmission of 3 and 1 dB with respect to the linear equalization and IVSTF-NLE, respectively.

Rede Social Pessoal de Cuidadores Informais de Adultos com Necessidades Especiais

Objetivo. Devido ao aumento da esperança de vida, os adultos com necessidades especiais vivem mais tempo, sendo os seus principais cuidadores, geralmente familiares, também mais envelhecidos. Tal situação representa novas necessidades específicas de apoio, sendo inúmeros os desafios colocados ao Serviço Social no sentido de garantir o bem-estar da pessoa com incapacidade e dos seus cuidadores. Assim, este estudo tem como objetivo realizar um levantamento das necessidades de apoio e a caraterização da rede social pessoal de apoio do cuidador informal de adultos com necessidades especiais. Participantes. A amostra é constituída por 40 cuidadores informais de adultos com necessidades especiais, integrados na resposta social “Centro de Atividades Ocupacionais-CAO” da Associação de Paralisia Cerebral de Coimbra, de ambos os sexos com idade igual ou superior a 40 anos. Material e métodos. Foi utilizado o Instrumento de Avaliação da Rede Social Pessoal e um questionário para caracterização sociodemográfica e sociofamiliar dos cuidadores, assim como para avaliação de necessidades. Resultados. Aproximadamente um terço dos cuidadores relatou a experiência de níveis moderados de sobrecarga associada à prestação de cuidados, enquanto mais de metade relatou a experiência de níveis elevados e muito elevados dessa sobrecarga; o apoio financeiro foi referido como a forma de apoio mais necessária no presente, ainda que o apoio em residência tenha sido percecionado por cerca de um terço dos cuidadores como a forma de apoio mais necessária no futuro; enquanto mais de metade considerou o apoio domiciliário e de unidade residencial (institucional). Estes cuidadores familiares referiram a "incerteza" e a "esperança" como os sentimentos mais frequentemente experienciados em relação ao futuro das suas vidas. No que respeita às redes sociais, as relações familiares são centrais a nível estrutural; em termos de caraterísticas funcionais da rede, foram observados valores mais elevados para as dimensões de reciprocidade do apoio e satisfação com a rede social. Implicações. Este estudo sublinha a importância da avaliação das necessidades de apoio dos cuidadores familiares de adultos com necessidades especiais. A sua implementação sistemática pode auxiliar a tomada de decisão baseada na evidência empírica para as intervenções do Serviço Social, tais como na planificação e gestão de respostas e serviços sociais, a par do reconhecimento e ativação dos recursos das próprias famílias, de forma a promover a eficiência dos recursos e eficácia das intervenções, focadas no bem-estar do cidadão com deficiência e das suas famílias. / Aim. The general increase in human life expectancy has resulted in greater rates of survival for adults with special care needs, as well as for their ageing family caregivers. This situation poses different and specific support needs, which represent a major challenge in social work interventions aimed at ensuring the well-being of disabled persons and their caregivers. Therefore, this study was aimed to describe the needs for support and the perceived social support network of family caregivers of adults with special care needs. Participants. The sample for this study comprised 40 family caregivers of disabled adults with special care needs, of both genders and aged 40 years old at minimum, who attended a long-term care facility at Coimbra Cerebral Palsy Association. Material and methods. Participants were administered a self-report questionnaire on socio-economic, family and caregiving needs, along with the Instrument for Assessing Personal Social Networks. Results. Nearly one third a family caregivers experienced moderate caregiving burden, while more than half experienced high or very high levels of caregiving burden; financial support was perceived as the most needed form of support in the present, but residential home care was identified as the most needed form of support in the future; while more than a half considered home-based support and residential support viable options for their disabled family members with special care needs. These family caregivers reported "uncertainty" and "hope" as the most common feelings towards their family life in the future. On the topic of social networks, family relations were found to be crucial at the structural level; in terms of functional characteristics of the network, elevated scores were observed for reciprocity of support and satisfaction with the social network. Implications. This study highlights the importance of increasing the specificity of the assessments of needs for support in family caregivers of disabled adults with special care needs. The systematic conduction of these assessments may assist evidence-based decision making in social work interventions, such as for planning and managing social services, acknowledging and activating the families' own resources, and ultimately promote the efficacy and effectiveness 57 interventions aimed at improving the well-being of disabled citizens and their families.