Browsing by Keyword "Instrumentation"
Now showing 1 - 20 of 136
Results Per Page
Sort Options
Item 3D convolutional neural networks initialized from pretrained 2D convolutional neural networks for classification of industrial parts(2021-02-04) Merino, Ibon; Azpiazu, Jon; Remazeilles, Anthony; Sierra, Basilio; ROBOTICA_FLEX; Medical TechnologiesDeep learning methods have been successfully applied to image processing, mainly using 2D vision sensors. Recently, the rise of depth cameras and other similar 3D sensors has opened the field for new perception techniques. Nevertheless, 3D convolutional neural networks perform slightly worse than other 3D deep learning methods, and even worse than their 2D version. In this paper, we propose to improve 3D deep learning results by transferring the pretrained weights learned in 2D networks to their corresponding 3D version. Using an industrial object recognition context, we have analyzed different combinations of 3D convolutional networks (VGG16, ResNet, Inception ResNet, and EfficientNet), comparing the recognition accuracy. The highest accuracy is obtained with EfficientNetB0 using extrusion with an accuracy of 0.9217, which gives comparable results to state-of-the art methods. We also observed that the transfer approach enabled to improve the accuracy of the Inception ResNet 3D version up to 18% with respect to the score of the 3D approach alone.Item Ammonium polyphosphate-melamine synergies in thermal degradation and smoke toxicity of flexible polyurethane foams(2023-08) Eceiza, I.; Aguirresarobe, R.; Barrio, A.; Fernández-Berridi, M. J.; Irusta, L.; BIOECONOMÍA Y CO2Polyurethane (PUR) foams can lead to fatal fires in the presence of an ignition and oxygen source. Obviously, the problem is not the mere loss of PUR foams properties but essentially, the smoke and toxic gases which are the main factors responsible for fire hazards. This paper reports on the main approaches taken to improve the smoke evolution and toxicity of isophorone diisocyanate (IPDI) based PUR foams which are the incorporation of ammonium polyphosphate (APP), melamine (M) and its combinations as additive flame retardants (FRs). In order to better understand the fire behavior, the influence of incorporated FR on the thermal degradation mechanism was also analyzed by means of thermogravimetry coupled to infrared spectroscopy (TGA-FTIR). In addition, foams were characterized in terms of smoke evolution and toxicity of released gases both asphyxiant and irritant using a smoke density chamber coupled to infrared spectroscopy (NBS-FTIR). Data showed that the mixture of APP and M in different amounts reduced the smoke generation and the concentration of harmful gases, underlying a synergetic effect for the combination of both flame-retardants.Item Analysing Edge Computing Devices for the Deployment of Embedded AI(2023-12) Garcia-Perez, Asier; Miñón, Raúl; Torre-Bastida, Ana I.; Zulueta-Guerrero, Ekaitz; HPAIn recent years, more and more devices are connected to the network, generating an overwhelming amount of data. This term that is booming today is known as the Internet of Things. In order to deal with these data close to the source, the term Edge Computing arises. The main objective is to address the limitations of cloud processing and satisfy the growing demand for applications and services that require low latency, greater efficiency and real-time response capabilities. Furthermore, it is essential to underscore the intrinsic connection between artificial intelligence and edge computing within the context of our study. This integral relationship not only addresses the challenges posed by data proliferation but also propels a transformative wave of innovation, shaping a new era of data processing capabilities at the network’s edge. Edge devices can perform real-time data analysis and make autonomous decisions without relying on constant connectivity to the cloud. This article aims at analysing and comparing Edge Computing devices when artificial intelligence algorithms are deployed on them. To this end, a detailed experiment involving various edge devices, models and metrics is conducted. In addition, we will observe how artificial intelligence accelerators such as Tensor Processing Unit behave. This analysis seeks to respond to the choice of a device that best suits the necessary AI requirements. As a summary, in general terms, the Jetson Nano provides the best performance when only CPU is used. Nevertheless the utilisation of a TPU drastically enhances the results.Item Analysis of Field Data to Describe the Effect of Context (Acoustic and Non-Acoustic Factors) on Urban Soundscapes(2017) Herranz-Pascual, Karmele; García, Igone; Diez, Itxasne; Santander, Alvaro; Aspuru, Itziar; Tecnalia Research & Innovation; CALIDAD Y CONFORT AMBIENTAL; ADAPTACIÓN AL CAMBIO CLIMÁTICOThe need to improve acoustic environments in our cities has led to increased interest in correcting or minimising noise pollution in urban environments, something that has been associated with the resurgence of the soundscape approach. This line of research highlights the importance of context in the perception of acoustic environments. Despite this, few studies consider together a wide number of variables relating to the context, and analyse the relative importance of each. The purpose of this paper is therefore to identify the acoustic and non-acoustic characteristics of a place (context) that influence an individual’s perception of the sound environment and the relative importance of these factors in soundscape. The aim is to continue advancing in the definition of an acoustic comfort indicator for urban places. The data used here were collected in various soundscape campaigns carried out by Tecnalia in Bilbao (Spain) between 2011 and 2014. These studies involved 534 evaluations of 10 different places. The results indicate that many diverse contextual factors determine soundscape, the most important being the congruence between soundscape and landscape. The limitations of the findings and suggestions for further research are also discussed.Item Analysis of Planar Double-Layer Timber Spatial Frames by Using Parametric Tools(2024-08) Manterola-Ubillos, Maddi; Gonzalez-Quintial, Francisco; Rico-Martinez, Jose Miguel; Benito Ayucar, Josu; Begiristain-Mitxelena, Jon Andoni; Materiales Construcción AzpeitiaIt is in the preliminary design phase of a project that the designer makes decisions concerning the global geometry of the structure. When working with space frames, the choice of the frame topology is key for the structural behavior. It is difficult to find manuals that provide guidance on which of the most common topologies is the right one for the project, let alone in wood construction. In response to this shortcoming, the use of parametric software is proposed (Grasshopper build1.0.0007 and Karamba 3D 2.2.0.16-220828). The aim is to create a dynamic catalog that responds instantaneously to changes in the parameters to provide information on structural behavior, pre-dimensioning and metrics. With the display of all this information, the architect will have enough technical argumentation to choose or reject options. The proposal is developed through a case study: the early design and analysis stages of flat double-layer timber spatial frames as for rectangular medium-span roofs.Item Analysis of the Refined Mean-Field Approximation for the 802.11 Protocol Model(2022-11) Ispizua, Begoña; Doncel, Josu; IAMean-field approximation is a method to investigate the behavior of stochastic models formed by a large number of interacting objects. A new approximation was recently established, i.e., the refined mean-field approximation, and its high accuracy when the number of objects is small has been shown. In this work, we consider the model of the 802.11 protocol, which is a discrete-time model and show how the refined mean-field approximation can be adapted to this model. Our results confirm the accuracy of the refined mean-field approximation when the model with N objects is in discrete time.Item Anomaly detection of a 5-phase AC electric motor using Machine Learning classification methods(Institute of Electrical and Electronics Engineers Inc., 2023) Robles, Nerea; Madariaga, Danel; Alvarez-Gonzalez, Fernando; Sierra-Gonzalez, Andres; POWERTRAINWith the goal of performing condition monitoring and anomaly detection applied to electric machines, tagged datasets are synthetically generated, consisting of time series of electrical and mechanical variables from a 5-phase AC synchronous motor, in different conditions of health or abnormal states. Different off-the-shelf Machine Learning classification methods are then applied to those datasets, to generate models that can identify the different abnormal states from the measured variables. Models' performance is compared, and the best candidate selected for doing real-time anomaly detection and predictive maintenance of similar AC electric motors.Item Application-Oriented Data Analytics in Large-Scale Metal Sheet Bending(2023-12) Penalva, Mariluz; Martín, Ander; Ruiz, Cristina; Martínez, Víctor; Veiga, Fernando; Val, Alain Gil del; Ballesteros, Tomás; FABRIC_INTELThe sheet-metal-forming process is crucial in manufacturing various products, including pipes, cans, and containers. Despite its significance, controlling this complex process is challenging and may lead to defects and inefficiencies. This study introduces a novel approach to monitor the sheet-metal-forming process, specifically focusing on the rolling of cans in the oil-and-gas sector. The methodology employed in this work involves the application of temporal-signal-processing and artificial-intelligence (AI) techniques for monitoring and optimizing the manufacturing process. Temporal-signal-processing techniques, such as Markov transition fields (MTFs), are utilized to transform time series data into images, enabling the identification of patterns and anomalies. synamic time warping (DTW) aligns time series data, accommodating variations in speed or timing across different rolling processes. K-medoids clustering identifies representative points, characterizing distinct phases of the rolling process. The results not only demonstrate the effectiveness of this framework in monitoring the rolling process but also lay the foundation for the practical application of these methodologies. This allows operators to work with a simpler characterization source, facilitating a more straightforward interpretation of the manufacturing process.Item Can Shared Control Improve Overtaking Performance? Combining Human and Automation Strengths for a Safer Maneuver(2022-12) Marcano, Mauricio; Tango, Fabio; Sarabia, Joseba; Chiesa, Silvia; Pérez, Joshué; Díaz, Sergio; CCAMThe Shared Control (SC) cooperation scheme, where the driver and automated driving system control the vehicle together, has been gaining attention through the years as a promising option to improve road safety. As a result, advanced interaction methods can be investigated to enhance user experience, acceptance, and trust. Under this perspective, not only the development of algorithms and system applications are needed, but it is also essential to evaluate the system with real drivers, assess its impact on road safety, and understand how drivers accept and are willing to use this technology. In this sense, the contribution of this work is to conduct an experimental study to evaluate if a previously developed shared control system can improve overtaking performance on roads with oncoming traffic. The evaluation is performed in a Driver-in-the-Loop (DiL) simulator with 13 real drivers. The system based on SC is compared against a vehicle with conventional SAE-L2 functionalities. The evaluation includes both objective and subjective assessments. Results show that SC proved to be the best solution for assisting the driver during overtaking in terms of safety and acceptance. The SC’s longer and smoother control transitions provide benefits to cooperative driving. The System Usability Scale (SUS) and the System Acceptance Scale (SAS) questionnaire show that the SC system was perceived as better in terms of usability, usefulness, and satisfaction.Item Carbon layers formed on steel and Ti alloys after ion implantation of C+ at very high doses(1999) Viviente, J. L.; Garcia, A.; Loinaz, A.; Alonso, F.; Oñate, J. I.; TECNOLOGÍA DE MEMBRANAS E INTENSIFICACIÓN DE PROCESOS; Centros PRE-FUSION TECNALIA - (FORMER); Tecnalia Research & InnovationIon implantation is a useful technique to tailor surface properties of steel and Ti alloys. In particular, very high dose C+ implantation (in the range of 1018 ions cm-2) offers the possibility of forming carbon layers without a sharp interface with the substrate material. In this study, ion implantation of carbon doses up to 8 × 1018 ions cm-2 has been performed on 440C martensitic stainless steel and Ti6A14V substrates under similar conditions and tribological and surface analysis results have been compared. Surface hardening occurred for all ion implantation conditions up to doses of 1018 ions cm-2 [1-3]. Higher doses resulted in a different behaviour for both materials. The stainless steel showed a softening while a twofold hardness increase was maintained in the Ti alloy. Nevertheless, at the higher implanted dose a decrease in hardness was also observed in the Ti alloy. Small area XPS analyses were performed to evaluate the chemical states after ion implantation and establish a relationship with the observed surface hardening. Depth profile XPS analyses showed that for a dose of 4 × 1018 ions cm-2 a carbon layer (with concentration over 85% at. C) was formed in the near surface region for both materials.Item Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning(2021-04-01) Saratxaga, Cristina L.; Bote, Jorge; Ortega-Morán, Juan F.; Picón, Artzai; Terradillos, Elena; del Río, Nagore Arbide; Andraka, Nagore; Garrote, Estibaliz; Conde, Olga M.; VISUAL; COMPUTER_VISION; Quantum(1) Background: Clinicians demand new tools for early diagnosis and improved detection of colon lesions that are vital for patient prognosis. Optical coherence tomography (OCT) allows microscopical inspection of tissue and might serve as an optical biopsy method that could lead to in-situ diagnosis and treatment decisions; (2) Methods: A database of murine (rat) healthy, hyperplastic and neoplastic colonic samples with more than 94,000 images was acquired. A methodology that includes a data augmentation processing strategy and a deep learning model for automatic classification (benign vs. malignant) of OCT images is presented and validated over this dataset. Comparative evaluation is performed both over individual B-scan images and C-scan volumes; (3) Results: A model was trained and evaluated with the proposed methodology using six different data splits to present statistically significant results. Considering this, 0.9695 (_0.0141) sensitivity and 0.8094 (_0.1524) specificity were obtained when diagnosis was performed over B-scan images. On the other hand, 0.9821 (_0.0197) sensitivity and 0.7865 (_0.205) specificity were achieved when diagnosis was made considering all the images in the whole C-scan volume; (4) Conclusions: The proposed methodology based on deep learning showed great potential for the automatic characterization of colon polyps and future development of the optical biopsy paradigm.Item CloudOps: Towards the Operationalization of the Cloud Continuum: Concepts, Challenges and a Reference Framework: Towards the Operationalization of the Cloud Continuum: Concepts, Challenges and a Reference Framework(2022-04-25) Alonso, Juncal; Orue-Echevarria, Leire; Huarte, Maider; HPA; Tecnalia Research & InnovationThe current trend of developing highly distributed, context aware, heterogeneous computing intense and data-sensitive applications is changing the boundaries of cloud computing. Encouraged by the growing IoT paradigm and with flexible edge devices available, an ecosystem of a combination of resources, ranging from high density compute and storage to very lightweight embedded computers running on batteries or solar power, is available for DevOps teams from what is known as the Cloud Continuum. In this dynamic context, manageability is key, as well as controlled operations and resources monitoring for handling anomalies. Unfortunately, the operation and management of such heterogeneous computing environments (including edge, cloud and network services) is complex and operators face challenges such as the continuous optimization and autonomous (re-)deployment of context-aware stateless and stateful applications where, however, they must ensure service continuity while anticipating potential failures in the underlying infrastructure. In this paper, we propose a novel CloudOps workflow (extending the traditional DevOps pipeline), proposing techniques and methods for applications’ operators to fully embrace the possibilities of the Cloud Continuum. Our approach will support DevOps teams in the operationalization of the Cloud Continuum. Secondly, we provide an extensive explanation of the scope, possibilities and future of the CloudOps.Item Collaboration-Centred Cities through Urban Apps Based on Open and User-Generated Data(2016-07-01) Aguilera, Unai; López-de-Ipiña, Diego; Pérez-Velasco, Jorge; Tecnalia Research & InnovationThis paper describes the IES Cities platform conceived to streamline the development of urban apps that combine heterogeneous datasets provided by diverse entities, namely, government, citizens, sensor infrastructure and other information data sources. This work pursues the challenge of achieving effective citizen collaboration by empowering them to prosume urban data across time. Particularly, this paper focuses on the query mapper; a key component of the IES Cities platform devised to democratize the development of open data-based mobile urban apps. This component allows developers not only to use available data, but also to contribute to existing datasets with the execution of SQL sentences. In addition, the component allows developers to create ad hoc storages for their applications, publishable as new datasets accessible by other consumers. As multiple users could be contributing and using a dataset, our solution also provides a data level permission mechanism to control how the platform manages the access to its datasets. We have evaluated the advantages brought forward by IES Cities from the developers' perspective by describing an exemplary urban app created on top of it. In addition, we include an evaluation of the main functionalities of the query mapper.Item A comparative study of the effect of Intelligent Control based Torque Vectoring Systems on EVs with different powertrain architectures(Institute of Electrical and Electronics Engineers Inc., 2019-10) Parra, Alberto; Zubizarreta, Asier; Perez, Joshue; Tecnalia Research & Innovation; CCAMIntelligent Transportation Systems (ITS) is currently one of the most active research areas, being electric vehicles (EVs) and their vehicle dynamics enhancement key topics. For this purpose, the development of optimal Advanced Driver-Assistance Systems (ADAS) and Advanced Vehicle Dynamics Control Systems is required. However, as electrified propulsion systems offer multiple topologies (and higher complexity), this task becomes much more difficult. In this context, the use of intelligent control techniques has been proposed as a suitable alternative to offer both performance and flexibility.In order to demonstrate the advantages of intelligent approaches and their ability to adapt to different scenarios, this work presents a comparative study of the performance of Intelligent Control based torque vectoring (TV) algorithms in electric vehicles with three different powertrain topologies: Front Wheel Driven (FWD), Rear Wheel Driven (RWD) and Four/All Wheel Driven (AWD). The same TV approach has been used for all topologies, and a skid-pad test has been selected as a critical manoeuvre for evaluating the lateral dynamics of each topology, which has been simulated using a high fidelity vehicle simulator.Results show that the same intelligent control approach can be used for different topologies without retuning its parameters, enhancing the vehicle dynamics for all cases. This demonstrates the flexibility of intelligent approaches due to their reduced model dependency. Additionally, results show that each architecture promotes a different type of dynamic behaviour in the vehicle: understeering behaviour for the FWD, oversteering behaviour for the RWD and a neutral behaviour for the AWD.Item Comparison of Time Domain Methods for Alignment of RR Signals Acquired by Different Sensor Systems(Institute of Electrical and Electronics Engineers Inc., 2023) Boljanić, Tanja; Malešević, Jovana; Vujnović, Sanja; Janković, Milica M.; SGThis paper compares three different methods for signal alignment called dynamic time warping (DTW), modified dynamic time warping (mDTW) and cross-correlation (CC). RR signals from two different sensor systems, a commercial Wellness Wearable System (Smartex, Italy) and custom-made BACQ system with multi-electrode array (Tecnalia, Sebia) are aligned by DTW, mDTW and CC. Several metrics such as correlation coefficient, reliability, root mean square method and Bland-Altman plots are calculated in order to show the performance of these three methods. All measures indicate that mDTW outperforms other methods. In addition, only mDTW successfully trimmed the beginning and the end of longer signal to match the short one.Item A Complete Framework for a Behavioral Planner with Automated Vehicles: A Car-Sharing Fleet Relocation Approach(2022-11) Arizala, Asier; Zubizarreta, Asier; Pérez, Joshué; CCAMCurrently, research on automated vehicles is strongly related to technological advances to achieve a safe, more comfortable driving process in different circumstances. The main achievements are focused mainly on highway and interurban scenarios. The urban environment remains a complex scenario due to the number of decisions to be made in a restrictive context. In this context, one of the main challenges is the automation of the relocation process of car-sharing in urban areas, where the management of the platooning and automatic parking and de-parking maneuvers needs a solution from the decision point of view. In this work, a novel behavioral planner framework based on a Finite State Machine (FSM) is proposed for car-sharing applications in urban environments. The approach considers four basic maneuvers: platoon following, parking, de-parking, and platoon joining. In addition, a basic V2V communication protocol is proposed to manage the platoon. Maneuver execution is achieved by implementing both classical (i.e., PID) and Model-based Predictive Control (i.e., MPC) for the longitudinal and lateral control problems. The proposed behavioral planner was implemented in an urban scenario with several vehicles using the Carla Simulator, demonstrating that the proposed planner can be helpful to solve the car-sharing fleet relocation problem in cities.Item Condition monitoring of wind turbine pitch controller: A maintenance approach: A maintenance approach(2018-07) González-González, Asier; Jimenez Cortadi, Alberto; Galar, Diego; Ciani, Lorenzo; Tecnalia Research & Innovation; IAWith the increase of wind power capacity worldwide, researchers are focusing their attention on the operation and maintenance of wind turbines. A proper pitch controller must be designed to extend the life cycle of a wind turbine’s blades and tower. The pitch control system has two primaries, but conflicting, objectives: to maximize the wind energy captured and converted into electrical energy and to minimize fatigue and mechanical load. Four metrics have been proposed to balance these two objectives. Also, diverse pitch controller strategies are proposed in this paper to evaluate these objectives. This paper proposes a novel metrics approach to achieve the conflicting objectives with a maintenance focus. It uses a 100 kW wind turbine as a case study to simulate the proposed pitch control strategies and evaluate with the metrics proposed. The results are shown in two tables due to two different wind models are used.Item The conformation of chloramphenicol in the ordered and disordered phases(2019-03-15) Meaurio, Emilio; Sanchez-Rexach, Eva; Butron, Amaia; Sarasua, Jose-Ramon; BIOECONOMÍA Y CO2The conformational behavior of chloramphenicol (CHL) in the solid, liquid and vapor phases is revisited here by means of FTIR spectroscopy and QM methods. In the crystalline phase, both the IR analysis and QM computations discard the conformer proposed by Acharya et al. (Acta Cryst., 1979, B35:1360–1363) and support the one proposed by Chatterjee et al. (J. Cryst. Mol. Struct., 1979, 9:295–304), characterized by an intramolecular O–H⋯O hydrogen bond in which the primary hydroxyl group acts as hydrogen bond donor. The conformational behavior of CHL in the liquid and gas phases has been analyzed using QM calculations. The Self-Consistent Reaction Field (SCRF) method with the Onsager solvation model has been used for the initial optimizations in solution, and the lowest energy conformers have been refined using the Solvation Model based on Density (SMD). In solution environment the intramolecular O–H⋯O hydrogen bond in CHL is reversed so that the secondary hydroxyl group acts as hydrogen bond donor. In addition, the dichloroacetamide group folds back further over the phenyl ring to form an intramolecular C–Cl⋯π halogen bond. Two different halogen bonds are actually observed (each one with a different chlorine atom) resulting in two different stable conformers, that can be detected by FTIR spectroscopy due to the conformational sensitivity of the C[dbnd]O group to the conformation of the dichloroacetyl group. Finally, the stability of the conformers with the polarity of the medium is also discussed.Item Constitutive modelling and mechanical characterization of aluminium-based metal matrix composites produced by spark plasma sintering(2010-05) Bolzon, Gabriella; Chiarullo, Enzo J.; Egizabal, Pedro; Estournes, Claude; Tecnalia Research & InnovationSpark plasma sintering has been applied to the production of aluminium-based functionally graded material systems to be used in abrasive and high temperature conditions. The overall mechanical properties of these metal matrix composites were determined during the optimization phases of the production process by a fast and reliable identification procedure based on instrumented indentation, which can be easily performed on small specimens. The experimental information gathered from conical (Rockwell) indentation was used as input data for the calibration of the material parameters entering the elastic-plastic Drucker-Prager constitutive model. Eventually, the so identified material parameters were used to predict the result of pyramidal (Vickers) indentation, in order to validate the model selection and the output of the identification procedure. The good matching between modelling and experimental results for the different test configurations confirmed the soundness of the considered approach, especially evidenced on the light of the strong influence on the overall mechanical characteristics of the material microstructure and defectiveness resulting from the production process, which prevent the use of classical homogenization rules to evaluate the macroscopic material properties.Item Continuous quantitative risk management in smart grids using attack defense trees(2020-08-07) Rios, Erkuden; Rego, Angel; Iturbe, Eider; Higuero, Marivi; Larrucea, Xabier; CIBERSEC&DLT; Tecnalia Research & InnovationAlthough the risk assessment discipline has been studied from long ago as a means to support security investment decision-making, no holistic approach exists to continuously and quantitatively analyze cyber risks in scenarios where attacks and defenses may target different parts of Internet of Things (IoT)-based smart grid systems. In this paper, we propose a comprehensive methodology that enables informed decisions on security protection for smart grid systems by the continuous assessment of cyber risks. The solution is based on the use of attack defense trees modelled on the system and computation of the proposed risk attributes that enables an assessment of the system risks by propagating the risk attributes in the tree nodes. The method allows system risk sensitivity analyses to be performed with respect to different attack and defense scenarios, and optimizes security strategies with respect to risk minimization. The methodology proposes the use of standard security and privacy defense taxonomies from internationally recognized security control families, such as the NIST SP 800-53, which facilitates security certifications. Finally, the paper describes the validation of the methodology carried out in a real smart building energy efficiency application that combines multiple components deployed in cloud and IoT resources. The scenario demonstrates the feasibility of the method to not only perform initial quantitative estimations of system risks but also to continuously keep the risk assessment up to date according to the system conditions during operation.