TECNALIA Publications Repository :: Browsing by Keyword "Machine Learning"

Browsing by Keyword "Machine Learning"

Now showing 1 - 16 of 16

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; POWERTRAIN
With 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.
Combined model-based and machine learning approach for damage identification in bridge type structures
(2021) Fernández-Navamuel, Ana; Zamora-Sánchez, Diego; Armijo-Prieto, Alberto; Varona-Poncela, Tomás; García-Sánchez, David; García-Villena, Francisco; Ruiz-Cuenca, Francisco; E&I SEGURAS Y RESILIENTES; DIGITALIZACIÓN Y AUTOMATIZACIÓN DE LA CONSTRUCCIÓN; Tecnalia Research & Innovation
In this work, we propose a combined approach of model-based and machine learning techniques for damage identification in bridge structures. First, a finite element model is calibrated with real data from experimental vibration modes for the undamaged or baseline state. Second, generic synthetic damage scenarios based on modal parameters are automatically generated with the model to train machine learning algorithms for damage classification (Support Vector Machine, SVM) and damage location and quantification (Neural Network, NN). For an initial validation of the method we use a lab scale truss bridge model, proving that specific damage scenarios can be assessed by the Supervised Machine Learning algorithms trained with generic damage scenarios including a certain variability. The NN provides an assessment in terms of damage location and quantification, whereas the SVM provides a damage severity classification with graphical indication of the damage location and quantification through a reduced dimension plot.
Compounding process optimization for recycled materials using machine learning algorithms
(2022) Lopez-Garcia, Pedro; Barrenetxea, Xabier; García-Arrieta, Sonia; Sedano, Iñigo; Palenzuela, Luis; Usatorre, Luis; Tecnalia Research & Innovation; POLIMEROS; FACTORY; COMPOSITE
The sustainable manufacturing of goods is one of the factors to minimize natural resource depletion and CO2 emissions. In the last decade a big effort has been done to transition from linear economy to circular economy. This transition requires to implement re-manufacturing processes into the current industrial manufacturing framework, replacing the sourcing of raw materials by re-manufacturing technologies. However, this transition is very challenging since it requires the transformation of the companies and more specially their processes, from traditional to circular. To speed up this transformation, the use of tools provided by the 4th industrial revolution are crucial. In particular, the use of artificial intelligence techniques enables the optimization of the re-manufacturing processes and make those optimizations available to all the stakeholders. This paper presents an optimization system for re-manufacturing of recycled fiber through compounding processes with materials that come from composite waste or end of life of products. The proposed approach has been trained with the data collected from several experiments carried out with a compounding machine under different specifications, fiber reinforcement grades, and output material properties. The system will allow to set up a compounding machine for different types of reinforced plastics needless of setting point experiments. The algorithms have been tested with previously unseen scenarios and they have proved to be efficient for giving the optimal material characteristics.
Computational Intelligence in the hospitality industry: A systematic literature review and a prospect of challenges
(2021-04) Guerra-Montenegro, Juan; Sanchez-Medina, Javier; Laña, Ibai; Sanchez-Rodriguez, David; Alonso-Gonzalez, Itziar; Del Ser, Javier; IA
This research work presents a detailed survey about Computational Intelligence (CI) applied to various Hotel and Travel Industry areas. Currently, the hospitality industry's interest in data science is growing exponentially because of their expected margin of profit growth. In order to provide precise state of the art content, this survey analyzes more than 160 research works from which a detailed categorization and taxonomy have been produced. We have studied the different approaches on the various forecasting methods and subareas where CI is currently being used. This research work also shows an actual distribution of these research efforts in order to enhance the understanding of the reader about this topic and to highlight unexploited research niches. A set of guidelines and recommendations for future research areas and promising applications are also presented in a final section.
A computer-aided decision support system for shoulder pain pathology
(Springer Verlag, 2010) López de Ipiña, K.; Hernández, M. C.; Graña, M.; Martínez, E.; Vaquero, C.; Corchado, Emilio; Demazeau, Yves; Pawlewski, Pawel; Corchado, Juan M.; Julián, Vicente; Corchuelo, Rafael; Campbell, Andrew; Fernández-Riverola, Florentino; Dignum, Frank; Bajo, Javier; PRINTEX
A musculoskeletal disorder is a condition of the musculoskeletal system which consists in that part of it is injured continuously over time. Shoulder disorders are one of the most common musculoskeletal cases attended in primary health care services. Shoulder disorders cause pain and limit the ability to perform many routine activities and affect about 15-25% of the general population. Several clinical tests have been described to aid diagnosis of shoulder disorders. However, the current literature acknowledges a lack of concordance in clinical assessment, even among musculoskeletal specialists. In this work a Computer-Aided Decision Support (CADS) system for Shoulder Pain Pathology has been developed. The paper presents the medical method and the development of the database and the (CADS) system based on several classical classification paradigms improve by covariance estimation methods. Finally the system was evaluated by a medical specialist.
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
(2020-06) Barredo Arrieta, Alejandro; Díaz-Rodríguez, Natalia; Del Ser, Javier; Bennetot, Adrien; Tabik, Siham; Barbado, Alberto; Garcia, Salvador; Gil-Lopez, Sergio; Molina, Daniel; Benjamins, Richard; Chatila, Raja; Herrera, Francisco; Tecnalia Research & Innovation; IA
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.
Feature extraction-based prediction of tool wear of Inconel 718 in face turning
(2018-08) Murua, M.; Suárez, A.; López de Lacalle, L. N.; Santana, R.; Wretland, A.; FACTORY; FABRIC_INTEL
Tool wear is a recurring topic in the cutting field, so obtaining knowledge about the tool wear process and the capability of predicting tool wear is of special importance. Cutting processes can be optimised with predictive models that are able to forecast tool wear with a suitable level of accuracy. This research focuses on the application of some regression approaches, based on machine learning techniques, to a face-turning process for Inconel 718. To begin with, feature extraction of the cutting forces is considered, to generate regression models. Subsequently, the regression models are improved with a reduced set of features obtained by computing the feature importance. The results provide evidence that the gradient-boosting regressor allows an increment in the wear prediction accuracy and the random forest regressor has the capability of detecting relevant features that characterise the turning process. They also reveal higher accuracy in predicting tool wear under high-pressure cooling as opposed to conventional lubrication.
HUMANISE: Human-Inspired Smart Management, towards a Healthy and Safe Industrial Collaborative Robotics
(2023-02) Lopez-de-Ipina, Karmele; Iradi, Jon; Fernandez, Elsa; Calvo, Pilar M.; Salle, Damien; Poologaindran, Anujan; Villaverde, Ivan; Daelman, Paul; Sanchez, Emilio; Requejo, Catalina; Suckling, John; ROBOTICA_FLEX; Tecnalia Research & Innovation
The workplace is evolving towards scenarios where humans are acquiring a more active and dynamic role alongside increasingly intelligent machines. Moreover, the active population is ageing and consequently emerging risks could appear due to health disorders of workers, which requires intelligent intervention both for production management and workers’ support. In this sense, the innovative and smart systems oriented towards monitoring and regulating workers’ well-being will become essential. This work presents HUMANISE, a novel proposal of an intelligent system for risk management, oriented to workers suffering from disease conditions. The developed support system is based on Computer Vision, Machine Learning and Intelligent Agents. Results: The system was applied to a two-arm Cobot scenario during a Learning from Demonstration task for collaborative parts transportation, where risk management is critical. In this environment with a worker suffering from a mental disorder, safety is successfully controlled by means of human/robot coordination, and risk levels are managed through the integration of human/robot behaviour models and worker’s models based on the workplace model of the World Health Organization. The results show a promising real-time support tool to coordinate and monitoring these scenarios by integrating workers’ health information towards a successful risk management strategy for safe industrial Cobot environments.
MACHINE LEARNING-BASED ANALYSIS ENGINE TO IDENTIFY CRITICAL VARIABLES IN MULTI-STAGE PROCESSES: APPLICATION TO THE INSTALLATION OF BLIND FASTENERS
(2020-09) MURUA, MAIALEN; VEIGA SUAREZ, FERNANDO; ORTEGA LALMOLDA, JUAN ANTONIO; Penalva Oscoz, Mariluz; DIEZ OLIVAN, ALBERTO; Tecnalia Research & Innovation
Quality control in manufacturing is a recurrent topic as the ultimate goals are to produce high quality products with less cost. Mostly, the problems related to manufacturing processes are addressed focusing on the process itself putting aside other operations that belong to the part’s history. This research work presents a Machine Learning-based analysis engine for non-expert users which identifies relationships among variables throughout the manufacturing line. The developed tool was used to analyze the installation of blind fasteners in aeronautical structures, with the aim of identifying critical variables for the quality of the installed fastener, throughout the fastening and drilling stages. The results provide evidence that drilling stage affects to the fastening, especially to the formed head’s diameter. Also, the most critical phase in fastening, which is when the plastic deformation occurs, was identified. The results also revealed that the chosen process parameters, thickness of the plate and the faster type influence on the quality of the installed fastener.
Metal Forming Process Efficiency Improvement Based on AI Services
(Springer Science and Business Media Deutschland GmbH, 2024) Boto, Fernando; Cabello, Daniel; Ortega, Juan Antonio; Puigjaner, Blanca; Alonso, Asier; Wagner, Achim; Alexopoulos, Kosmas; Makris, Sotiris; FACTORY
In this work, the application of Artificial Intelligence (AI) and Machine Learning (ML) techniques in the field of metal forming processes in Shear Forming and Spinning machines are explored. The main objective is to improve the quality of the parts produced and the efficiency of these processes through the implementation of predictive models and online value-added services. Firstly, different methods for the analysis and evaluation of the quality of manufactured parts are presented. Additionally, predictive models for online failure detection are developed, based on historical and real-time data, which helps prevent failures and reduce production costs. Furthermore, the challenge of detecting changes in the input material, which can have a significant impact on process outcomes, is addressed. Lastly, the implementation of an algorithm towards “zero defects” is proposed to achieve optimal conditions in the metal forming process. The described approaches enable customers of the incremental forming machine manufacturer to access a diverse range of services associated with the implemented methods. ...
Neural Network Power Flow Approach to Detect Overload and Voltage Anomalies in Low-Voltage Unbalanced Networks, Agnostic of Network Topology
(IEEE Computer Society, 2024) González-Garrido, Amaia; Rivera, Jon Ander; Zaballa, Juan Florez; Rodríguez-Seco, Jose Emilio; Perea, Eugenio; POWER SYSTEMS; IA; DIGITAL ENERGY
The application of Power Flow (PF) algorithms at Low Voltage (LV) becomes essential, to ensure safe and cost-effective operation. Deterministic approaches do not appear suitable and scalable for LV networks, with a higher risk of non-convergence. The proposed Neural Network Power Flow model (NN-PF) provides accurate power loading, voltage magnitudes and angles in LV unbalanced network, based on nodal consumption and generation power, while being agnostic of the LV network model. Broader dataset is generated for training and testing purposes, including solar generation and undesired voltage events. Despite challenges posed by limited dataset size and the absence of the network topology and features, the NN-PF demonstrates robust performance and high accuracy to identify voltage anomalies and overloads in LV networks. The highest Mean Absolute Error (MAE) is 2e-4 p.u. (0.48 V), 4.6 kW active and 1.51 kVAr reactive power flow at extreme steady-state conditions (V < 0.95 p.u.).
On the design of a CADS for shoulder pain pathology
(2010) De Ipiña, K. López; Hernández, M. C.; Martínez, E.; Vaquero, C.; PRINTEX
A musculoskeletal disorder is a condition of the musculoskeletal system, which consists in part of it being injured continuously over time. Shoulder disorders are one of the most common musculoskeletal cases attended in primary health care services. Shoulder disorders cause pain and limit the ability to perform many routine activities, affecting about 15-25 % of the general population. Several clinical tests have been described to aid diagnosis of shoulder disorders. However, the current literature acknowledges a lack of concordance in clinical assessment, even among musculoskeletal specialists. We are working on the design of a Computer-Aided Decision Support (CADS) system for Shoulder Pain Pathology. The paper presents the results of our efforts to build a CADS system testing several classical classification paradigms, feature reduction methods (PCA) and K-means unsupervised clustering. The small database size imposes the use of robust covariance matrix estimation methods to improve the system performance. Finally, the system was evaluated by a medical specialist.
Randomization-based machine learning in renewable energy prediction problems: Critical literature review, new results and perspectives
(2022-03) Del Ser, J.; Casillas-Perez, D.; Cornejo-Bueno, L.; Prieto-Godino, L.; Sanz-Justo, J.; Casanova-Mateo, C.; Salcedo-Sanz, S.; IA
In the last few years, methods falling within the family of randomization-based machine learning models have grasped a great interest in the Artificial Intelligence community, mainly due to their excellent balance between performance in prediction problems and their computational efficiency. The use of these models for prediction problems related to renewable energy sources has been particularly notable in recent times, including different ways in which randomization is considered, their hybridization with other modeling techniques and/or their multi-layered (deep) and ensemble arrangement. This manuscript comprehensively reviews the most important features of randomization-based machine learning methods, and critically examines recent evidences of their application to renewable energy prediction problems, focusing on those related to solar, wind, marine/ocean and hydro-power renewable sources. Our study of the literature is complemented by an extensive experimental setup encompassing three real-world problems dealing with solar radiation prediction, wind speed prediction in wind farms and hydro-power energy. In all these problems randomization-based methods are reported to achieve a better predictive performance than their corresponding state-of-the-art solutions, while demanding a dramatically lower computational effort for its learning phases. Finally, we pause and reflect on important challenges faced by these methods when applied to renewable energy prediction problems, such as their intrinsic epistemic uncertainty, or the need for explainability. We also point out several research opportunities that arise from this vibrant research area.
Remaining useful life estimation of ball bearings by means of monotonic score calibration
(Institute of Electrical and Electronics Engineers Inc., 2015-06-16) Carino, J. A.; Zurita, D.; Delgado, M.; Ortega, J. A.; Romero-Troncoso, R. J.; FACTORY
The estimation of remaining useful life applied to industrial machinery and its components is one of the current trends in the advanced manufacturing field. In this context, this work presents a reliable methodology applied to ball bearings health monitoring. First, the proposed methodology analyses the available vibration and temperature data by means of the Spearman coefficient. This step allows the identification of the most significant monotonic relationship between features and the evolution of the remaining useful life. The method is complemented by means of the application of one-class support vector machine in order to obtain the remaining useful life indication trough the mapping of the classification scores. The proposed scheme shows a significant accuracy and reliability of the degradation detection due to the coherent management of the information. This fact is experimentally demonstrated by a run-to-failure test bench and the comparison with classical approaches.
A slag prediction model in an electric arc furnace process for special steel production
(2021) Murua, Maialen; Boto, Fernando; Anglada, Eva; Cabero, Jose Mari; Fernandez, Leixuri; FACTORY; Tecnalia Research & Innovation; CIRMETAL
In the steel industry, there are some parameters that are difficult to measure online due to technical difficulties. In these scenarios, soft-sensors, which are online tools that aim forecasting of certain variables, play an indispensable role for quality control. In this investigation, different soft sensors are developed to address the problem of predicting the slag quantity and composition in an electric arc furnace process. The results provide evidence that the models perform better for simulated data than for real data. They also reveal higher accuracy in predicting the composition of the slag than the measured quantity of the slag.
Towards Smarter Security Orchestration and Automatic Response for CPS and IoT
(IEEE Computer Society, 2023) Nguyen, Phu; Dautov, Rustem; Song, Hui; Rego, Angel; Iturbe, Eider; Rios, Erkuden; Sagasti, Diego; Nicolas, Gonzalo; Valdés, Valeria; Mallouli, Wissam; Cavalli, Ana; Ferry, Nicolas; CIBERSEC&DLT; VISUAL
Current security orchestration and response (SOAR) approaches have primarily focused on specific layers of systems, such as Intrusion Detection Systems, the network layer, or the application layer. We aim to find the gaps in the existing SOAR approaches for IoT/CPS-based systems, especially critical infrastructures, and propose some directions to fill in these gaps. This paper presents a literature survey and future research directions for advancing SOAR towards increased automation and more holistic operation, especially for the cyber-physical security of critical infrastructures. We have found 14 primary SOAR studies and discussed the gaps in general. There is a significant gap when it comes to a comprehensive and systematic approach to SOAR for multi-layered systems using IoT/CPS and considering the computing continuum perspective. To address the gap, we present our on-going work on a framework of multi-layer SOAR decision-making methods and orchestration tools that leverage Reinforcement Learning (RL)-based adaptation intelligence, virtual reality, avatar-human interaction and advanced Cyber Threat Intelligence (CTI) tools.

Browsing by Keyword "Machine Learning"

Results Per Page

Sort Options