Predictive analytics

Predictive analytics is a discipline that encompasses a wide range of techniques employed in the process of data analysis (“data mining”), including statistics and “machine learning”.

Together with visual analytics, predictive analytics aims to extract the knowledge implicit in data; obtaining from these relations and patterns hidden from an initial view, and facilitate their interpretation by the end user.

TEKNIKER develops analytics models based on multiple sources of information in order to monitor, diagnose and make predictions, taking into account the various stages within the process of data analysis known as data mining:

Acquisition, processing and storage of information

  • Integration of various devices (sensors, meters, mobile devices, web applications, etc.) and available information systems (both private and public)
  • Gathering existing information in both data format and from experiences and heuristics (expertise) about a specific domain (e.g. mechanical degradation, health index, energy anomalies, and so on).

Development of models

  • Development of models based on data and knowledge: KBS, Machine Learning (supervised and non-supervised; RRBB, NNs, SVM, etc.), semantic reasoning, chemometrics, analysis of reliability, statistics, rules, and so on.
  • Adjustment of the models for working in situations of uncertainty (knowledge based on the data gathered and which is either incomplete or of poor reliability).

The resulting models capture links between the different factors in order to facilitate the evaluation of risks and benefits associated with a particular set of conditions, and which can then be used to guide decision-taking.

Incorporation of the models into the final system:

  • Incorporation of the models into decision support systems (off-line) or into embedded software (on-line)
  • Analytical reasoning facilitated by visual interactive interfaces. Representation of information in a visual format, to enable greater interaction with and comprehension of the data when drawing conclusions and taking decisions.

Related contents

    • Array ( [id] => 24 [idcategoria] => 3 [idsubcategoria] => [imagen] => [caso_exito_1] => [caso_exito_2] => [caso_exito_3] => [cliente_1] => [cliente_2] => [cliente_3] => [direcciones_email] => consultasweb@tekniker.es [titulo] => Predictive analytics [video] => [texto_1] =>

    Predictive analytics is a discipline that encompasses a wide range of techniques employed in the process of data analysis (“data mining”), including statistics and “machine learning”.

    Together with visual analytics, predictive analytics aims to extract the knowledge implicit in data; obtaining from these relations and patterns hidden from an initial view, and facilitate their interpretation by the end user.

    [fase_1] => [fase_2] => [fase_3] => [fase_4] => [texto_2] =>

    TEKNIKER develops analytics models based on multiple sources of information in order to monitor, diagnose and make predictions, taking into account the various stages within the process of data analysis known as data mining:

    Acquisition, processing and storage of information

    • Integration of various devices (sensors, meters, mobile devices, web applications, etc.) and available information systems (both private and public)
    • Gathering existing information in both data format and from experiences and heuristics (expertise) about a specific domain (e.g. mechanical degradation, health index, energy anomalies, and so on).

    Development of models

    • Development of models based on data and knowledge: KBS, Machine Learning (supervised and non-supervised; RRBB, NNs, SVM, etc.), semantic reasoning, chemometrics, analysis of reliability, statistics, rules, and so on.
    • Adjustment of the models for working in situations of uncertainty (knowledge based on the data gathered and which is either incomplete or of poor reliability).

    The resulting models capture links between the different factors in order to facilitate the evaluation of risks and benefits associated with a particular set of conditions, and which can then be used to guide decision-taking.

    Incorporation of the models into the final system:

    • Incorporation of the models into decision support systems (off-line) or into embedded software (on-line)
    • Analytical reasoning facilitated by visual interactive interfaces. Representation of information in a visual format, to enable greater interaction with and comprehension of the data when drawing conclusions and taking decisions.
    [texto_tabla] => [enlace_flickr] => https://www.flickr.com/photos/teknikerik4/sets/72157650347715968/ [enlace_youtube] => https://www.youtube.com/user/Teknikertv [enlace_issuu] => [enlace_slideshare] => [seo_h1] => Predictive analytics [seo_url] => predictive-analytics [seo_title] => Predictive analytics - TEKNIKER [seo_desc] => TEKNIKER develops analytics models based on multiple sources of information in order to monitor, diagnose and make predictions. [imagenes] => [enlaces] => Array ( [0] => Array ( [imagen] => [titulo] => Planetic [texto_corto] => [enlace] => http://planetic.es/ [alt] => PLANETIC ) [1] => Array ( [imagen] => [titulo] => ARTEMIS [texto_corto] => [enlace] => http://www.artemis-ju.eu/home_page [alt] => ARTEMIS ) [2] => Array ( [imagen] => [titulo] => NESSI [texto_corto] => [enlace] => http://www.nessi-europe.eu/default.aspx?page=home [alt] => NESSI ) [3] => Array ( [imagen] => [titulo] => Center for Intelligent Maintenance Systems (IMS) [texto_corto] => [enlace] => http://www.imscenter.net/ [alt] => Center for Intelligent Maintenance Systems (IMS) ) ) [publicaciones] => Array ( [0] => Array ( [titulo] => AI-powered system for residential demand response [enlace] => an-ai-powered-system-for-residential-demand-response ) [1] => Array ( [titulo] => Contributions to time series analysis, modelling and forecasting to increase reliability in industrial environments [enlace] => time-series-analysis-to-increase-reliability-in-industrial-environments ) [2] => Array ( [titulo] => Advances in sovereign data sharing: identification and assessment of the main features of distributed usage control solutions and improvements in the policy quality [enlace] => advances-in-sovereign-data-sharing-identification-and-assessment-of-the-main-features-of-distributed-usage-control-solutions-and-improvements-in-the-policy-quality ) [3] => Array ( [titulo] => Sentiment Analysis Techniques for Positive Language Development [enlace] => sentiment-analysis-techniques-for-positive-language-development ) [4] => Array ( [titulo] => On the use of context information for an improved application of data-based algorithms in condition monitoring [enlace] => on-the-use-of-context-information-for-an-improved-application-of-data-based-algorithms-in-condition-monitoring ) [5] => Array ( [titulo] => Fault diagnosis and planning optimisation within an e-maintenance framework [enlace] => fault-diagnosis-and-planning-optimisation-within-an-e-maintenance-framework ) [6] => Array ( [titulo] => Optimizing E-Maintenance Through Intelligent Data Processing Systems [enlace] => optimizing-e-maintenance-through-intelligent-data-processing-systems ) [7] => Array ( [titulo] => Optimization of the multivariate calibration of a Vis-NIR sensor for the on-line monitoring of marine diesel engine lubricating oil by variable selection methods [enlace] => optimization-of-the-multivariate-calibration-of-a-vis-nir-sensor-for-the-on-line-monitoring-of-marine-diesel-engine-lubricating-oil-by-variable-selection-methods ) [8] => Array ( [titulo] => Health Monitoring for Electro-mechanical Nose Landing Gear Door Actuator of a UAV, Based on Simulation Modelling and Data-driven Techniques [enlace] => health-monitoring-for-electro-mechanical-nose-landing-gear-door-actuator-of-a-uav-based-on-simulation-modelling-and-data-driven-techniques ) [9] => Array ( [titulo] => A probabilistic model for cognitive-affective user state awareness [enlace] => a-probabilistic-model-for-cognitive-affective-user-state-awareness ) [10] => Array ( [titulo] => Chemometric methods applied to the optimization of calibration of VIS-NIR sensor systems for real time fluids monitoring [enlace] => chemometric-methods-applied-to-the-optimization-of-calibration-of-vis-nir-sensor-systems-for-real-time-fluids-monitoring ) [11] => Array ( [titulo] => Aportaciones para el diagnóstico y pronóstico en problemas industriales mediante técnica de Clasificación Supervisada [enlace] => aportaciones-para-el-diagnostico-y-pronostico-en-problemas-industriales-mediante-tecnica-de-clasificacion-supervisada ) [12] => Array ( [titulo] => Developments in Artificial Intelligence Technologies to Support Automation of Condition Monitoring Tasks [enlace] => developments-in-artificial-intelligence-technologies-to-support-automation-of-condition-monitoring-tasks ) ) [sectores] => Array ( [0] => Array ( [titulo] => Aeronautics and space [seo_url] => aeronautics-and-space [imagen] => aeronautica.svg ) [1] => Array ( [titulo] => Automotive [seo_url] => automotive [imagen] => automocion.svg ) [2] => Array ( [titulo] => Renewable energy [seo_url] => renewable-energy [imagen] => energias_renovables.svg ) [3] => Array ( [titulo] => Machine tools and manufacturing [seo_url] => machine-tools-and-manufacturing [imagen] => maquina_herramienta.svg ) ) [soluciones] => Array ( [0] => Array ( [titulo] => Automation and industrial robotics [seo_url] => automation-and-industrial-robotics [imagen] => ST_AutomatizacionRobotica_808x450px_icono.jpg ) [1] => Array ( [titulo] => Sensor devices [seo_url] => sensor-devices [imagen] => ST_DispositivosSensores_808x450px_icono.jpg ) [2] => Array ( [titulo] => Industrial maintenance [seo_url] => industrial-maintenance [imagen] => ST_MantenimientoIndustrial_808x450px_icono.jpg ) [3] => Array ( [titulo] => Mechatronic systems [seo_url] => mechatronic-systems [imagen] => ST_SistemasMecatronicos_808x450px_icono1.jpg ) ) [equipamiento] => Array ( [0] => Array ( [id] => 20 [titulo] => SpectraQuest Gearbox Prognostics Simulator (GPS) test bench [imagen] => Banco_Ensayo_Engranajes_Spectra_Quest_GPS.jpg [texto] =>
    CHARACTERISTICS OF THE EQUIPMENT
    • Test bench for counter-rotating motors
    • Range of velocity: 0 to 1500 rpm
    • Maximum radial torque: 50 Nm.
    • Maximum axial working load: 11734 N
    • Lubricant oil bath
    • Monitoring of torque exerted,vibrations, control of position/velocity (encoders), axial working load
    • Possibility of applying radial and axial loads
    • Possibility of dynamic variation of radial load and velocity

    EXPERTISE

    • Simulation of industrial gearboxes for maximising the number of configurations in all their elements
    • Degradation and component fault tests of different kinds (bearings, gears) under different operating conditions
    • Research into the dynamics of the gears and their acoustic behaviour, monitoring of conditions, diagnosis and prognosis (gears, bearings, etc.) by means of installed sensors (accelerometers, encoders, current, torque and force sensors)
    ) [1] => Array ( [id] => 21 [titulo] => FZG gearbox test bench [imagen] => Banco_Ensayo_Engranajes_FZG.jpg [texto] =>
    CHARACTERISTICS OF THE EQUIPMENT
    • Test bench for power re-circulating or Four Square gearbox
    • Distance between centres: 91.5 mm
    • Ranges of velocity: 100 to 3000 rpm (possibilities of 1:1 and 25:1 reduction)
    • Transmission ratio: 1:1.5
    • Maximum torque: 1000 Nm
    • Lubricant bath by spraying
    • Control and monitoring of the oil temperature 

    EXPERTISE

    • Characterisation of lubricants for gearboxes. Standard tests for scuffing, pitting, micropitting, etc. (DIN 51354-1/2, ISO 14635-1, ASTM D 4998, FVA 54/I-IV, etc.)
    • Characterisation of materials, surface treatment and gearbox geometry
    • Analysis of surface damage (surface wear and fatigue), transmission error, power losses, vibrations, noise, root tension, variation of temperature of the oil.
    ) ) )

Industrial sectors

Aeronautics and space

Automotive

Renewable energy

Machine tools and manufacturing