Home GMV PitIA Deteção precoce de anomalias Inteligência Artificial na indústria Informação geral Manutenção operacional e preditiva Solução orientada para a manutenção preditiva de alto rendimento de instalações industriais e onde automatizamos o processo de deteção de anomalias no funcionamento mediante a gestão de variáveis em tempo real. Proposta tecnológica Sistema escalável e modular Facilidade de manejamento para operadores Desenvolvimento e manutenção simples de modelos Technology proposal Why GMV PitIA®? Adaptable to multiple domainsApplicable to various sectors, ranging from industrial processes to space systems.Based on actual operating dataIt models complex systems based on historical and operational data without disrupting the process.Explainability of ResultsIt helps identify the causes of abnormal operation and deviations from normal operating conditions.Designed to support decision-makingIntuitive interfaces and visualizations designed for operators and analysts.Flexible and scalable deploymentCompatible with cloud and on-premises environments and adaptable to different integration needs.A modular and configurable systemAn architecture based on independent components that facilitates adaptation to different use cases, the addition of new features, and integration with existing data sources and systems. Applicable sectors Use cases Space Anomaly detection in satellite telemetry Space missions continuously generate large volumes of telemetry. Detecting anomalous behavior in this data is essential for supporting operations teams, reducing false alarms, and anticipating potential system degradations.GMV PitIA® enables us to address this challenge by learning the normal behavior of multivariate systems and detecting significant deviations in telemetry data. In addition to generating alerts, the tool helps explain the source of the anomaly by indicating which parameters contribute most to the detected error. Characteristics To validate the solution, GMV PitIA® was applied to the ESA Anomaly Detection Benchmark, which is based on real, annotated data from European Space Agency missions. The objective was to compare GMV PitIA® against benchmark algorithms and demonstrate a methodology that can be applied in an operational setting. The rows in the table represent different approaches to anomaly detection, ranging from simple statistical methods, such as Global STD3/STD5, to machine learning models such as iForest, KNN, or Telemanom ESA. GMV PitIA® offers a solid balance between model performance, scalability, usability, and robustness compared to benchmark methods such as Global STD, iForest, KNN, and Telemanom ESA. It is particularly well-suited when the volume of telemetry data is high, tagged data is limited, and alerts must be explainable. Key benefits GMV PitIA® demonstrates its ability to transform large volumes of telemetry data into explainable and operationally useful alerts:Detection without labeled data: it learns the system's normal behavior without the need for prior examples of anomalies. Scalability in complex systems: it works with multiple telemetry channels and large volumes of data. Explainable Alerts: Identifies which parameters contribute most to each detected deviation. Ready for operation: it allows models to be updated periodically, with low computational requirements and easy integration into monitoring processes. Industry Prediction of critical variables in industrial processes In industrial settings, plant analyzers are essential for monitoring critical process variables. However, continued use may entail operating costs, maintenance requirements, frequent calibrations, and the risk of downtime due to failures.GMV PitIA® makes it possible to address this challenge using predictive models trained on historical operational data. The tool learns the relationship between process variables and generates real-time predictions, maintaining visibility on critical variables even during periods when the analyzer is turned off.The goal of this use case is to minimize the startup time of the plant analyzers by using predictions from GMV PitIA® while they are turned off. This reduces the use of the analyzer without losing control over critical process variables. Process The process is conceived as a continuous cycle: GMV PitIA® is initially trained using the analyzer's historical data. When the analyzer is turned off, the model provides predictions. When the analyzer is turned back on, the new actual data is used to retrain the model and reduce the prediction error.During power-off periods, GMV PitIA®acts as a virtual simulation of the analyzer, allowing the process to continue to be monitored. During operational periods, the system incorporates new real-time measurements to keep the model up to date and improve the accuracy of subsequent predictions.GMV PitIA®proved capable of predicting critical process variables with high accuracy based on historical operating data, while maintaining a reliable estimate during periods when the analyzer was shut down. The results confirm that it is feasible to significantly reduce the analyzer's startup time without compromising process control Key benefits GMV PitIA®helps optimize industrial operations by transforming historical and process data into useful predictions for decision-making:Reduced use of the analyzer: it reduces the time it needs to be turned on without losing visibility into critical variables. Continuous prediction: it maintains an estimate of the process when the analyzer is turned off. Updated model: it incorporates new real-world data collected during operating periods to improve accuracy. Increased plant availability: it reduces ongoing reliance on physical equipment that is prone to failure or requires maintenance. More proactive decisions: it facilitates data-driven operations, with information available even in the absence of direct measurements. Designed for different profiles Modeling and analysis: Data scientists can develop and maintain predictive models in an agile manner, leveraging available historical and operational data.Operation and supervision: Operators have access to displays, indicators, and alerts that allow them to understand the system's status, detect deviations, and take proactive action. Technical Resources and Documentation Información Brochure[Paper] Proceedings of the 2025 Conference on Big Data from Space (BiDS'25): https://dx.doi.org/10.2760/2119408[Paper] European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry: https://arxiv.org/abs/2406.17826 Contact form Nome * Correio eletrónico * Empresa Mensagem Quero receber comunicações comerciais por meios eletrónicos Trataremos os seus dados para gerir os pedidos ou as sugestões que nos envie. Quando for necessário para dar resposta à sua mensagem, em função do país ou área de interesse que nos indique, podemos comunicar os seus dados a outras empresas do Grupo GMV. Pode exercer os seus direitos de proteção de dados entrando em contacto com [email protected]. Mais informações na nossa Política de privacidade. * Campos obrigatórios Related news IndústriaCibersegurança News Incorporar a cibersegurança na cadeia de fornecimento num contexto industrial Mais notícias
