Operational Modes Detection in Industrial Gas Turbines Using an Ensemble of Clustering Methods.

Operational modes of a process are described by a number of relevant features that are indicative of the state of the process. Hundreds of sensors continuously collect data in industrial systems, which shows how the relationship between different variables changes over time and identifies different modes of operation. Gas turbines' operational modes are usually defined regarding their expected energy production, and most research works either are focused a priori on obtaining these modes solely based on one variable, the active load, or assume a fixed number of states and build up predictive models to classify new situations as belonging to the predefined operational modes. However, in this work, we take into account all available parameters based on sensors' data because other factors can influence the system status, leading to the identification of a priori unknown operational modes. Furthermore, for gas turbine management, a key issue is to detect these modes using a real-time monitoring system. Our approach is based on using unsupervised machine learning techniques, specifically an ensemble of clusters to discover consistent clusters, which group data into similar groups, and to generate in an automatic way their description. This description, upon interpretation by experts, becomes identified and characterized as operational modes of an industrial process without any kind of a priori bias of what should be the operational modes obtained. Our proposed methodology can discover and identify unknown operational modes through data-driven models. The methodology was tested in our case study with Siemens gas turbine data. From available sensors' data, clusters descriptions were obtained in an automatic way from aggregated clusters. They improved the quality of partitions tuning one consistency parameter and excluding outlier clusters by defining filtering thresholds. Finally, operational modes and/or sub-operational modes were identified with the interpretation of the clusters description by process experts, who evaluated the results very positively.

Condition Assessment of Industrial Gas Turbine Compressor Using a Drift Soft Sensor Based in Autoencoder.

Maintenance is the process of preserving the good condition of a system to ensure its reliability and availability to perform specific operations. The way maintenance is nowadays performed in industry is changing thanks to the increasing availability of data and condition assessment methods. Soft sensors have been widely used over last years to monitor industrial processes and to predict process variables that are difficult to measured. The main objective of this study is to monitor and evaluate the condition of the compressor in a particular industrial gas turbine by developing a soft sensor following an autoencoder architecture. The data used to monitor and analyze its condition were captured by several sensors located along the compressor for around five years. The condition assessment of an industrial gas turbine compressor reveals significant changes over time, as well as a drift in its performance. These results lead to a qualitative indicator of the compressor behavior in long-term performance.