Session: 20-05 Operation and testing in Oil and Gas Applications

Submission Number: 176273

Compressor Fleet Diagnostics by Employing MLP-Generated Heatmaps 

Reciprocating compressors are renowned for their versatility and widespread application across various installations. Ensuring their reliable operation is paramount, as failures can lead to costly unscheduled downtimes, safety hazards, and significant production losses. Consequently, the identification of both healthy and faulty operating conditions is essential. This study addresses this challenge by means of the integration of multi-layer perceptron (MLP) models for cross-regression analysis combined with heatmap visualization.

In this study, we propose a comprehensive framework that initiates with MLP training, with seemingly healthy data, targeting feature regression of acceleration, velocity, and fast Fourier transform (FFT) datasets. This is followed by the visualization of discrepancies between model predictions and ground truth data in the form of heatmaps, thus facilitating the identification of both the magnitude and location of these discrepancies. The methodology is systematically applied across various datasets with different time frame lengths to evaluate its effectiveness for a fleet of compressors.

The framework is applied to field data from three reciprocating compressors of the same product family, characterized by different architectures. One of the three compressors is also located on a different site. The data covers more than two years in total, encompassing variables that range from crank angle degrees, i.e., acceleration and velocity, to frequency domain representations, i.e., FFT data.

The results demonstrate the efficacy of the proposed framework in detecting faulty operation across both the frequency and crank angle degree domains. Additionally, the methodology proves capable of the reliable identification of the faulty data.

Presenting Author: Carlo Antonio Caputo University of Ferrara

Presenting Author Biography: Carlo Antonio Caputo earned his BSc and MSc in Mechanical Engineering at the University of Ferrara (Italy). He then took part in a one-year double-degree program at Cranfield University (UK), where he received his MSc in Thermal Power and Propulsion. Afterwards, Mr. Caputo began his PhD at his alma mater, the University of Ferrara, focusing on energy systems and turbomachinery diagnostics and prognostics by means of machine learning (ML) and artificial intelligence (AI) tools.

Authors:

Carlo Antonio Caputo University of Ferrara
Mauro Venturini University of Ferrara
Lucrezia Manservigi University of Ferrara
Michael Schulze Siemens Energy
Giovanni Bechini Siemens Energy