The monitoring of rotating machinery is an essential activity for asset management today. Due to the large amount of monitored equipment, analyzing all the collected signals/features becomes an arduous task, leading the specialist to rely often on general alarms, which in turn can compromise the accuracy of the diagnosis. In order to make monitoring more intelligent, several machine learning techniques have been proposed to reduce the dimension of the input data and also to analyze it. This paper, therefore, aims to compare the use of vibration features extracted based on machine learning models, expert domain, and other signal processing approaches for identifying bearing faults (anomalies) using machine learning (ML)—in addition to verifying the possibility of reducing the number of monitored features, and consequently the behavior of the model when working with reduced dimensionality of the input data. As vibration analysis is one of the predictive techniques that present better results in the monitoring of rotating machinery, vibration signals from an experimental bearing dataset were used. The proposed features were used as input to an unsupervised anomaly detection model (Isolation Forest) to identify bearing fault. Through the study, it is possible to verify how the ML model behaves in view of the different possibilities of input features used, and their influences on the final result in addition to the possibility of reducing the number of features that are usually monitored by reducing the dimension. In addition to increasing the accuracy of the model when extracting correct features for the application under study, the reduction in dimensionality allows the specialist to monitor in a compact way the various features collected on the equipment.
7 November 2020 in The International Journal of Advanced Manufacturing Technology
Anais do Congresso Internacional de Engenharia Mecânica e Industrial (978-65-5941-094-1) - Identificação Do Momento Ideal De Troca De Ferramentas De Corte Através Do Monitoramento Do Desgaste Por Sinal De Vibração E Inteligência Artificial
1 February 2020 in e-Journal of Nondestructive Testing
The Largest Portal of Nondestructive Testing (NDT) Open Access Archive, Conference Proceedings, Journal Articles, News, Products, Services. Professional Networking, Exhibition, Forums, Jobs
The quantification and hierarchization of noise sources in machines is essential for developing and building better projects. The independent component analysis methodology was applied to hermetic reciprocating compressors in this study to classify the main noise sources. Five methodologies are presented in the time and frequency domains, for which ERBM is better in the recovery of impulsive sources in the time domain and Jade stands out in the frequency domain for the recovery of harmonic sources. Compressor analysis is restricted to frequencies up to 1000 Hz due to signal synchronization and absence of shell vibrating modes. The effects of gas unbalance and pulsation are observed as the main sources, with the first being responsible for noise at frequencies close to 60 Hz, while pulsation is responsible for the 500 Hz bands.