Balancing of a rigid rotor using artificial neural network to predict the correction masses

Abstract

ABSTRACT. This paper deals with an analytical model of a rigid rotor supported by hydrodynamic journal bearings where the plane separation technique together with the Artificial Neural Network (ANN) is used to predict the location and magnitude of the correction masses for balancing the rotor bearing system. The rotating system is modeled by applying the rigid shaft Stodola-Green model, in which the shaft gyroscopic moments and rotatory inertia are accounted for, in conjunction with the hydrodynamic cylindrical journal bearing model based on the classical Reynolds equation. A linearized perturbation procedure is employed to render the lubrication equations from the Reynolds equation, which allows predicting the eight linear force coefficients associated with the bearing direct and cross-coupled stiffness and damping coefficients. The results show that the methodology presented is efficient for balancing rotor systems. This paper gives a step further in the monitoring process, since Artificial Neural Network is normally used to predict, not to correct the mass unbalance. The procedure presented can be used in turbo machinery industry to balance rotating machinery that require continuous inspections. Some simulated results will be used in order to clarify the methodology presented.Key words: rigid balancing, rotor balancing, artificial neural network.RESUMO. Balanceamento de um rotor rígido, usando redes neurais artificiais para a predição das massas de correção. Este trabalho foi desenvolvido com o objetivo de empregar a técnica de balanceamento de separação de planos juntamente com Redes Neurais Artificiais (RNA) para a predição da localização e massas de correção para o balanceamento de um sistema rotor-mancal, para tal, foi empregado um modelo analítico consitituído por um rotor rígido apoiado em mancais hidrodinâmicos. O sistema rotativo foi modelado com base no modelo de eixo rígidos de Stodola-Green, no qual foram considerados o efeito girocópico e a inércia rotatória, além de um modelo de mancal hidrodinâmico cilíndrico baseado nas equações de Reynolds que permitiu a determinação de oito coeficientes lineares de força associados com os coeficientes de rigidez e amortecimento diretos e cruzados do mancal. Os resultados mostraram que a metodologia apresentada foi eficiente para o balanceamento de rotores. Este trabalho fornece grande contribuição para o processo de monitoramento, uma vez que Redes Neurais Artificiais normalmente são empregadas para identificação, e não para a correção do desbalanceamento. O procedimento apresentado pode ser empregado no balanceamento de turbomáquinas industriais, as quais necessitam de contínuas avaliações. Resultados simulados são apresentados com o objetivo de ilustrar metodologia de balanceamento proposta.Palavras-chave: balanceamento rígido, balanceamento, redes neurais artificiais.

Unbalance Localization of a Multi-Disc Rotor by Hybridizing Wavelet Transformation and Neural Network

“…The correctness of the proposed DWANN model compared to the earliest model presented Walker et al (2014) is a little higher thought current DWANN model can predict the radius and the mass value of the unbalance with adequate accuracy. As specified in the literature survey, in the active rotor balancing [30,31] detecting the location of the unbalance mass with proper accuracy and online output is very advantageous (Beltran-Carbajal and Silva-Navarro,2013; Cupial and Koziol, 2013). This accomplished DWANN model can be employed in this aim.…”

Unbalance Rotor Parameters Detection Based on Artificial Neural Network

“…31,32 This achieved ANN model can be applied in this aim. Most of the former established ANN models generally were created for fault classification, [24][25][26][27][28][29] but some of them were employed to identify unbalance parameters. 30,33…”

“…26 In addition, the number of the systems equipped by a hybrid of ANN and fuzzy systems have been used to detect unbalance in the rotary system, 28 to classify faults of the turbo generators, 28 and to approximate the correction masses value for the balancing rotor. 29 The integration of ANN with Wavelet, Possibility Theory, and Taguchi were tried in rotary system diagnosis. [38][39][40] The unbalance localization via ANN was developed for a multi-disc rotor.…”

Analysis of fat mass value, clinical and metabolic data and interleukin-6 in HIV-positive males using regression analyses and artificial neural network

“…On the other hand, engineering approach has been considered and studied extensively as an alternative prognostic method in health management field. Among its adaptive mathematical methods used is the Artificial Neural Network (ANN), a data processing model mapped according to brain behavioural system and act as prediction tool with complex pattern model (Santos, Duarte, Faria, & Eduardo, 2009). The main reasons are it can mimic non-linear relationships, handle adaptive learning, pattern recognition and classification, attributes regarded as important in building medical predictive models.…”