Data-Driven Prognostics of Alternating Current Solenoid Valves

Mazaev, Ganjour; Ompusunggu, Agusmian Partogi; Tod, Georges; Crevecoeur, Guillaume; Hoecke, Sofie Van

doi:10.1109/phm-besancon49106.2020.00024

Cited by 8 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The regions where local minima and maxima were extracted from, were chosen based on where the largest deviation was visible when comparing the signals of a device in a healthy state and one in a defective state (State 0 vs State 2 in Fig 2 ). The process of extracting features from locations within the data where the largest changes occur throughout the lifetime of a device, was inspired by the work of Mazaev et al (2020) [16] . In a similar way, nine more features were extracted from the raw data to form one feature vector, or sample.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Data driven health monitoring of Peltier modules using machine-learning-methods

Cotorogea¹,

Marino²,

Vogl³

2022

SLAS Technology

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

“…Lastly and even though it was known that they were related to the PWM signal, voltage, and current readings (bottom graph in Fig 2 ) of the Peltier Modules were also regarded. [16)]. In a similar way, nine more features were extracted from the raw data to form one feature vector, or sample.…”

Section: Data Acquisition and Labelingmentioning

confidence: 99%

Data driven health monitoring of Peltier modules using machine-learning-methods

Cotorogea¹,

Marino²,

Vogl³

2022

SLAS Technology

View full text Add to dashboard Cite

“…Sarwar et al [22] developed an algorithm for fault isolation and diagnosis of high pressure fuel pump SVs using current feedback. Mazaev et al [23] proposed data-driven RUL prediction approaches using shallow feature-based approaches and an ensemble of CNNs to construct a health index of SVs, which are used to extrapolate RUL. This work directly compares the performance of the presented methodology with these results.…”

Section: B Solenoid Valvesmentioning

confidence: 99%

“…These metrics serve as an indication of the overall performance of the proposed CNN models for the RUL prediction task. The CNN models are compared with the deep and shallow learning methods used in [23]. In this work, health indices are computed up to 70% degradation, after which these health indices are extrapolated in order to compute the RUL.…”

Section: A Rul Predictionmentioning

confidence: 99%

Bayesian Convolutional Neural Networks for Remaining Useful Life Prognostics of Solenoid Valves With Uncertainty Estimations

Mazaev

Crevecoeur

Hoecke

2021

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Solenoid valves are essential components of industrial systems and therefore widely used. As they suffer from high failure rates in the field, fault prognosis of these assets plays a major role for improving their maintenance and reliability. In this work, Bayesian convolutional neural networks are used to predict the remaining useful life (RUL) of solenoid valves, by training them on the valve's current signatures. Predictive performance is further improved upon by using salient physical features obtained from an electromechanical model as the network's training input. Results show that our designed network architecture produces well-calibrated uncertainty estimations of the RUL predictive distributions, which is an important concern in prognostic decision-making. I. INTRODUCTIONT HE purpose of Prognostics and Health Management (PHM) is to enable optimal maintenance strategies, as to prevent machine failure, extend the lifetime of machines and reduce operational costs. This is achieved by detecting incipient faults, fault isolation, identification of different fault types (fault diagnostics) and fault prognosis. These techniques typically imply the analysis of healthy and/or faulty conditions indicated by process measurements.Two main approaches exist for estimating the remaining useful life (RUL). Physics-based approaches rely on physical domain knowledge, which describe normal operation and physical degradation laws. Data-driven approaches are based on condition monitoring data, which are used for constructing statistical or machine learning models [1]. The term "hybrid approaches" is commonly used for approaches that combine physics-based and data-driven techniques.Deep learning (DL) techniques are an important subcategory of data-driven approaches. Features are learned automatically at multiple levels of feature representations, which allows DL to learn complex relations mapping the input to the output directly. This contrasts DL with feature-based approaches such as decision tree ensembles or Gaussian process regression, which rely on the construction of features [2]. DL is T.

show abstract

“…With the rise of data-driven methods such as machine learning, this is a more direct and effective method to establish the model by using experimental data for solenoid valve system. Mazaev et al (2020) trained the deep neural network through experimental data, and obtained the remaining service life prediction model of solenoid valve. They used adaNET algorithm based on TensorFlow, which is opensource from Google.…”

Section: Introductionmentioning

confidence: 99%

Experimental and numerical validation of a proportional solenoid valve based on the data-driven model

Jiang

Ren

et al. 2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

Solenoid valves are widely used in mechatronics, robotic systems and industrial occasions. An accurate model is very important for the design and control of a solenoid valve. The dynamical model of the solenoid valve is difficult to obtain due to the complexity of the structure and the interaction of multiple physical fields. This paper proposes two kinds of model of solenoid valve: grey box model and black box model, on the basis of experimental data. ARX model is selected as the basic structure of the grey box model. After clustering the data with the fuzzy c-means algorithm, the overall experimental data is divided into several local linear sub-models, and the model coefficients of the local linear model are obtained by partial least square regression. The overall expression of the model is obtained by combining the local sub-models with membership degree. For the black box model, support vector regression algorithm is used to identify. On the basis of selecting the appropriate parameters, we obtain the black box model of solenoid valve based on data. For the above two models, we carry out experimental verification and error analysis, and compare with the traditional modelling method. According to the results, it can be seen that on the basis of the experimental data, using the data-driven method to construct the model has many advantages, avoiding complex physical analysis, and has high accuracy. The model with high precision will be used in the accurate control and observing estimation of the solenoid valve.

show abstract

Data-Driven Prognostics of Alternating Current Solenoid Valves

Cited by 8 publications

References 12 publications

Data driven health monitoring of Peltier modules using machine-learning-methods

Data driven health monitoring of Peltier modules using machine-learning-methods

Bayesian Convolutional Neural Networks for Remaining Useful Life Prognostics of Solenoid Valves With Uncertainty Estimations

Experimental and numerical validation of a proportional solenoid valve based on the data-driven model

Contact Info

Product

Resources

About