A Review of Machinery Diagnostics and Prognostics Implemented on a Centrifugal Pump

McKee, Kristoffer K.; Forbes, Gareth L.; Mazhar, Ilyas; Entwistle, Rodney; Howard, Ian

doi:10.1007/978-1-4471-4993-4_52

Cited by 23 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An unscheduled shutdown of a centrifugal pump in continuous process plants causes a huge financial loss in terms of maintenance, cost, and downtime [7]. The maintenance cost distribution for the rotating machines at a petrochemical plant is shown in Figure 1 [8,9]. It has been observed that 70% of the maintenance cost is associated with the pump.…”

Section: Introductionmentioning

confidence: 99%

Design of a Novel Electric Diagnostic Technique for Fault Analysis of Centrifugal Pumps

2019

View full text Add to dashboard Cite

Centrifugal pumps are the fundamental components of most industries. They are used in almost every industry to transfer liquid through pipes. The breakdown of a pump causes heavy production losses, and hence, the development of an economical and user-friendly condition monitoring system is vital in order to estimate the health of a pump in a timely manner, and to avoid an unscheduled breakdown. The intrusive condition monitoring techniques (such as vibration analysis and acoustic emission) developed for the fault diagnosis of pumps utilize expensive vibration sensors, and these sensors need to be installed on the pump body for data collection. Non-intrusive techniques (such as motor current analysis) have been proven to be economical, but have limited capabilities for diagnosing the incipient faults in pumps operating in a noisy industrial environment. The electric diagnostic technique (EDT) proposed in this paper does not require the purchase of extra sensors, and instead utilizes the existing sensors, which are usually installed on the machines, to measure and display the motor line current and voltage. The EDT has been developed in the Laboratory Virtual Instrument Engineering Workbench (LabVIEW) so as to measure the three-phase line current, and then transform it into two-phase d–q currents. These d–q currents are plotted as patterns, and the statistical features of these patterns are used to segregate the centrifugal pump fault types. Detailed experiments and evaluations have been performed in order to check the viability of the developed EDT technique.

show abstract

Section: Introductionmentioning

confidence: 99%

Design of a Novel Electric Diagnostic Technique for Fault Analysis of Centrifugal Pumps

2019

View full text Add to dashboard Cite

show abstract

“…So far, several scholars have paid attention on condition motoring of centrifugal pump. McKee et al 1,2 introduced the fault modes of centrifugal pump, and reviewed the available diagnostic and prognostic methods on centrifugal pump. Compared to the operating conditions, such as current, voltage, vacuum gauge reading, and pressure gauge reading, vibration signals are widely applied in condition motoring of centrifugal pump.…”

Section: Introductionmentioning

confidence: 99%

Experimental investigation and multi-conditions identification method of centrifugal pump using Fisher discriminant ratio and support vector machine

Qiu

Huang

2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

For identifying the operation situations of centrifugal pumps by artificial intelligence, we performed an experiment on multi-flow conditions. The multi-flow conditions were simulated by adjusting an automatic flow-regulating valve installed on outlet pipe, and the vertical vibration signals of 20 flow points at the bearing house were collected by the test system. By time-domain analysis, frequency-domain analysis, information entropy, empirical modal decomposition, and wavelet packet decomposition methods, a comprehensive feature space was constructed. In addition, the optimal features were selected by Fisher discriminant ratio, and the dimensionality of the selected optimal features was reduced with principal component analysis. Finally, support vector machine algorithm was employed to identify the real-time flow condition, and the hyper-parameters of support vector machine classifier model were optimized by a grid search technique. Results show that the vibration test can effectively simulate the operation situation of centrifugal pumps under multi-flow conditions, and the proposed multi-flow conditions identification method has achieved a good identification performance.

show abstract

“…In the industrial processes, though strict regulations and stable operating conditions are required, even the most sophisticated machines cannot avoid the runtime exception [1]. Due to a large number of human interactions in the industrial manufacturing process, human errors may cause abnormalities in the overall process.…”

Section: Introductionmentioning

confidence: 99%

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

Yang

Song

et al. 2019

2019 IEEE International Conference on Power Data Science (ICPDS)

View full text Add to dashboard Cite

In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction. However, the traditional prediction models are fixed while the conditions of the machines change over time, thus making the errors of predictions increase with the lapse of time. In this paper, we propose a general data renewal model to deal with it. Combined with the similarity function and the loss function, it estimates the time of updating the existing prediction model, then updates it according to the evaluation function iteratively and adaptively. We have applied the data renewal model to two prediction algorithms. The experiments demonstrate that the data renewal model can effectively identify the changes of data, update and optimize the prediction model so as to improve the accuracy of prediction.

show abstract

A Review of Machinery Diagnostics and Prognostics Implemented on a Centrifugal Pump

Cited by 23 publications

References 38 publications

Design of a Novel Electric Diagnostic Technique for Fault Analysis of Centrifugal Pumps

Design of a Novel Electric Diagnostic Technique for Fault Analysis of Centrifugal Pumps

Experimental investigation and multi-conditions identification method of centrifugal pump using Fisher discriminant ratio and support vector machine

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

Contact Info

Product

Resources

About