Online (Remote) Teaching for Laboratory Based Courses Using “digital Twins” of the Experiments

Covid-19 pandemic has introduced radical changes to the engineering education so that most of the teaching moved to the off-campus setting of online classes. However, conducting the laboratory classes, a fundamental part of engineering education has remained to be a challenge. To address to this situation, an ambitious approach is taken to re-establish the laboratory experience entirely online with the help of digital twins of the laboratory experiments. Laboratory based undergraduate courses are important parts of the curriculum at the Lucerne University of Applied Sciences (HSLU), Switzerland. During the Covid-19 pandemic, it was necessary to adapt to the new environment of remote learning and modify the laboratory experiments so that they can be carried out online. The approach was to develop digital twins of each laboratory experiment with web applications and to provide an environment together with supporting videos and interactive problems so that the laboratory experiments can be carried out remotely. This paper explains the development of the digital twins of the laboratory experiments and provides information about the selected experiments such as potential vortex, linear momentum equation, diffuser flow, radial compressor, fuel cell, and pump test rig. A remote or distance learning has many hurdles, a major one being how to teach hands-on laboratory courses outside of an actual laboratory. The experience at the HSLU showed that teaching online laboratories using the digital twins of the experiments can work and the students can take part in remote laboratories that meet the learning objectives.

Cavitation Analysis in Centrifugal Pumps Based on Vibration Bispectrum and Transfer Learning

Detection of cavitation in centrifugal pumps is critical in their condition monitoring. In order to detect cavitation more accurately and confidently, more advanced signal processing techniques are needed. For the classification of a pump conditions based on the outputs of these techniques, advanced machine learning techniques are needed. In this research, an automatic system for cavitation detection is proposed based on machine learning. Bispectral analysis is used for analyzing the vibration signals. The resulting bispectrum images are given to convolutional neural networks (CNNs) as inputs. The CNNs are a pretrained AlexNet and a pretrained GoogleNet, which are used in this application through transfer learning. On the contrary, a laboratory test setup is used for generating controlled cavitation in a centrifugal pump. The suggested algorithm is implemented on the vibration dataset acquired from the laboratory pump test setup. The results show that the cavitation state of the pump can be detected accurately using this system without any need to image processing or feature extraction.

Fault Prediction of Centrifugal Pump Based on Improved KNN

To effectively predict the faults of centrifugal pumps, the idea of machine learning k-nearest neighbor algorithm (KNN) was introduced into the traditional Mahalanobis distance fault discrimination, and an improved centrifugal pump fault prediction model of KNN based on the Mahalanobis distance is proposed. In this method, the Mahalanobis distance is used to replace the distance function in the conventional KNN algorithm. Grid search and cross-validation are used to determine the optimal K value of the prediction model. A centrifugal pump test rig was established to solve three common faults of centrifugal pumps: cavitation, impeller damage, and machine seal damage, and the method was verified. The results show that this method can effectively distinguish the specific fault types of centrifugal pumps based on vibration signals, and the fault prediction accuracy of the off-balance condition is up to 82%. This study provides a novel idea and method for centrifugal pump fault prediction and diagnosis and avoids the interaction between parameters when monitoring multiple parameters.

The Thiem team – Adolf and Günther Thiem, two forefathers of hydrogeology

Adolf and Günther Thiem, father and son, left behind a methodological legacy that many current hydrogeologists are probably unaware of. It goes much beyond the Dupuit-Thiem analytical model for pump test analysis, which is connected to their name. Methods, which we use on a day-to-day basis today, such as isopotential maps, tracer tests and vertical wells were amongst the many contributions which the Thiems either developed or improved. Remarkably, this was not done in a university context but rather as a by-product of their practical work designing and building water supply schemes in countries all over Europe. Some of these water works are still active. Both Thiems were also great science communicators. Their contributions were read and applied in many countries, especially in the US, through a personal connection between Günther and O.E. Meinzer, the leading USGS hydrogeologist of the time.

PyTheis—A Python Tool for Analyzing Pump Test Data

The Theis equation is an important mathematical model used for analyzing drawdown data obtained from pumping tests to estimate aquifer parameters. Since the Theis model is a nonlinear equation, a complex graphical procedure is employed for fitting this equation to pump test data. This graphical method was originally proposed by Theis in the late 1930s, and since then, all the groundwater textbooks have included this fitting method. Over the past 90 years, every groundwater hydrologist has been trained to use this tedious procedure for estimating the values of aquifer transmissivity (T) and storage coefficient (S). Unfortunately, this mechanical procedure does not provide any intuition for understanding the inherent limitations in this manual fitting procedure. Furthermore, it does not provide an estimate for the parameter error. In this study, we employ the public domain coding platform Python to develop a script, namely, PyTheis, which can be used to simultaneously evaluate T and S values, and the error associated with these two parameters. We solve nine test problems to demonstrate the robustness of the Python script. The test problems include several published case studies that use real field data. Our tests show that the proposed Python script can efficiently solve a variety of pump test problems. The code can also be easily adapted to solve other hydrological problems that require nonlinear curve fitting routines.

Influences of eccentricity ratio on the internal flow and cavitation characteristics of progressing cavity pump

A Progressing Cavity Pump (PCP) works by forming a progressive seal cavity through the eccentric rotation of rotor. PCP parameters, such as eccentricity ratio [Formula: see text], can influence its performance and cavitation characteristics. The internal correlation among clearance fluid, cavitation characteristics, and pump performance should be explored to reveal the variation laws of internal flow and cavitation characteristics in PCP under different [Formula: see text]. In this study, a contrast analysis on external characteristics (e.g. volume efficiency) of pump with different eccentricity ratios was carried out by combining an RNG [Formula: see text] turbulence model based on Singhal full-cavitation model and the model pump test method. Moreover, gas volume distribution of PCP was analyzed and the optimal value range of eccentricity ratio was proposed. Results demonstrate that the axial force and axial power of PCP basically remain the same, volume efficiency increases, and cavitation performance decreases with the increase of [Formula: see text], and the optimal value for [Formula: see text] ranges from 0.17 to 0.24. In addition, a revised NPSHQ is proposed to quantify the cavitation characteristics of PCP.

Experiment and simulation about the effect of wear-ring abrasion on the performance of a marine centrifugal pump

The wear-ring abrasion can cause performance degradation of the marine centrifugal pump. In order to study the effect of front and back wear-ring clearance on a pump, test and numerical simulation were used to investigate the performance change of a pump. The test results show that the head and efficiency of pump decrease by 3.56% and 9.62% respectively at 1.0 Qd due to the wear-ring abrasion. Under 1.0 Qd, with the increase of the front wear-ring the vibration velocity at pump foot increases from 0.4 mm/s to 1.0 mm/s. The axis passing frequency (APF) at the measuring points increases significantly and there appears new characteristic frequency of 3APF and 4APF. The numerical simulation results show that the front wear-ring abrasion affects the flow at the inlet of the front chamber of the pump and impeller passage. And the back wear-ring abrasion has obvious effect on the flow in the back chamber of the pump and impeller passage, while the multi-malfunction of the front wear-ring abrasion and back wear-ring abrasion has the most obvious effect on the flow velocity and flow stability inside pump. The pressure pulsation at Blade Passing Frequency (BPF) of the three schemes all decrease with the increase of the clearance.