Effective Condition Monitoring System Research Articles

Digital twin-driven vibration amplitude simulation for condition monitoring of axial blowers in blast furnace ironmaking

ABSTRACT Long-term reliable condition monitoring (CM) of blast furnace blowers is essential to avoid catastrophic failure. Due to variable working conditions, the predefined thresholds in current CM systems influence the accuracy of the monitoring process and can lead to misdiagnoses. In order to overcome this limitation, we propose a digital twin (DT)-based scheme to monitor vibrations found in blowers. Factors believed to impact the distribution of vibration amplitudes are analysed using data collected from a constant speed axial blower operating in an industrial commercial environment and, based on which, a machine learning-based adaptive amplitude simulation model is developed on our on-site private cloud computing platform. Outcomes reveal that different guide vane openings in the manufacturing process can cause changes in amplitudes. By integrating the newly-arriving sensor data, vibration amplitudes can be more accurately predicted in the virtual space. The gap between the simulated and actual value narrowed from ±5 µm to within ±3 µm, from which a dynamic threshold can be defined. The resulting DT model, coupled with the on-site private cloud computing platform, which alleviates the shortage of computational and storage capacity in steel plants, allows for a much more effective CM system.

Comparison of Data Sources for Robot Gear Condition Monitoring

Industrial robot gear condition monitoring has the potential to increase the productivity of highly automated production lines. In order to implement an effective condition monitoring system, data must be collected which correlates with the robot gear’s state of health. The sensor choice and the characteristics of these sensors are crucial to the success of a condition monitoring system. Hence, we compare current and vibration sensor data from different accelerated robot gear wear tests in different frequency ranges to determine a suitable sensor setup. In the presented experiments, both data sources detect faults at a similar point in time and the variation of the frequency ranges has different effects on the data quality.

A Hybrid Chatter Detection Method Based on WPD, SSA, and SVM-PSO

As a kind of self-excited vibrations, chatter vibration is extremely common in end milling, especially in high-speed cutting processes. It affects the machining accuracy of products and decreases the processing efficiency of machine tools. Thus it is very crucial to develop an effective condition monitoring system to extract the chatter feature before chatter vibration grows. In this paper, a hybrid chatter detection method (HCDM) is proposed for chatter feature extraction and classification in end milling. Firstly, wavelet packet decomposition is employed to decompose cutting vibration signals into a series of wavelet coefficients, and the signals of each frequency band are reconstructed. Secondly, fast Fourier transform and singular spectrum analysis are chosen to obtain the chatter features. Furthermore, the support vector machine model is optimized by particle swarm optimization to recognize the cutting states in end milling. At last, cutting experiments of 300 M steel under different machining conditions are conducted, and the results indicate that the proposed HCDM can distinguish the stable, transition, and chatter states accurately and rapidly in end milling.

Fault Detection of a Spherical Tank Using a Genetic Algorithm-Based Hybrid Feature Pool and k-Nearest Neighbor Algorithm

Fault detection in metallic structures requires a detailed and discriminative feature pool creation mechanism to develop an effective condition monitoring system. Traditional fault detection methods incorporate handcrafted features either from the time, frequency or time-frequency domains. To explore the salient information provided by the acoustic emission (AE) signals, a hybrid of feature pool creation and an optimal features subset selection mechanism is proposed for crack detection in a spherical tank. The optimal hybrid feature pool creation process is composed of two major parts: (1) extraction of statistical features from time and frequency domains, as well as extraction of traditional features associated with the AE signals; and (2) genetic algorithm (GA)-based optimal features subset selection. The optimal features subset is then provided to the k-nearest neighbor (k-NN) classifier to distinguish between normal (NC) and crack conditions (CC). Experimental results show that the proposed approach yields an average 99.8% accuracy for heath state classification. To validate the effectiveness of the proposed approach, it is compared to conventional non-linear dimensionality reduction techniques, as well as those without feature selection schemes. Experimental results show that the proposed approach outperforms conventional non-linear dimensionality reduction techniques, achieving at least 2.55% higher classification accuracy.

Non-contact sensor placement strategy for condition monitoring of rotating machine-elements

Careful selection and location of sensors are of key importance in the construction and implementation of an effective condition monitoring system. There is a continual call for depletion of maintenance and operational costs of rotating machine elements. Health monitoring of bearings, which is regarded as a crucial component of rotating machinery, is expected to facilitate in the preclusion of machine breakdown and ensure the machine availability by maintenance actions in time. The effectiveness and reliability of measurement approaches for monitoring the condition of the bearing are influenced by both the signal processing techniques and locations of the sensors selected for fault characteristic extraction. This paper proposes a low cost Non-contact optimal sensor placement (NC-OSP) methodology in order to get information of high quality related to the dynamic features of the machines. Experiments were conducted using different bearing conditions under different operating conditions and sensor placement positions. Mathematical models have been proposed based on the response parameters and input variables experimentation using response surface methodology. Results indicate that the most effective input variable to control the response parameters viz. FFT vibration amplitude of characteristic frequency and RMS value of time domain was the shaft speed followed by load and angle of incidence. The responses proposed by the optimal models have been observed at 8° angle of incidence with maximum load and speed. The optimal outcomes have been validated experimentally which proved that the predicted results were in sync with the actual ones. The proposed work has significant potential in industrial environment with complex systems, where the condition monitoring approach with proper placement of sensors can play an important role.

Wind Turbine Fault Detection and Identification Through PCA-Based Optimal Variable Selection

An effective condition monitoring system of wind turbines generally requires installation of a high number of sensors and use of a high sampling frequency in particular for monitoring of the electrical components within a turbine, resulting in a large amount of data. This can become a burden for condition monitoring and fault detection systems. This paper aims to develop algorithms that will allow a reduced dataset to be used in wind turbine fault detection. This paper first proposes a variable selection algorithm based on principal component analysis with multiple selection criteria in order to select a set of variables to target fault signals while still preserving the variation of data in the original dataset. With the selected variables, this paper then describes fault detection and identification algorithms, which can identify faults, determine the corresponding time and location where the fault occurs, and estimate its severity. The proposed algorithms are evaluated with simulation data from PSCAD/EMTDC, Supervisory control and data acquisition data from an operational wind farm, and experimental data from a wind turbine test rig. Results show that the proposed methods can select a reduced set of variables with minimal information lost whilst detecting faults efficiently and effectively.

Analysis of Partial Discharge Signal Characteristics of Nano-Mineral Oil for Transformer Condition Monitoring Applications

Transformer is an expensive and key component in an electric power transmission network. Most of the failure of transformer occurs due to degradation of insulation oil, which further leads to major economical losses and power shutdown. Advancements in nanotechnology has given horizons for the development of nanofluids for transformer insulation applications. Understanding the enhancements in dielectric properties of nanofiller added mineral oil is a hot research area. In recent times, partial discharge (PD) detection and analysis is a well recognized insulation condition monitoring technique for transformers. However, reports on PD signal characteristics of nano filler added mineral oil is scanty. This paper attempts to investigate the PD characteristics of SiO2 nanofiller added mineral oil at different %wt concentrations of nanofiller material. Major PD source normally experienced in transformers i.e. corona discharge due to non-uniform electric field was simulated in the laboratory using needle-plane electrode configuration and the corresponding PD signals were measured using wide band PD detection system. Important PD characteristics such as inception voltage, stable PD formation voltage, PD amplitude with respect to increase in voltage stress and PD signal frequency spectrum were evaluated. Results clearly show that addition of SiO2 nanofiller material in the base mineral oil enhances PD performance of mineral oil and these results will be useful for electrical utilities for developing effective condition monitoring system for transformers.

Circuit breaker condition assessment through a fuzzy‐probabilistic analysis of actuating coil's current

Circuit breaker (CB) is a component providing significant electrical protection for power transmission and distribution systems. Hence, an effective condition monitoring system for the CBs is of imminent importance. This study presents a fuzzy-probabilistic-based condition assessment algorithm to assess the CB operation performance by monitoring its trip/close coil current (C.C.), and suggests a simple yet effective condition assessment tool. The C.C. patterns are acquired by measurements carried out on 60 CBs (72.5 kV, SF6) under faulty and normal conditions. To intelligently assess the CB's operating state (i.e. normal, alarm and emergency), in terms of its reliability, the optimum C.C. features with minimum interdependence were obtained. Furthermore, a fuzzy-probabilistic method is proposed based on the results of the statistical analyses of the features. The feasibility and applicability of the proposed method in CB condition assessment is verified against the experimental measured data.

Optimising Sensor Location for an Enhanced Gearbox Condition Monitoring System

Sensors location plays an important role in designing an effective condition monitoring system. Stability and reliability of information captured entirely depends on sensor location. The aim of this research is to investigate the relationship between sensor location and detecting the fault in a gearbox system. This paper proposes a methodology for locating indirect monitoring sensors such as acoustic emission and vibration on a gearbox system to obtain high quality information regarding the behaviour of machine conditions. Experimental work is designed to evaluate the optimum sensors' position for detecting faults in the gearbox system. The gearbox is operated under healthy and unhealthy conditions with varying levels of effective speed and load using full factorial experimental design method. The spectral kurtosis has been implemented as a sensory feature by computing the kurtosis for a range of frequency components in a time frequency diagram. The results from this study have shown that the implemented approach is a suitable method for providing a better understanding of acoustic emission and vibration signals to improve the reliability and the capability of condition motioning system.

Model-based condition monitoring of PEM fuel cell using Hotelling T2 control limit

Although a variety of design and control strategies have been proposed to improve the performance of polymer electrolyte membrane (PEM) fuel cell systems, temporary faults in such systems still might occur during operations due to the complexity of the physical process and the functional limitations of some components. The development of an effective condition monitoring system that can detect these faults in a timely manner is complicated by the operating condition variation, the significant variability/uncertainty of the fuel cell system, and the measurement noise. In this research, we propose a model-based condition monitoring scheme that employs the Hotelling T 2 statistical analysis for fault detection of PEM fuel cells. Under a given operating condition, the instantaneous load current, the temperature and fuel/gas source pressures of the fuel cell are measured. These measurements are then fed into a lumped parameter dynamic fuel cell model for the establishment of the baseline under the same operating condition for comparison. The fuel cell operation is simulated under statistical sampling of parametric uncertainties with specified statistics (mean and variance) that account for the system variability/uncertainty and measurement noise. This yields a group of output voltages (under the same operating condition but with uncertainties) as the baseline. Fault detection is facilitated by comparing the real-time measurement of the fuel cell output voltage with the baseline voltages by employing the Hotelling T 2 statistical analysis. The baseline voltages are used to evaluate the output T 2 statistics under normal operating condition. Then, with a given confidence level the upper control limit can be specified. Fault condition will be declared if the T 2 statistics of real-time voltage measurement exceeds the upper control limit. This model-based robust condition monitoring scheme can deal with the operating condition variation, various uncertainties in a fuel cell system, and measurement noise. Our analysis indicates that this scheme has very high detection sensitivity and can detect the fault conditions at the early stage.