Figure 6 - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
Source publication
Condition Monitoring (CM) of wind turbines can greatly reduce the maintenance costs for wind farms, especially for offshore wind farms. A new condition monitoring method for a wind turbine gearbox using temperature trend analysis is proposed. Autoassociative Kernel Regression (AAKR) is used to construct the normal behavior model of the gearbox temp...
Context in source publication
Context 1
... x 4 is the gearbox temperature measurement in the observation vectors, and 4 ˆ x is the AAKR model estimate for x 4 . A time window with width N is adopted to calculate the moving average or mean value and standard deviation for the N successive residuals in the window: The moving window is shown in Figure 6. ...
Similar publications
It is common for wind turbines to be installed in remote locations on land or offshore, leading to difficulties in routine inspection and maintenance. Further, wind turbines in these locations are often subject to harsh operating conditions. These challenges mean there is a requirement for a high degree of maintenance. The data generated by monitor...
This article offers reasons to defend the use of generic behavior models as opposed to specific models in applications to determine component degradation. The term generic models refers to models based on operating data from various units, whereas specific models are calculated using operating data taken from a single unit. Moreover, generic models...
Atmospheric conditions have a clear influence on wake effects. Stability classification is usually based on wind speed, turbulence intensity, shear and temperature gradients measured partly at met masts, buoys or LiDARs. The objective of this paper is to find a classification for stability based on wind turbine Supervisory Control and Data Acquisit...
Using 10-minute wind turbine supervisory control and data acquisition (SCADA) system data to predict faults can be an attractive way of working toward a predictive maintenance strategy without needing to invest in extra hardware. Classification methods have been shown to be effective in this regard, but there have been some common issues in their a...
Atmospheric conditions have a clear influence on wake effects. Stability classification is usually based on wind speed, turbulence intensity, shear and temperature gradients measured partly at met masts, buoys or LiDARs. The objective of this paper is to find a classification for stability based on wind turbine Supervisory Control and Data Acquisit...
Citations
... Moreover, since the corrosion damage, busting, scraping and other faults can be detected at an early stage, they are assessed with low criticality and hence are identified using the condition monitoring (CM) methods such as ultrasonic testing or Auto-Associative Kernel Regression (AAKR). Data from wind turbine powertrain diagnostic tests was collected in [24], wherein electrical measurement used to identify mechanical faults and collected data used to reveal vibration signature of gear eccentricity was examined, that were both successful. Variations in oil properties, including the viscosity, moisture content, particle density, and detritus, are widely utilised to indicate potential faults and as inspection approaches. ...
... Moreover, since the corrosion damage, busting, scraping and other faults can be detected at an early stage, they are assessed with low criticality and hence are identified using the condition monitoring (CM) methods such as ultrasonic testing or Auto-Associative Kernel Regression (AAKR). Data from wind turbine powertrain diagnostic tests was collected in [24], wherein electrical measurement used to identify mechanical faults and collected data used to reveal vibration signature of gear eccentricity was examined, that were both successful. Variations in oil properties, including the viscosity, moisture content, particle density, and detritus, are widely utilised to indicate potential faults and as inspection approaches. ...
Renewable energy is seen as the greatest solution for meeting growing energy needs. Wind energy is regarded as a rich energy source, and it frequently coexists alongside solar energy. In comparison to fossil fuels, it is inexhaustible and pollution-free. Based on its purpose and energy producing yield, wind turbines are frequently classified as small or large systems. This paper will present an overview of all possible faults in a wind turbine from structural damage to electrical fault. To improve the system's reliability, sustainable materials and advanced technologies for the development of various parts of wind turbines are being supported. Turbine blades, generators, and other auxiliary parts play an important role in the turbine's smooth functioning. Thus, their material properties are paramount. Hence, an overview of different parts, their yearly corresponding faults and their breakdown causes, are presented in this paper.
... The prediction of the SOC depends on the average voltage the most and on the nonlinear behavior of the battery voltage. Since the average voltage is the average of the voltages (the present voltage and the previous voltage values) of a moving window, which is a statistical method to quickly identify the changes in the residual mean value and standard deviation [32], it contains a lot of information on the previous condition of the SOC. It is the main requirement of the RNN, that the previous important input and output, should be considered for the present output. ...
Enhancing the accuracy of the battery state of charge (SOC) estimation is essential in developing more effective, dependable, and convenient electric vehicles. In this paper, a hybrid CNN and gated recurrent unit-long short-term memory (CNN-GRU-LSTM) approach, which is a recurrent neural network (RNN) based model with an explainable artificial intelligence (EAI) was used for the battery SOC estimation, where the cell parameters were explicitly synchronized to the SOC. The complexed link between the monitoring signals related to current, voltage, and temperature, and the battery SOC, was established using the deep learning (DL) technique. A LG 18650HG2 li-ion battery dataset was used for training the model so that the battery was subjected to a dynamic process. Moreover, the data recorded at ambient temperatures of −10 °C, 0 °C, 10 °C, and 25 °C are fed into the method during training. The trained model was subsequently used to estimate the SOC instantaneously on the testing datasets. At first, the training process was carried out with all temperature data to estimate the SOC by the trained model at various ambient temperatures. The proposed approach was capable to encapsulate the relationships on time into the network weights and, as a result, it produced more stable, accurate, and reliable estimations of the SOC, compared to that by some other existing networks. The hybrid model achieved a mean absolute error (MAE) of 0.41% to 1.13% for the −10 °C to 25 °C operating temperatures. The EAI was also utilized to explain the battery SOC model making certain decisions and to find out the significant features responsible for the estimation process.
... These readings are generally included in the SCADA dataset along with ambient temperature [206]; therefore, they are generally processed along with several other thermophysical measurements to detect anomalies. Some noteworthy examples for CM focused solely and/or prominently on temperature readings can be found in Guo et al. [59], Guo & Bai [207], Cambron et al. [208], and Astolfi et al. [209]. Even more specifically, approaches based on oil temperature measurements were recently reviewed by Touret et al. [210]. ...
A complete surveillance strategy for wind turbines requires both the condition monitoring (CM) of their mechanical components and the structural health monitoring (SHM) of their load-bearing structural elements (foundations, tower, and blades). Therefore, it spans both the civil and mechanical engineering fields. Several traditional and advanced non-destructive techniques (NDTs) have been proposed for both areas of application throughout the last years. These include visual inspection (VI), acoustic emissions (AEs), ultrasonic testing (UT), infrared thermography (IRT), radiographic testing (RT), electromagnetic testing (ET), oil monitoring, and many other methods. These NDTs can be performed by human personnel, robots, or unmanned aerial vehicles (UAVs); they can also be applied both for isolated wind turbines or systematically for whole onshore or offshore wind farms. These non-destructive approaches have been extensively reviewed here; more than 300 scientific articles, technical reports, and other documents are included in this review, encompassing all the main aspects of these survey strategies. Particular attention was dedicated to the latest developments in the last two decades (2000–2021). Highly influential research works, which received major attention from the scientific community, are highlighted and commented upon. Furthermore, for each strategy, a selection of relevant applications is reported by way of example, including newer and less developed strategies as well.
... This approach has demonstrated high accuracy, flexibility, and generalization with broad applications in various types of industrial equipment [6]- [13]. It can be effectively applied not only for non-rotating equipment, such as boilers in a coal plant [9] and gear boxes in a wind turbine [10], but also for rotating machines, such as bearings in engines [11] and blades in compressors or steam turbines [12]. ...
... 14) Identification of influencing factors. The PPCA loadings obtained by (10) are further employed to identify the sensor variables that mainly influence faults, which will facilitate the root cause analysis of faults in the smart maintenance of turbomachines. ...
... Based on the results shown in Figs. 19 and 20, it can be clearly observed that the fault was mainly attributed to PC2, PC5, and PC6. Figure 21 shows the loadings of the three PCs obtained using (10), which indicates the contribution of each variable to PCs. This indicates that the faults are primarily represented by six variables: CTD, CTIM, CSGV, DWATT, and two-stage one-wheel space temperature variables. ...
Faults in the critical components of a large rotatory machine often result in unplanned breakdowns, leading to a significant loss of property and life. Condition monitoring, as a key component in the smart maintenance of industrial equipment, has become a promising tool for providing automatic early alerting of potential damage to critical components, thus reducing potential outages and improving system safety and reliability while lowering maintenance costs. This is still a very challenging topic in various industrial fields because of data imperfection and multivariate correlation, as well as the variation in faults and components in different machines. This paper presents an optimized probabilistic signal reconstruction methodology to address these challenges in the fault prediction of rotatory machines using multivariate vibration signals. Three signal reconstruction methods, that is, Bayesian wavelet multiscale decomposition, probabilistic principal component analysis, and auto-associative kernel regression, were seamlessly integrated to address the noise, high dimensionality, and correlation in the sensed multivariate vibration data for accurate fault prediction. The bandwidth parameter in the auto-associative kernel regression approach was optimized to represent the health status of the rotatory machine. The obtained model was further utilized to predict the responses under unknown conditions. The alerting threshold, based on the squared mean errors of the predicted and measured time series, was automatically adjusted using a rolling window strategy and then employed to predict the possible fault. Finally, the validity, feasibility and generalization of the proposed methodology are illustrated by applying two cases of different rotating machines: centrifugal compressor and gas turbine.
... The HI of a system is constructed from the consistent feature class based on the linear weighted fusion strategy and the dynamic change of the weight by [19]. In [20], the auto associated kernel regression (AAKR) method is proposed, which takes the features collected under the health status of the equipment as the weighted sum, and determines the device HI according to the similarity between the current signal and the reconstructed signal. Baraldi et al. [21] proposed an improved AAKR (IAAKR) method considering the low robustness of the traditional AAKR method and applied it to the condition monitoring of the Pressurized Water Reactor Nuclear Power Plant. ...
... A permutation matrix P perm is defined, such that when it is applied to the vector V d , the components of the obtained vector are the same of it but appear in the decreasing order. P c − P i h is mapped by D p and P perm as Equation 20. ...
Railway turnout systems (RTS), as one of the most critical ground infrastructures of the high-speed rail, which directly impact the railway operation safety, are also susceptible to frequent faults. Hence, efficient fault prediction and intelligent maintenance decision support of RTS are significant to avoid unexpected outages and guarantee the operation safety of trains. A key challenge for fault prediction of RTS is to extract and select effective feature combinations that describe the degradation status of the system and then generate health indicators (HI) with high monotonicity, correlation, and robustness. In this paper, we focus on the jam fault caused by insufficient lubrication, which is one of the most frequent faults of RTS, and we present a novel unsupervised adaptive latent feature extraction method based on the improved sparse auto-encoder (ISAE). The locally weighted regression (LOESS) is performed to smooth the extracted latent features to overcome the influence of the noise. Improved auto-associative kernel regression (IAAKR) is utilized to fuse the feature combination and generate HI, which can intuitively describe the degradation status of RTS. Finally, the gated recurrent unit (GRU) network is introduced to enhance the correlation data process and construct the fault prediction models. The parameters of GRU are optimized by the improved particle swarm optimization (IPSO) algorithm. Extensive experiments are conducted on a real-world RTS degradation dataset collected from the Changsha Railway Station in China, which is related to the jam fault caused by the lubrication reduction, and the results show the proposed method achieves better prediction performance compared to state-of-the-art methods in terms of different evaluation metrics.
... According to the same study, "among all bearings in a planetary gearbox, the planet bearings, intermediate shaft-locating bearings, and highspeed locating bearings tend to fail at a higher rate, whereas the planet carrier bearings, hollow shaft bearings, and non-locating bearings are the bearings that are most likely to fail." An additional significant failure is decoupling between the shaft and the gearbox, which is considered to be catastrophic [127], whereas other faults such as pitting, cracking, scratching and other faults are graded with lower cruciality [144], as they can be spotted on time via gearbox diagnosis and condition monitoring (CM) techniques, e.g., acoustic emission (AE) [145] or auto-associative kernel regression (AAKR) [146]. Captured in [136] is data relating to wind turbine drivetrain diagnostics, in which electrical evaluation was used to check for mechanical flaws, and the diagnosis of gear eccentricity was examined, both of which were successful. ...
To meet the increasing energy demand, renewable energy is considered the best option. Its patronage is being encouraged by both the research and industrial community. The main driving force for most renewable systems is solar energy. It is abundant and pollutant free compared to fossil products. Wind energy is also considered an abundant medium of energy generation and often goes hand in hand with solar energy. The last few decades have seen a sudden surge in wind energy compared to solar energy due to most wind energy systems being cost effective compared to solar energy. Wind turbines are often categorised as large or small depending on their application and energy generation output. Sustainable materials for construction of different parts of wind turbines are being encouraged to lower the cost of the system. The turbine blades and generators perform crucial roles in the overall operation of the turbines; hence, their material composition is very critical. Today, most turbine blades are made up of natural fiber-reinforced polymer (NFRP) as well as glass fiber-reinforced polymer (GFRP). Others are also made from wood and some metallic materials. Each of the materials introduced has specific characteristics that affect the system’s efficiency. This investigation explores the influence of these materials on turbine efficiency. Observations have shown that composites reinforced with nanomaterials have excellent mechanical characteristics. Carbon nanotubes have unique characteristics that may make them valuable in wind turbine blades in the future. It is possible to strengthen carbon nanotubes with various kinds of resins to get a variety of different characteristics. Similarly, the end-of-life treatment methods for composite materials is also presented.
... The multivariate state estimation technique (MSET) is one of the most used data-driven fault detection methods. The MSET model is developed with normal operating data, but unlike ANN, complicated parameter searching is not necessary during the MSET model construction, making it much easier and more feasible to be implemented in practical use [19][20][21][22][23][24][25][26][27]. By using MSET, faults can be detected without the need for fault records that are difficult to obtain, physical mechanism knowledge, and complicated parameter determination. ...
The induced draft (ID) fan is an important piece of auxiliary equipment in coal-fired power plants. Early fault detection of the ID fan can provide predictive maintenance and reduce unscheduled shutdowns, thus improving the reliability of the power generation. In this study, an adaptive model was developed to achieve the early fault detection of ID fans. First, a non-parametric monitoring model was constructed to describe the normal operating characteristics with the multivariate state estimation technique (MSET). A similarity index representing operation status was defined according to the prediction deviations to produce warnings of early faults. To deal with the model accuracy degradation because of variant condition operation of the ID fan, an adaptive strategy was proposed by using the samples with a high data quality index (DQI) to manage the memory matrix and update the MSET model, thereby improving the fault detection results. The proposed method was applied to a 300 MW coal-fired power plant to achieve the early fault detection of an ID fan. In addition, fault detection by using the model without an update was also compared. Results show that the update strategy can greatly improve the MSET model accuracy when predicting normal operations of the ID fan; accordingly, the fault can be detected more than 4 h earlier by using the strategy with the adaptive update when compared to the model without an update.
... Recently the auto-associative kernel regression (AAKR) method has been developed as a similarity-based model (SBM) for condition monitoring and fault alerting in largescale turbomachines (Garvey 2007, Di Maio 2013, Fei 2015, Sairam 2016, Yu 2017, Guo 2011, Brandsaeter 2017, Qian 2018, Baraldi 2015. This approach utilizes multivariate historical data collected at normal conditions to establish a system identification model representing the Weijian Tang et al. ...
... A health index calculated from the difference of predicted responses and actual measurements is employed to quantitively assess the status of the system. This approach has demonstrated its high accuracy, flexibility and generalization with a broad spectrum of applications in various types of equipment (Garvey 2007, Di Maio 2013, Fei 2015, Sairam 2016, Yu 2017, Guo 2011, Brandsaeter 2017, Qian 2018, Baraldi 2015. It can be effectively applied not only for non-rotating equipment such as boiler in a coal plant (Yu 2017), and gear box in a wind turbine (Guo 2011), but also for rotating machines such as bearings in engine (Brandsaeter 2017), and blades in compressor or steam turbines (Qian 2018). ...
... This approach has demonstrated its high accuracy, flexibility and generalization with a broad spectrum of applications in various types of equipment (Garvey 2007, Di Maio 2013, Fei 2015, Sairam 2016, Yu 2017, Guo 2011, Brandsaeter 2017, Qian 2018, Baraldi 2015. It can be effectively applied not only for non-rotating equipment such as boiler in a coal plant (Yu 2017), and gear box in a wind turbine (Guo 2011), but also for rotating machines such as bearings in engine (Brandsaeter 2017), and blades in compressor or steam turbines (Qian 2018). ...
Faults in the critical components of a turbomachine usually result in unplanned outage, leading to huge loss of properties and life. Condition monitoring becomes a promising tool to provide automatic early alerting of potential damage in critical components thus ensuring the system safety and reliability while lowering its maintenance cost. This is still a challenging hot topic due to the data imperfection and multivariate correlation, as well as the variation of faults and components in different turbomachines. This paper presents an enhanced generic probabilistic similarity-based method to address these challenges in fault prediction of large turbomachines. Bayesian wavelet multi-scale decomposition is proposed to address the potential noise in the sensed multivariate time historical data. The advanced signal processing balances the over-denoising and under-denoising of raw multivariate signals. An optimized auto-associative kernel regression (OAKR) approach is developed to represent the healthy status of the turbomachine system and further predict its responses under unknown status. The band width of the kernel function in the method is optimized through Nelder-Mead simplex algorithm. The alerting threshold based on the squared mean errors of the predicted and measured time series is adjusted automatically through a rolling window strategy. A comparison study is conducted to demonstrate the effectiveness and feasibility of the proposed methodology by using the real-world data and events collected from a centrifugal compressor.
... The MSET model is developed with normal operating data, but unlike ANN, complicated parameter searching is not necessary during the MSET model construction, making it much easier and more feasible to be implemented in practical use. By using MSET, faults can be detected with no need for fault records (which are difficult to obtain), physical mechanism knowledge, and complicated parameter determination [12][13][14]. MSET can learn the process features with historical normal operations and produce a prediction of the actual measured data sample, which is named the observation. By evaluating the similarity between the predicted value and the observation, operating faults can be identified. ...
... MSET is a widely used data-driven method and it mines the features of healthy states from the history database [13][14][15]. However, like all the data-driven models, the accuracy of the MSET model has an important dependence on the training data, which are called as a memory matrix and represent the relationship among feature variables. ...
The induced draft (ID) fan is important auxiliary equipment in the thermal power plant. It is of great significance to monitor the operation of the ID fan for safe and efficient production. In this paper, an adaptive warning model is proposed to detect early faults of ID fans. First, a non-parametric monitoring model is constructed to describe the normal operation states with the multivariate state estimation technique (MSET). Then, an early warning approach is presented to identify abnormal behaviors based on the results of the MSET model. As the performance of the MSET model is heavily influenced by the normal operation data in the historic memory matrix, an adaptive strategy is proposed by using the samples with a high data quality index (DQI) to manage the memory matrix and update the model. The proposed method is applied to a 300 MW coal-fired power plant for early fault detection, and it is compared with the model without an update. Results show that the proposed method can detect the fault earlier and more accurately.
