Early Detection Of Degradation Research Articles

Performance degradation assessment of rolling bearings for electrostatic monitoring based on IDDAE and ADPC

Abstract To improve the early degradation detection capability of the electrostatic monitoring system for rolling bearings, a performance degradation evaluation method based on improved deep denoising autoencoder (IDDAE) and adaptive density peak clustering (ADPC) is proposed in this paper. Firstly, the fusion of electrostatic charge signal features with conventional time-domain, frequency-domain and time-frequency-domain features constitutes the characteristic parameter set of the electrostatic monitoring system indicating the status of the bearings. Then, in order to improve the feature extraction ability of DAE, the deep network DDAE is constructed, and L1 regularisation and Dropout mechanism are applied to avoid overfitting in the deep network, so as to achieve non-linear mapping dimensionality reduction of high-dimensional features. Moreover, to eliminate the error caused by manually selecting the clustering centre, the parameters are adaptively determined by entropy value method and comprehensive optimisation search on the basis of DPC, thus avoiding the "chain effect" that occurs in traditional DPC when data are incorrectly aggregated due to incorrect assignment of clustering centres. Consequently, an improved ADPC algorithm is used to establish a model to measure the health status of bearings, calculate the Mahalanobis distance (MD) be-tween the test set and the cluster centre, and quantitatively characterize the degree of performance degradation of rolling bearings. Finally, combining the 3σ principle, a repair method that can satisfy online monitoring and adapt to spurious fluctuations in different situations is established on a sliding window to obtain an improved index IMD that can accurately characterise the rolling bearing degradation process. The experimental results show that the proposed method can identify early bearing degradation earlier and has better monotonicity, robustness and tendency than other performance degradation assessment methods.

Exploring Catalase Activity as A Biological Indicator in Degraded Soils

This study examines the relationship between catalase activity in degraded soils and soil properties, and addresses its potential as an indicator of soil health and productivity. Catalase, a key enzyme reflecting microbial activity and soil aeration, has been analyzed in 30 soil samples collected from the disturbed surface layer (0-15 cm depth) of erosion-prone areas characterized by rubble accumulation on hill slopes and soil compaction in foot slopes. The soil in the study area is classified as Typic Xerortent. Catalase enzyme activity in the soil samples varied between 10.4 and 48 µl O2 g-1 dry soil. In addition to catalase, the physicochemical properties of the soil were also assessed, including pH, electrical conductivity, organic matter content, and texture. Nutrient contents, including nitrogen (0.046-0.239 g N 100 g-1), phosphorus (1.77-20.05 µg P g-1), and potassium (0.01-3.31 meq K 100 g-1), were also measured. A positive correlation was observed between catalase activity and potassium and phosphorus levels, but the relationship with nitrogen was statistically insignificant. These findings suggest that catalase activity can serve as a biological indicator for the early detection of degradation in soils at risk of erosion. The study provides valuable insights into the impact of erosion on soil biochemistry and highlights the role of catalase in assessing soil health and guiding sustainable land management practices.

Development of isotopically labelled 65Cu embedded PMMA-65CuO nanocomposites for detection and quantification of PMMA bone cement degradation at trace levels

Polymethyl methacrylate (PMMA) bone cement is a popular bone-filling material for biomedical applications. Bone-cement implant failure is a common occurrence, but the consequence of this failure can be prevented/minimised by early detection of degradation. This work utilises a stable isotope labelling approach to monitor PMMA bone cement degradation. Stable isotopically enriched traceable nanoparticles of 65CuO were synthesized and introduced to PMMA bone cement. Accelerated and normal degradation of 65CuO-loaded PMMA bone cement nanocomposite was performed in acetone and simulated body fluid (SBF). 65Cu was detected and quantified upon PMMA bone cement nanocomposite degradation. The results showed a linear correlation between bone cement degradation and tracer release. When the 65CuO-PMMA composite deteriorated by 6.10 ± 3.04% in acetone, 5.6 ± 2.5 µg of tracer was released in 10 min. Similarly, after one week of degradation in SBF, 0.35 ± 0.31 µg of 65Cu tracer was released, translating to a 0.18 ± 0.09% weight loss. The stable isotopic tracer approach allowed us to measure and detect 65Cu under conditions of high background Cu concentration present in the human body upon 0.2% of PMMA nanocomposite degradation. 65CuO nanoparticles addition to PMMA bone cement did not alter the cytocompatibility (proliferation, differentiation, and osteocalcin formation) in MG-63 cells.

In-Flight Monitoring of a Primary Flight Control Electromechanical Actuator⋆

We aim at designing a monitoring algorithm able to perform early detection of degradation that may lead to jamming in the electromechanical actuators (EMAs) used for primary flight control. The challenge is to construct a detection algorithm performing an online monitoring using in-flight data. As the EMAs only move during specific phases of flight, the data subsets containing relevant information for the identification of at least some friction parameters must be determined. This is achieved by using tools from sensitivity analysis. The resulting data analysis is used to govern the parameter estimation part of a Dual Extended Kalman Filter (DEKF) in such a way that all informative data are exploited at best for friction estimation. The method is validated on healthy and faulty synthetic data resulting from a detailed EMA simulator.

A Review of Remote Sensing and GIS based Change Detection Techniques for Identification of Sites need Ecological Restoration in Garhwal Himalayas

Forest ecological restoration is a vital step for climate change mitigation and maintaining biodiversity. It aims to recreate, initiate, or accelerate the recovery of an ecosystem that has been disturbed. However, forest monitoring and assessment of forest losses in the Himalayan region is a major challenge due to difficult terrain conditions. The recent advancements in Remote Sensing and Geographic Information System (RS&GIS) techniques are enabling the quick and cost-effective solution for ecological restoration by mapping, monitoring, and quantification of areas that are affected due to degradation and deforestation. The present study aims to provide a review of recent advances in the methods and data products that can be used to extract information with regard to location, timing, and extent of vegetation losses and the past studies related to vegetation change conducted in the Garhwal region of Western Himalaya. The challenges and opportunities for the use of remote sensing in the field of restoration ecology have been discussed. The review revealed that there is very limited information available about the complex Himalayan ecosystem. Further research in the field of forest monitoring to assist in early detection of degradation and formulation of area-specific ecological restoration techniques is needed.

A New Feature Extraction Technique for Early Degeneration Detection of Rolling Bearings

Feature extraction technology is an important part of bearing diagnosis, especially for early degradation detection. However, the traditional feature extraction technology can not effectively remove noise or is not sensitive to periodic weak faults, which leads to be inclined to raise false alarms and prediction delay for early degradation detection. In order to solve these two issues, a new feature extraction technique is presented based on Envelope Harmonic-to-noise Ratio (EHNR) and Adaptive Variational Mode Decomposition (AVMD). First of all, the minimum average envelope entropy is used as the objective function to search the optimal parameters of the Variational Modal Decomposition (VMD) adaptively by the Grey Wolf Optimization (GWO) algorithm. The problem of under-decomposition or over-decomposition caused by improper parameter setting is avoided. Then, a new index called Effective Weighted Sparseness Kurtosis (EWSK) is proposed. This index can separate the effective modal components and noise modal components only by the positive and negative results, so as to achieve the purpose of removing noise interference and retaining a large amount of fault information. Finally, the EHNR of the reconstructed signal is calculated, and its sensitivity to periodic fault shock is utilized to detect the early degradation starting point of the rolling bearing. Experimental results show that the proposed method outperforms several state-of-the-art detection methods in terms of early degradation point detection, false alarm rate and computational complexity. The superior performances of the presented AVMD-EHNR method can provide the basis for early fault diagnosis and remaining useful life prediction of rolling bearings.

An Unsupervised Bayesian OC-SVM Approach for Early Degradation Detection, Thresholding, and Fault Prediction in Machinery Monitoring

In the literature pertaining to condition-based maintenance using machine learning, the class of unsupervised approaches has yet to be fully explored. In particular, the topics of fault prediction and unsupervised degradation modeling, which have significant importance to practice, have not been widely studied. In this article, we propose a novel unsupervised approach for early degradation detection and fault prediction, termed the Bayesian one-class support vector machine (B-OCSVM), which is based on OC-SVM and the hierarchical Bayesian framework. The proposed approach aims to address key gaps in the literature by proposing a new unsupervised OC-SVM hyperparameter estimation method for early degradation detection and new degradation threshold, which is used to predict when a detected degradation process will manifest as a fault. Unlike traditional prognostic approaches, the proposed degradation threshold can be defined without prior knowledge pertaining to the fault. Fault prediction is achieved using a novel prognostic in conjunction with a hierarchical Bayesian degradation framework. We validate and benchmark the proposed approach against the state of the art using run-to-failure data from three datasets to demonstrate the earlier detection point of the proposed approach compared to existing approaches and to showcase how the proposed degradation threshold and novel prognostic can be used effectively to predict when faults will occur. In addition, the results show that B-OCSVM generalizes well to a number of different operating conditions and fault types, which signifies that the early detection and prognostic elements of the proposed approach have strong practical significance in real-world applications.

Identification of land degradation hotspots in semiarid region of Anantapur district, Southern India, using geospatial modeling approaches

Land degradation and desertification has been graded as a foremost environmental dispute for the coming eras. Thus, the surveillance and early detection of degradation is a major objectives for a number of scientific and policy organizations, with RS and GIS techniques being a candidate choice for the development of monitoring systems. This study was carried out as an attempt to develop a new modeling approach for identification of desertified hotspots based on normalized difference vegetation index (NDVI) in semiarid region of Anantapur district, Southern India. A supervised classification was carried out on the six reflective bands for the past 28 years, i.e., from 1990 to 2018 individually with the aid of ground truth data. Ground truth information collected during field data and land cover map of 2005–2006 was used to assess the accuracy of the classification results. Using ancillary data, visual interpretation and expert knowledge of the area through GIS further refined the classification results. Post-classification change detection technique was used to produce change image through cross-tabulation. Changes among different NDVI classes such as water bodies, agricultural fields, vegetation, degraded lands, desertified lands were assessed. During the study period, a very severe land degradation has taken place as a results reveals that 31.93% of the land in this region is facing the land degradation and desertification conditions; in that 17.34% of the land face the severe land degradation and 14.59% of the land have been desertified. These changes in land cover led to vegetation degradation and water logging in part of the study area.

PV field reliability status—Analysis of 100 000 solar systems

AbstractIn this study, we analyzed annual production data from 100 000 photovoltaic systems as well as comments relating to their performance and maintenance. Our analysis revealed that 80% to 90% of all systems performed within 10% of the predicted production or better. Also, 56% of the systems were still performing above P50 or the median at 5 years. However, a small but significant tail of about 7000 systems perform below P90 expectations. In general, residential systems have a lower rate of failure than utility or commercial systems. Despite higher rates of component failures, utility systems lose less power than residential or commercial systems. This outcome is likely due to closer monitoring and better operations and maintenance practices. Inverters are still the components that reportedly fail most often (4%‐6%), but other failures such as unspecified repair and meters cause more production loss. Reported module failures are relatively rare (0.2%) and are within the range of historical values. Installation quality affects performance and safety as indicated by data showing connector, wiring, breaker, and fuse failures due to undersizing, electrical design, and improper connection. Lastly, early detection of degradation and proactive response resulted in less impact on production than reactive, unplanned repairs.

Roller Bearing Performance Degradation Assessment Based on Fusion of Multiple Features of Electrostatic Sensors.

This paper presents a new method to assess the performance degradation of roller bearings based on the fusion of multiple features, with the aim of improving the early degradation detection ability of the electrostatic monitoring system. At first, a set of feature parameters of the electrostatic monitoring system indicating the normal state of the bearings are extracted from the perspective of the time domain, frequency domain and complexity. Then, the parameter set is processed to reduce the dimensions and eliminate the redundancy using spectral regression. With the processed features, a Gaussian mixed model is established to gauge the health of the bearing, providing the distance value obtained using Bayesian inference as a quantitative indicator for assessing the performance degradation. The method is applied to access the life of a bearing in which the mechanic fatigue is artificially accelerated. The test results show that the proposed method can better reflect the degradation process of the bearing compared to other evaluation methods. This enables the electrostatic monitoring technique to detect the degradation of the bearing earlier than the vibration monitoring, providing a powerful tool for the condition monitoring of roller bearings.

Fault Prediction via Symptom Pattern Extraction Using the Discretized State Vectors of Multisensor Signals

Fault prediction and early degradation detection have received considerable attention in many engineering disciplines. Fault symptoms can be identified by abnormal values or unusual trends in the monitored sensor signals over a certain period prior to fault occurrence. However, how to extract abnormal pattern, particularly those with conditional relations among multiple sensor signals, remains unclear. Pattern extraction is further difficult particularly when there is no gradient relationship between measurements and operational states due to highly scattered data and unclear boundaries for distinguishing operational states. Additionally, defining the time period for symptom periods is challenging. To resolve these issues, we define the terms symptom pattern and symptom period, and then present a symptom pattern extraction method that collects all evidence of potential fault occurrence from multiple sensor signals. We postulate that, given time markers of fault occurrences, a symptom period precedes the occurrence of a fault. Symptom patterns are defined as either only found in the symptom periods or not found in the given time series, but similar to fault patterns. We further discuss an iterative search procedure for determining the length of symptom periods and propose a severity assessment method for symptom patterns. Finally, we apply the symptom pattern extraction and severity assessment methods to an online fault prediction procedure. By assessing the total severity of patterns in the monitoring window, early warning decision can be made. The procedure is tested in the early detection of abnormal cylinder temperature in a marine diesel engine and automotive gasoline engine knocking.

Early Degradation Detection of the Insulation Resistance of Multi-Layer Ceramic Capacitors by the Pattern Analysis of Capacitance and Dissipation Signals

Early Degradation Detection of the Insulation Resistance of Multi-Layer Ceramic Capacitors by the Pattern Analysis of Capacitance and Dissipation Signals

Development of Cell-Protecting Methods for Carbon-Removal from Porous Ni-YSZ Anodes and Regeneration of the Cell Performance

Solid oxide fuel cells are highly efficient units, which directly convert the chemical energy of gaseous fuels into electrical energy without additional conversion steps. The overall efficiency can be increased by using heat losses occurring during the operation at high temperatures between 600–1000°C. SOFCs further offer a great fuel flexibility and compared to other fuel cell types they can internally reform hydrocarbons. Internal conversion of carbon-containing fuels over nickel as the most widely used catalyst tends to promote carbonaceous deposits on the anode surface as well as inside the anode, causing deactivation of the fuel cells. Nevertheless, undisturbed operation with conventional fuels and early detection of the cell degradation are highly important for the commercial usage of solid oxide fuel cells in industry, such as in auxiliary power units or especially for mobile application. Formation and deposition of carbonaceous species on the anode surface of solid oxide fuel cells may be prevented under specific operating conditions such as high steam/carbon ratio or high current density. The increasing amount of steam in fuel can chemically remove carbon adsorbed on the anode surface thus reducing the total amount of carbon deposits. However, this would significantly dilute the fuel thus reducing the overall power and the cell efficiency. Further possibility to avoid carbon formation is to operate the cells under load higher than the critical current density. However, increase of the steam amount or variation of the cell load is neither realistic nor advantageous for the commercial purpose. Without the need for the variation of the operating conditions, such as higher amount of steam or higher load, early detection of degradation phenomenon and applying of appropriate cell-protecting regeneration strategies can improve the operating reliability of the SOFC systems. In order to prolong the cell’s lifetime and to accelerate the market access of SOFCs, diverse approaches for carbon removal in a cell-protecting manner and regeneration of the cell performance were developed and detailed examined. They are outlined within this study. The practicability of the developed methods for industrial application was also considered. The regeneration strategies are based on application of: (1) gaseous components, for the gasification of carbon deposits, and (2) electrochemical methods, which remove carbon during the cell loading. Operation under gaseous components as hydrogen, water vapour or oxygen-enriched gas mixtures allowed complete carbon removal. Nevertheless, under operation in a fuel cell mode, only the approach that combined hydrogen and water vapour removed carbon from the anode while also protecting it from further undesired degradation. It is important to note that very high amount of water can deteriorate the cell performance and even provoke unwanted nickel oxidation, which thus must be considered. However, the allowed water vapor amount must thus me determined. Furthermore, feeding the anode with a very low amount of oxygen in a wide temperature range showed high carbon removal rates but resulted in further deterioration of the cell performance, and eventually led to mechanical degradation. Both methods for carbon removal in a cell-protecting manner and approaches that induced further microstructure degradation are presented within this study.

Land degradation trend assessment over Iberia during 1982-2012

Land degradation is recognized as an important environmental and social problem in arid and semi-arid regions, particularly within a climate change context. In the last three decades the entire Mediterranean basin has been affected by more frequent droughts, covering large sectors and often lasting more than one year. The Iberian Peninsula has been equally affected by intense drought events since the 1980s. According to the latest IPCC report the Mediterranean region will suffer further hydrological stress in the coming decades, as a consequence of diminishing of precipitation and increasing of average and extreme temperatures. This climatic outlook coupled with the land abandonment and/or intensification of some areas requires a continuous monitoring and early detection of degradation. The present work intends to contribute to such objectives.Land degradation could be stated as a longstanding deterioration in ecosystems productivity. Here we assess the ability of NDVI to be used as an indicator of land degradation over Iberia, from 1982 to 2012. The negative trends of the residuals obtained after removing the precipitation influence on NDVI were assumed to indicate land degradation. A widespread land improvement was observed over Iberia with few hot spots of land degradation located mainly in central and southern sectors and in east Mediterranean and Atlantic coasts. The comparison of spatial patterns of residual trends with dryness for the aridity regions over Iberia highlighted the relatively small fraction of land degradation that experiences an increased dryness, although almost totality belonging to semi-arid region. On the other hand, land improvement is only associated with a tendency of wetness in the northeastern humid sector. Moreover, less than 20% of the area presenting land degradation corresponds to regions associated with land cover changes, being the new land cover types associated with transitional woodland-shrub, permanent and annual crops and permanently irrigated land areas.

Failure mode prediction and energy forecasting of PV plants to assist dynamic maintenance tasks by ANN based models

In the field of renewable energy, reliability analysis techniques combining the operating time of the system with the observation of operational and environmental conditions, are gaining importance over time.In this paper, reliability models are adapted to incorporate monitoring data on operating assets, as well as information on their environmental conditions, in their calculations. To that end, a logical decision tool based on two artificial neural networks models is presented. This tool allows updating assets reliability analysis according to changes in operational and/or environmental conditions.The proposed tool could easily be automated within a supervisory control and data acquisition system, where reference values and corresponding warnings and alarms could be now dynamically generated using the tool. Thanks to this capability, on-line diagnosis and/or potential asset degradation prediction can be certainly improved.Reliability models in the tool presented are developed according to the available amount of failure data and are used for early detection of degradation in energy production due to power inverter and solar trackers functional failures.Another capability of the tool presented in the paper is to assess the economic risk associated with the system under existing conditions and for a certain period of time. This information can then also be used to trigger preventive maintenance activities.

Assessing Land Degradation and Desertification Using Vegetation Index Data: Current Frameworks and Future Directions

Land degradation and desertification has been ranked as a major environmental and social issue for the coming decades. Thus, the observation and early detection of degradation is a primary objective for a number of scientific and policy organisations, with remote sensing methods being a candidate choice for the development of monitoring systems. This paper reviews the statistical and ecological frameworks of assessing land degradation and desertification using vegetation index data. The development of multi-temporal analysis as a desertification assessment technique is reviewed, with a focus on how current practice has been shaped by controversy and dispute within the literature. The statistical techniques commonly employed are examined from both a statistical as well as ecological point of view, and recommendations are made for future research directions. The scientific requirements for degradation and desertification monitoring systems identified here are: (I) the validation of methodologies in a robust and comparable manner; and (II) the detection of degradation at minor intensities and magnitudes. It is also established that the multi-temporal analysis of vegetation index data can provide a sophisticated measure of ecosystem health and variation, and that, over the last 30 years, considerable progress has been made in the respective research.

Equipment Health Monitoring with Non-Parametric Statistics for Online Early Detection and Scoring of Degradation


 
 
 This paper develops a health monitoring scheme to detect and trend degradation in dynamic systems that are characterised by multiple parameter time-series data. The presented scheme provides early detection of degradation and ability to score its significance in order to inform maintenance planning and consequently reduce disruption. Non-parametric statistics are proposed to provide this early detection and scoring. The non-parametric statistics approximate the data distribution for a sliding time window, with the change in distribution is indicated using the two-sample Kolmogorov-Smirnov test. Trending the changes to the signal distribution is shown to provide diagnostic capabilities, with deviations indicating the precursors to failure. The paper applies the equipment health monitoring scheme to address the growing concerns for future gas turbine fuel metering valve availability. The fuel metering unit within a gas turbine is a complex electro-mechanical system, failures of which can be a major source of airline dis- ruption. The application is performed on data acquired from a series of industrial tests performed on large civil aero-engine fuel metering units subjected to varying levels of contaminant. The data exhibits characteristics of degradation, which are identified and trended by the equipment health monitoring scheme presented in this paper.
 
 

Condition Monitoring for Early Failure Detection. Frognerparken Pumping Station as Case Study

A case study has been carried out to investigate how process data from Frognerparken Pumping Station can be used more efficiently to get an early detection of degradation or failures of the pump systems. The technical condition is described by use of a single number from 0 to 100, denoted as the Technical Condition Index (TCI), where maximum value describes the design condition as new and the minimum value describes the state of total degradation. As presented in this paper, the pump station is broken down to subsystems where each subsystem consists of several nodes with its own TCI value. The overall pump station's TCI number is then computed by aggregating a weighted sum of all the subsystems’ TCIs.A method for early failure detection is also developed and is based on combining energy balance law together with the nonlinear extended Kalman filter to estimate model parameters for both the heating and the cooling phase of the pump. The model parameters are directly related to the temperature change and will give an indication of degradation during the transient phase even if the pump is working properly. During a visual inspection one of the pump had significantly higher temperature and vibration compared to the other pumps, and based on received timeseries for that specific day, we were able to validate the proposed method with realistic data.

Use partly hidden Markov model to evaluate a future failure

The diagnosis of failures, if done properly and enabling early degradation detection, represents a means to optimise the production unit and to reduce the costs by avoiding failures. This challenge can be addressed through hidden Markov models HMMs that can estimate the probability of a future failure based on observation system. However, sudden changes in system behaviour due to either system malfunction or one of its components will affect the operation process. Thus, previous errors have an impact on the current system state and a regular HMM does not meet this requirement unlike partly hidden Markov models PHMMs, which combines the power of conditioning the state transition probability to the previous observation. In this paper and for the first time, we propose to use PHMM as a mechanism to identify a future failure of industrial furnace. The obtained results prove that using PHMM seems to be particularly effective, efficient and outperforms the HMM.

Degradation of ‘Lumarith’ Cellulose Acetate

Objects manufactured from cellulose acetate comprise one of the most problematic groups of plastic in the collections of the Smithsonian Institution's National Museum of American History (NMAH). To understand better cellulose acetate degradation, a ‘salesman's sample kit’ of ‘Lumarith’ brand, injection-molded, cellulose acetate color samples, manufactured by the Celluloid Company in the early twentieth century and now in the NMAH collection, was studied using minimally invasive analytical techniques at the Smithsonian Institution's Museum Conservation Institute (MCI). The kit includes 49 plastic coupons that vary in color, transparency, chemical composition and current state of degradation. Results of analysis were compared with Celluloid Company records at the NMAH Archives Center and Celanese Corporation in Narrows, Virginia, in order to determine the causes for their current level of preservation or degradation. The possible reasons for the degradation of some coupons are discussed; methods are proposed for identifying cellulose acetate objects that are at risk and for early detection of degradation.