1,721,046 research outputs found
Experimental validation of multi-sensor data fusion model for railway wheel defect identification
No full textWheel defects are detrimental for railway train and track components and should be detected and identified as early as possible. Wheel Impact Load Detector (WILD) is a commercial condition monitoring system used for detecting the defective wheels. This system usually measures the rail strain at different points by multiple sensors. WILD converts the measured strains to the force and uses the peak force, dynamic force, and ratio of the peak force to the static force to estimate the condition of the in-service wheels. These methods are useful for detecting the severe defects contributing to the contact force to the extent that exceed a predetermined threshold. Therefore, in the prior research a fusion method has been developed to reconstruct a new informative pattern from the data collected by the multiple sensors. The reconstructed pattern provides a comprehensive description of the wheel condition. This paper validates the fusion method using a set of lab tests to investigate the applicability of the proposed method. For this purpose, a test rig has been built consisting of a circular rail, a rotating arm, and a wheel. Six strain sensors have been installed under the rail in the symmetric locations over the rail circle with 60 degree intervals. The fusion method used to reconstruct a signal from the bending strain signals measured by the multiple sensors. Different wheel defects including the flat and out-of-round wheels have been tested and the results validated the fusion method by providing informative patterns.Transport Engineering and Logistic
Unsupervised Physics-Informed Health Indicator Discovery for Complex Systems
No full textDiscovering health indicators (HI) is essential for prognostics and health management of complex systems, as an HI enables timely interventions and effective maintenance strategies. However, most of the existing methodologies for HI discovery rely on labeled data which is expensive and complicated to obtain in the real world. In this paper, we propose a novel, unsupervised physics-informed model structured after expert knowledge in the form of a graphical representation of the expected relationships between sensor readings, operating conditions, and degradation. In addition, a soft constraint is used to guide the representation of the HI according to generally available expert knowledge about degradation. We evaluated the model on a turbofan engine dataset and conducted four experiments by manipulating the original data to create realistic real-world scenarios. The proposed method discovers an HI that exhibits better intrinsic qualities than the current state-of-the-art methodologies, leading to enhanced prognostic performance. Notably, in situations where the initial health state of each system varies, the proposed method achieves an average prognostic performance improvement of approximately 20% compared to existing state-of-the-art methods.Air Transport & Operation
Generic Hybrid Models for Prognostics of Complex Systems
No full textHybrid models combining physical knowledge and machine learning show promise for obtaining accurate and robust prognostic models. However, despite the increased interest in hybrid models in recent years, the proposed solutions tend to be domain-specific. As a result, there is no compelling strategy of what, where, and how physics-derived knowledge can be integrated into deep learning models depending on the available representation of physical knowledge and the quality of data for the development of prognostic models for complex systems. This Ph.D. project aims to develop a general strategy for hybridizing prognostic models by exploring multiple methods to incorporate physical knowledge at various stages of the learning algorithm. The project will prioritize general expert knowledge as the primary source of information, while domain-specific knowledge will serve as an additional feature when applicable.Air Transport & Operation
Interpretable neural network with limited weights for constructing simple and explainable HI using SHM data
No full textRecently, companies all over the world have been focusing on the improvement of autonomous health management systems in order to enhance performance and reduce downtime costs. To achieve this, the remaining useful life predictions have been given remarkable attention. These predictions depend on the proper designing process and the quality of health indicators (HI) generated from structural health monitoring sensors based on prior established multiple prognostic evaluation criteria. Constructing such HIs from noisy sensory data demands powerful models that enable the automatic selection and fusion of features taken from those relevant measurements. Deep learning models are promising to autonomously extract features in scenarios with a huge volume of data without requiring considerable domain expertise. Nonetheless, the features established by artificial neural networks are complicated to comprehend and cannot be regarded as physical system characteristics. In this regard, the goal of this paper is to extend a new model; an interpretable artificial neural network that enables the automatic selection and fusion of features to construct the most appropriate HIs with remarkably fewer parameters. This model consists of additive and multiplicative layers that provide a feature fusion that better reflects the system’s physical properties. Additionally, the weights are discretized in two ways: a) using a ternary form with values {-1, 0, 1}, and b) relaxing the aforementioned ternary form by rounding the weights at the first decimal point in the range of [-1, 1]. Both discretization techniques have the ability to softly control the number of parameters that should be ignored. This trick guarantees interpretability for the neural network by extracting simple yet powerful equations representing the constructed HIs. Finally, the model’s performance is evaluated and compared with other approaches using a practical case study. The results show that the proposed approach's designed HIs are both interpretable and of high quality according to the criteria of the HI's evaluation.Structural Integrity & Composite
Ageing-aware battery discharge prediction with deep learning
No full textISSN:0306-2619ISSN:1872-9118ISSN:1872-911
Adaptive Prognostics: A reliable RUL approach
No full textIn the past decade, data-driven methodologies have gained increasing popularity, offering a foundation for predicting the remaining useful life (RUL) of engineering systems and structures using condition monitoring (CM) data. A particularly intriguing challenge lies in accurately predicting the RUL of systems that exhibit exceptional performance, whether underperforming or overperforming, owing to unforeseen phenomena occurring during their operational life. These unique systems, often referred to as outliers, pose a formidable challenge for RUL prediction. This research addresses this challenge by introducing a novel data-driven model, which is known as the Similarity Learning Hidden Semi-Markov Model (SLHSMM) and extends the capabilities of the Non-Homogeneous Hidden Semi-Markov Model (NHHSMM). The training dataset comprises strain data obtained from open-hole carbon-epoxy specimens exposed solely to fatigue loading. In contrast, the validation-testing dataset includes strain data from two specimens subjected to both fatigue and in-situ impact loading, representing an unexpected and previously unseen event in the training data. The study compares RUL estimations generated by the SLHSMM and NHHSMM. The results indicate that the SLHSMM outperforms the NHHSMM, offering superior accuracy in predicting outliers' RUL. This underscores its capability to adapt to unexpected phenomena and seamlessly incorporate unforeseen data into prognostics.Structural Integrity & Composite
Rail Wear Estimation for Predictive Maintenance:a strategic approach
Full text linkSince the very beginning of rail transport, wear has been identified as one of the dominant damage mechanisms that influence the Remaining Useful Life (RUL) of rail tracks. Whereas maintenance of the track is now predominantly executed at fixed intervals or based on yearly inspections, the accurate prediction of rail wear could considerably improve the maintenance process. The present work proposes a method for long-term rail wear prediction using measurements of actual rail and wheel profiles as starting point. By doing so, the computational expensive step of updating the rail profile in a wear calculation, as is done in presently used methods, can be omitted. The proposed method is used to study a number of generic trends, varying curve radius and rail or wheel profile. Further, the method is validated against measured wear on actual track sections for moderate curves. Finally, it can easily be extended to include variations in operational usage of the track (type / weight of trains, geometric details, slip conditions) in the future. The method presented in this paper can therefore assist in improving the track maintenance process by maximizing the utilization of the track service life, and minimizing maintenance costs
Automated Failure Diagnosis in Aviation Maintenance Using eXplainable Artificial Intelligence (XAI)
Full text linkAn incorrect or incomplete repair card, typically used in aviation maintenance for reporting failures, may result in incorrect maintenance and make it very hard to analyse the maintenance data. There are several reasons for this incomplete reporting. Firstly, (part of) the information is often unknown at the moment the maintenance crew fills in the card. Also, the findings on repair cards are generally filled out as freeform text, making it difficult to automatically interpret the findings. An automatically assessed failure description will lead to more complete and consistent repair cards. This will also improve the efficiency of troubleshooting since this failure diagnosis can add information which would otherwise not be at the disposal of the maintenance crew at that time. This research will utilise a data driven approach combining maintenance and usage data. The model will be based on Artificial Intelligence (AI) such that it is no longer necessary to completely understand the physics of a (sub)system or component. XAI (eXplainable AI) will be added to the model to provide transparency and interpretability of the assessed diagnosis. The different steps towards this failure diagnosing model are applied to a case study with a main wheel of the RNLAF (Royal Netherlands Air Force) F-16. This preliminary feasibility study already showed the value of this automated failure diagnosis model with an improvement in diagnosis accuracy from 60% to 69%
Enhanced Data Driven Decision Support
Full text linkAs items are increasingly being equipped with sensors, the applicability of data driven decision support will similarly grow. This paper surveys an endeavor to support decisions with sensor recordings that were coincidentally available. To become meaningful decision support, these sensor recordings should enable better causal inferences because decisions are intended to cause the future. However, data driven decision support is not trivial as normative decision theory is known to suffer from validation issues. This work attempts to alleviate concerns about (i) the assessment of preference, (ii) causal inferences from non-experimental data and (iii) the assessment of the uncertainty about the prospective outcome of a decision. This work will demonstrate that sensor recordings indeed can provide appreciable decision support by presenting two typical cases of human recorded events that were enriched with sensor recordings. From these sensor recordings, prima facie causes and effects of a decision maker’s concern were inferred. These type of inferences may potentially have a considerable impact on conventional maintenance policy assessments following a reliability centered maintenance process. Reliability centered maintenance merely anticipates on the believed consequences of failures by scheduled inspections, overhauls or discards. As sensor recordings are efficiently collected at a high sampling rate, scheduling inspections may become superfluous. Sight on the prima facie causes of failures may enable a kind of proactive control of failures that has not been addressed in the decision logic of a reliability centered maintenance process
A Bayesian assessment for railway track geometry degradation prognostics
Full text linkAdvanced PHM techniques have the potential to substantially reduce railway track maintenance costs while increasing safety and availability. However, there is still a significant lack of knowledge and experience in relation to suitable PHM models and algorithms within the context of railway track geometry degradation. This paper proposes a Bayesian model class methodology for prognostics performance assessment whereby different prognostics algorithms can be rigorously assessed and ranked according to their relative probability to predict the future degradation process. The proposed framework is exemplified and tested for a case study about track degradation prognostics using published data about track settlement, taken from a simulated traffic loading experiment carried out at the Nottingham Railway Test Facility
- …
