215 research outputs found
Enhanced Data Driven Decision Support
Get PDFAs 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
Don't make everything predictable
Get PDFEen volledige fabriek uitrusten met sensoren en daarop voorspellend onderhoudtoepassen, is nu nog veel te kostbaar. Veel efficiënter is dit te doen bij de toptienvan meest kritische installaties, adviseert prof. dr. ir. Tiedo Tinga. In EuropoortKringen praat hij over de beperkingen van artificial intelligence, de vorderingenvan het project PrimaVera en zijn verwachting hoe predictive maintenance zich dekomende jaren gaat ontwikkelen
Rail Wear Estimation for Predictive Maintenance:a strategic approach
Get PDFSince 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)
Get PDFAn 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%
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
Predictive maintenance of military systems based on physical failure models
Get PDFPreventive maintenance is required to keep critical systems available at reasonable costs. Instead of applying the traditional experience-based approach of statistical analysis of failure data, the present paper proposes to adopt a predictive maintenance policy that relies on detailed knowledge of the physical failure mechanisms. A structured scheme for this approach is presented. Then three case studies from the military, a helicopter, a naval gas turbine and a military vehicle, are used to demonstrate the benefits of this approach
Innovative predictive maintenance concepts to improve life cycle management
Get PDFFor naval systems with typically long service lives, high sustainment costs and strict availability requirements, an effective and efficient life cycle management process is very important. In this paper four approaches are discussed to improve that process: physics of failure based predictive maintenance, advanced data analysis, condition based maintenance and maintenance optimization. For all these approaches, understanding of the failure behaviour and quantifying the effects of variations in usage of the system appear to be the key factor for improvements
- …
