Estimating the remaining useful life (RUL) of an asset lies at the heart of prognostics and health management (PHM) of many operations-critical industries such as aviation. Mod- ern methods of RUL estimation adopt techniques from deep learning (DL). However, most of these contemporary tech- niques deliver only single-point estimates for the RUL without reporting on the confidence of the prediction. This practice usually provides overly confident predictions that can have severe consequences in operational disruptions or even safety. To address this issue, we propose a technique for uncertainty quantification (UQ) based on Bayesian deep learning (BDL). The hyperparameters of the framework are tuned using a novel bi-objective Bayesian optimization method with objectives the predictive performance and predictive uncertainty. The method also integrates the data pre-processing steps into the hyperparameter optimization (HPO) stage, models the RUL as a Weibull distribution, and returns the survival curves of the monitored assets to allow informed decision-making. We vali- date this method on the widely used C-MAPSS dataset against a single-objective HPO baseline that aggregates the two ob- jectives through the harmonic mean (HM). We demonstrate the existence of trade-offs between the predictive performance and the predictive uncertainty and observe that the bi-objective HPO returns a larger number of hyperparameter configurations compared to the single-objective baseline. Furthermore, we see that with the proposed approach, it is possible to configure models for RUL estimation that exhibit better or comparable performance to the single-objective baseline when validated on the test sets.
DOCUMENT
From the article: Abstract The Information Axiom in axiomatic design states that minimising information is always desirable. Information in design may be considered to be a form of chaos and therefore is unwanted. Chaos leads to a lack of regularities in the design and unregulated issues tend to behave stochastically. Obviously, it is hard to satisfy the FRs of a design when it behaves stochastically. Following a recently presented and somewhat broader categorization of information, it appears to cause the most complication when information moves from the unrecognised to the recognised. The paper investigates how unrecognised information may be found and if it is found, how it can be addressed. Best practices for these investigations are derived from the Cynefin methodology. The Axiomatic Maturity Diagram is applied to address unrecognised information and to investigate how order can be restored. Two cases are applied as examples to explain the vexatious behaviour of unrecognised information.
MULTIFILE
This book is both a short introduction to the recent developments, challenges and opportunities in Aviation Maintenance, Repair and Overhaul(MRO), and at the same time, a presentation of the research focal areas and the key waypoints towards smarter and more sustainable MRO. Innovation and integration have always been key aspects of Aviation. Currently, evolutions in aircraft design, materials and production techniques are ahead of the MRO practices in use.This gap is creating demand for new knowledge to develop and operationalise adaptive, digital and sustainable MRO tools, applicable or integrated in modern aircraft systems and components.
DOCUMENT
Design educators and industry partners are critical knowledge managers and co-drivers of change, and design graduate and post-graduate students can act as catalysts for new ideas, energy, and perspectives. In this article, we will explore how design advances industry development through the lens of a longitudinal inquiry into activities carried out as part of a Dutch design faculty-industry collaboration. We analyze seventy-five (75) Master of Science (MSc) thesis outcomes and seven (7) Doctorate (PhD) thesis outcomes (five in progress) to identify ways that design activities have influenced advances in the Dutch aviation industry over time. Based on these findings, we then introduce an Industry Design Framework, which organizes the industry/design relationship as a three-layered system. This novel approach to engaging industry in design research and design education has immediate practical value and theoretical significance, both in the present and for future research. https://doi.org/10.1016/j.sheji.2019.07.003 LinkedIn: https://www.linkedin.com/in/christine-de-lille-8039372/
MULTIFILE
Het lectoraat Innoverend ondernemen verbonden aan De Haagse Hogeschool heeft op 12 november 2015 een seminar georganiseerd over nieuwe businessmodellen en de nieuwe economie. Van deze dag hebben we een verslag gemaakt middels deze uitgave. Een interessant naslagwerk voor alle ruim 150 deelnemers van dit seminar, die kunnen teruglezen wat ze deze dag hebben geleerd, maar ook kunnen leren van de workshops waarin ze niet hebben geparticipeerd. Daarnaast is deze uitgave leerzaam voor iedereen die geïnteresseerd is in nieuwe businessmodellen vanuit verschillende perspectieven, waarin theorie en praktijk samen komen.
DOCUMENT
Airline ground operations are subject to the conflicting demands of short turn-around times and safety requirements. They involve multiple parties, but are less regulated than airborne processes. Not surprisingly, more than a quarter of all aircraft incidents occur on the ground. These incidents lead to aircraft damage and associated costs, risk of injuries, and can potentially impact in-flight safety. KLM Ground Services has targeted platform safety performance as an area for improvement. However, existing safety awareness programs have had limited effect. A direct link between safety culture surveys and safety performance has not been established, and therefore these are insufficient to give adequate feedback on interventions. Newly developed by the Texas University are the Line Operations Safety Assessments (LOSA), first targeted at cockpit operations. Variants are available since October 2010 for the platform and maintenance environments. The research group for Aviation Engineering at the Amsterdam University of Applied Sciences has used the original platform LOSA material and tailored these to the specific circumstances at KLM. Results to date show that with these modifications, platform LOSA is a useful tool to quantify safety performance and to generate trend data. The effect of safety interventions can now be monitored. Referentie de Boer, R.J., Koncak, B., Habekotté, R., & van Hilten, G.J. (2011), Introduction of ramp-LOSA at KLM Ground Services , Human Factors and Ergonomics Society Annual Meeting, Leeds, United Kingdom
DOCUMENT
The current systematic framework of aviation has developed complex air transport systems where reliability and performance are sensitive and instantly adaptive to the supply side due to the growing and elevated degree of demand in aviation market circumstances. The role of quality measurements has increased. Determining quality performance indicators is difficult because of the system's uniqueness, interdependency, and unsupportable characteristics. This is accomplished by using the 'analytical hierarchy process (AHP)' by developing a survey based on a three-level hierarchical model of the air transport supply-side quality dispersed among four groups of aviation professionals, namely 1) pilots 2) ATCOs 3) aircraft engineers, and 4) aviation managers. The scope of this study is to analyse the crucial components of the present air transportation system and draw a distinction between all the current system components.
DOCUMENT
"The World of the [open] innovator" described the background of the revolution we are in in innovation and what the consequences are for innovation, changing towards design driven open innovation. We reframed innovation to meet new needs and values of companies and organizations in our work field. We do not take this light-hearted. We know the field of innovation and used our experience and conversation with stakeholders to come up with the insight of The [open] Innovator. What strengthened us were reactions from companies and organization we asked to cocreate or participate. There seemed to be an instant recognition and appeal to our vision and approach. But we also realize that we are in the stage of prototyping and we need you, as our lead users to be critical, yet to trust us. You, being an [open] innovator, will do great wonders, because you will be taught to deal with this uncertainty and dig in new, unknown situations or problems. You will learn the tools for research, for communication, for visualization. You will become a cooperative, open-minded problem solver. You will be able - with all the skills and tools we will provide you - to make the difference. But we need you to reflect upon your progress and needs; help us to get an insight in to your uncertainties, values and unmet needs, to enable us to improve our thinking and teaching. However, innovation can only be learned by doing! Start cracking, start experimenting, start having fun. Welcome to the future, that has just started.
DOCUMENT
![The World of the [open] innovator](https://publinova-harvester-content-prod.s3.amazonaws.com/thumbnails/files/previews/pdf/20250506150122198446.042ed686-762c-429d-ba80-1c82380cb051-thumbnail-400x300.png)
Data-driven condition-based maintenance (CBM) and predictive maintenance (PdM) strategies have emerged over recent years and aim at minimizing the aviation maintenance costs and environmental impact by the diagnosis and prognosis of aircraft systems. As the use of data and relevant algorithms is essential to AI-based gas turbine diagnostics, there are different technical, operational, and regulatory challenges that need to be tackled in order for the aeronautical industry to be able to exploit their full potential. In this work, the machine learning (ML) method of the generalised additive model (GAM) is used in order to predict the evolution of an aero engine’s exhaust gas temperature (EGT). Three different continuous synthetic data sets developed by NASA are employed, known as New Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS), with increasing complexity in engine deterioration. The results show that the GAM can be predict the evolution of the EGT with high accuracy when using several input features that resemble the types of physical sensors installed in aero gas turbines currently in operation. As the GAM offers good interpretability, this case study is used to discuss the different data attributes a data set needs to have in order to build trust and move towards certifiable models in the future.
DOCUMENT
Deze tekst beschrijft de globale digitale kloof. Daarbij wordt opgemerkt dat we ons niet mogen laten verleiden door de simpliciteit van het meetbare, t.w. het al dan niet hebben van een computer met internettoegang. De digitale kloof kent immers meerdere dimensies, waarvan bezit maar een is. Zo moet er bv. ook relevante inhoud beschikbaar zijn. Het is schrijnend te observeren dat er op internet massaal informatie beschikbaar is over ingeblikt voedsel voor huisdieren, maar weinig hoe cholera te vermijden. Waarom zou iemand in het zuiden dan op internet gaan ? Op het einde van deze tekst wordt de digitale kloof vergeleken met een eenhoorn.
DOCUMENT
