A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines

Nguyen, Khanh T. P.; Medjaher, Kamal; Tran, Do T.

doi:10.1007/s10462-022-10260-y

Cited by 41 publications

(10 citation statements)

References 232 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of PHM is to optimize operational readiness by employing affordable, integrated, and embedded diagnostics and prognostics, embedded training and testing, serialized item management, automatic identification technology (AIT), and iterative technology refreshes [10]. The PHM method has been widely applied in many industries, and many reviews of industrial applications have been published [11][12][13][14][15].…”

Section: Basics Of Phm Methodologymentioning

confidence: 99%

The Optimization of a Model for Predicting the Remaining Useful Life and Fault Diagnosis of Landing Gear

Chang,

Hsu,

Hsu

et al. 2023

Aerospace

View full text Add to dashboard Cite

With the development of next-generation airplanes, the complexity of equipment has increased rapidly, and traditional maintenance solutions have become cost-intensive and time-consuming. Therefore, the main objective of this study is to adopt predictive maintenance techniques in daily maintenance in order to reduce manpower, time, and the cost of maintenance, as well as increase aircraft availability. The landing gear system is an important component of an aircraft. Wear and tear on the parts of the landing gear may result in oscillations during take-off and landing rolling and even affect the safety of the fuselage in severe cases. This study acquires vibration signals from the flight data recorder and uses prognostic and health management technology to evaluate the health indicators (HI) of the landing gear. The HI is used to monitor the health status and predict the remaining useful life (RUL). The RUL prediction model is optimized through hyperparameter optimization and using the random search algorithm. Using the RUL prediction model, the health status of the landing gear can be monitored, and adaptive maintenance can be carried out. After the optimization of the RUL prediction model, the root-mean-square errors of the three RUL prediction models, that is, the autoregressive model, Gaussian process regression, and the autoregressive integrated moving average, decreased by 45.69%, 55.18%, and 1.34%, respectively. In addition, the XGBoost algorithm is applied to simultaneously output multiple fault types. This model provides a more realistic representation of the actual conditions under which an aircraft might exhibit multiple faults. With an optimal fault diagnosis model, when an anomaly is detected in the landing gear, the faulty part can be quickly diagnosed, thus enabling faster and more adaptive maintenance. The optimized multi-fault diagnosis model proposed in this study achieves average accuracy, a precision rate, a recall rate, and an F1 score of more than 96.8% for twenty types of faults.

show abstract

Section: Basics Of Phm Methodologymentioning

confidence: 99%

The Optimization of a Model for Predicting the Remaining Useful Life and Fault Diagnosis of Landing Gear

Chang,

Hsu,

Hsu

et al. 2023

Aerospace

View full text Add to dashboard Cite

show abstract

“…As technology advances, GBD studies are poised to benefit from emerging trends and technological advancements. Integration of artificial intelligence (AI) and machine learning algorithms can streamline data analysis, improve disease modeling, health management and enhance the accuracy of burden estimates [42], [43]. Stakeholders have opined that responsibly and ethically leveraging on AI can help reduce global disease burden and improve population health-outcomes [44]- [46].…”

Section: Emerging Trends and Future Directionsmentioning

confidence: 99%

Review of global burden of disease studies: trends, challenges, and future directions

Otorkpa,

Emmanuel

et al. 2024

IJPHS

View full text Add to dashboard Cite

Global burden of disease (GBD) studies plays an important role in assessing the variability of risk factors, injuries, and diseases worldwide, providing essential evidence for policy-making and healthcare planning. This study presents a review of current literature on GBD studies, aiming to analyze the trends, challenges, and future directions in this field. We conducted a review of published GBD studies from inception to date, utilizing major scientific databases and relevant sources. Our findings reveal several noteworthy trends in GBD studies. Over the years, GBD studies have expanded to cover a wider range of diseases and risk factors, providing a more comprehensive understanding of global health. Advances in data availability, technology, and modeling techniques have improved the accuracy of disease burden estimates. The inclusion of disability-adjusted life years (DALYs) has enabled comparisons as well as prioritization of interventions. However, challenges remain, such as limited data in middle and low-income countries and methodological complexities. The COVID-19 pandemic has emphasized the need for responsive methodologies. Future directions include strengthening data collection, utilizing machine learning, big data analytics, ethical use of artificial intelligence and promoting collaboration for consistent GBD studies.

show abstract

“…All proposed definitions are correct, but in the authors' view, the main difference is the range of devices that can be defined. Specifically, one definition states that an AI system can only be created by a human, whereas the other is not limited to human involvement in the creation process (Nguyen et al, 2023). One definition is more general, while the other is narrower, attempting to define the characteristics, functions and types of such systems more precisely.…”

Section: Data Ownershipmentioning

confidence: 99%

Data ownership in training artificial intelligence in healthcare

Žukovs,

Upenieks

2023

SOCRATES

View full text Add to dashboard Cite

"In the framework of this article, we research whether, according to the national regulation of Latvia, the data used in the training of artificial intelligence (AI) in medicine can be considered an object of property rights. An analytical and descriptive method will be used for the research. The analytical method will help analyse the data as a property term and determine its principles. Meanwhile, the descriptive method will describe the AI technology definition and processes. The work will clarify whether Latvia should provide a more transparent and fairer approach to patient data and their right to fully manage it, based on the examples of Finland and Belgium. We cannot consider all personal data objects of property rights in civil law because it is difficult to determine the beginning and end of personal data. However, personal data obtained from an organisation and stored in the personal cloud are considered an object of property rights. At the same time, by analogy, it can be concluded that ownership rights to data may also exist in other circumstances, depending on the type of data and its storage location. Keywords: personal data, property rights, civil law, medicine law."

show abstract

A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines

Cited by 41 publications

References 232 publications

The Optimization of a Model for Predicting the Remaining Useful Life and Fault Diagnosis of Landing Gear

The Optimization of a Model for Predicting the Remaining Useful Life and Fault Diagnosis of Landing Gear

Review of global burden of disease studies: trends, challenges, and future directions

Data ownership in training artificial intelligence in healthcare

Contact Info

Product

Resources

About