Dynamic artificial neural network-based reliability considering operational context of assets.

Izquierdo, Juan Santiago Murgui; Márquez, Adolfo Crespo; Uribetxebarria, Jone

doi:10.1016/j.ress.2019.03.054

Cited by 36 publications

(17 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, much of the current literature on RAM analysis pays attention to the modelling and accurate estimation of reliability [52], [53]. This attention is motivated by the importance of such analysis when making decisions to improve operational safety and economical efficiency of the assets in a riskbased approach.…”

Section: A Data Analysis Modulementioning

confidence: 99%

Asset Management Framework and Tools for Facing Challenges in the Adoption of Product-Service Systems

Erguido

Márquez

Castellano

et al. 2022

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

Servitisation is recognized as a key business strategy for Original Equipment Manufacturers willing to move up the value chain. However, several barriers have to be overcome in order to successfully integrate products and services. Many of these barriers are caused by the technical challenges associated with the design and management of the product-service systems, such as life cycle service level and cost estimation, risk management, or the system design and pricing.Asset management presents itself as a key research area in order to overcome these barriers as well as to integrate product-service systems within the manufacturers' operations management. It is the scope of this paper to provide theoretical and practical insights with regards to the alignment of asset management and product-service system research areas. To support the alignment between both areas, a management framework which gathers specific technologies, including reliability analysis, simulation modelling and multi-objective optimisation algorithms, is presented. The purpose of the framework is to provide manufacturers with a decision-support tool that facilitates the main managerial challenges faced when implementing a servitisation strategy.The paper contributions are successfully applied to case studies in the railway and wind energy sectors based on real field data, thereby demonstrating their suitability for both facilitating manufacturer's decisionmaking process and better satisfying stakeholders' interests. MANAGERIAL RELEVANCE STATEMENTShifting from product-oriented to service-oriented business models could become critical for those manufacturers aiming at moving up the value chain for a better future market position. However, such business models imply to assume the ownership of the products that they used to sell, and in rather unknown scenarios. Thus, products become manufacturers' assets, which need to be managed for them to provide value to their businesses over their entire life cycle.The lack of asset management capabilities at manufacturers' side may develop a serious risk that is further translated into barriers hindering service-oriented business models adoption. Such barriers are related to difficulties, for instance, to properly define the product-service system contracts or to fulfil stakeholders' requirements during the system life cycle in highly uncertain scenarios.In this context, the present paper proposes a management framework to provide manufacturers some of the capabilities needed to overcome above mentioned barriers, helping them to design and manage successful 2 product-service systems.The framework designed consists of analytical and empirical models providing advanced capabilities for product-service systems management. Likewise, the paper helps manufacturers understand the managerial insights that such capabilities may provide them along their different decision processes, which are further illustrated through wind energy and railway case studies. AbstractServitisation is recognized as a key business strategy f...

show abstract

Section: A Data Analysis Modulementioning

confidence: 99%

Asset Management Framework and Tools for Facing Challenges in the Adoption of Product-Service Systems

Erguido

Márquez

Castellano

et al. 2022

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

show abstract

“…Different techniques of data analysis are already applied in the rail sector, such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Random Forests (RF) [22][23][24][25]. Regarding asset management, different studies exist in the literature [26][27][28]. Ghofrani et al [29], Thaduri et al [30], Pipe et al [31], and Lee et al [32] developed data-driven models able to forecast the status of assets in order to achieve predictive maintenance strategies.…”

Section: Literature Reviewmentioning

confidence: 99%

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

et al. 2020

View full text Add to dashboard Cite

The objective of this study is to show the applicability of machine learning and simulative approaches to the development of decision support systems for railway asset management. These techniques are applied within the generic framework developed and tested within the In2Smart project. The framework is composed by different building blocks, in order to show the complete process from data collection and knowledge extraction to the real-world decisions. The application of the framework to two different real-world case studies is described: the first case study deals with strategic earthworks asset management, while the second case study considers the tactical and operational planning of track circuits’ maintenance. Although different methodologies are applied and different planning levels are considered, both the case studies follow the same general framework, demonstrating the generality of the approach. The potentiality of combining machine learning techniques with simulative approaches to replicate real processes is shown, evaluating the key performance indicators employed within the considered asset management process. Finally, the results of the validation are reported as well as the developed human–machine interfaces for output visualization.

show abstract

“…Currently, the most widely used proxy models are polynomial response surface proxy model [11], Kriging proxy model [12][13][14], radial basis function proxy model [15,16], and BP neural network proxy model [17][18][19]. Among them, the BP neural network proxy model significantly improves the robustness of the overall design of the mechanical structure with low calculation cost and high noise processing capability.…”

Section: Introductionmentioning

confidence: 99%

Motion Reliability Analysis of Unlocking Trigger Device Based on CPSO-BR-BP Neural Network with Uncertain Parameters

Tian

Fan

Zhang

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Aiming at overcoming the problem that the mechanism function of the unlocking trigger device is difficult to obtain and the corresponding reliability analysis cannot be performed, a motion reliability analysis method based on the CPSO-BR-BP neural network proxy model is proposed. Firstly, the particle swarm algorithm is optimized through the chaotic sequence, and the back-propagation (BP) neural network is optimized using Chaos Particle Swarm Optimization (CPSO) and Bayesian Regularization (BR) algorithm. The CPSO-BR-BP neural network proxy model is established, and the reliability of shape memory alloys (SMA) wire unlocking based on the structural function is calculated. Moreover, according to the structural function of the separation process, the motion reliability based on the proxy model and the improved membership function is calculated. Finally, a series reliability model is established based on the unlocking process and the separation process to calculate the reliability of the whole machine. The reliability of the unlocking trigger device is analyzed by the proposed method. Results show that the proposed method is computationally efficient with the calculated reliability of 0.9987.

show abstract

Dynamic artificial neural network-based reliability considering operational context of assets.

Cited by 36 publications

References 53 publications

Asset Management Framework and Tools for Facing Challenges in the Adoption of Product-Service Systems

Asset Management Framework and Tools for Facing Challenges in the Adoption of Product-Service Systems

On Applying Machine Learning and Simulative Approaches to Railway Asset Management: The Earthworks and Track Circuits Case Studies

Motion Reliability Analysis of Unlocking Trigger Device Based on CPSO-BR-BP Neural Network with Uncertain Parameters

Contact Info

Product

Resources

About