A review of model based and data driven methods targeting hardware systems diagnostics

Abstract

System health diagnosis serves as an underpinning enabler for enhanced safety and optimized maintenance tasks in complex assets. In the past four decades, a wide-range of diagnostic methods have been proposed, focusing either on system or component level. Currently, one of the most quickly emerging concepts within the diagnostic community is system level diagnostics. This approach targets in accurately detecting faults and suggesting to the maintainers a component to be replaced in order to restore the system to a healthy state. System level diagnostics is of great value to complex systems whose downtime due to faults is expensive. This paper aims to provide a comprehensive review of the most recent diagnostics approaches applied to hardware systems. The main objective of this paper is to introduce the concept of system level diagnostics and review and evaluate the collated approaches. In order to achieve this, a comprehensive review of the most recent diagnostic methods implemented for hardware systems or components is conducted, highlighting merits and shortfalls.

The Benefits in Coupling Exergy Analysis and Life Cycle Assessment in the Context of Sustainable Manufacturing for Industry 4.0: A Real Industrial Case

“…Among the modelling techniques [18], and relevant to big data analytics, there are a) the model-based approach, that represents the real system involving the construction of a mathematical/physical model from the input parameters measured; b) the data-driven approach, focused on the analysis of a large number of raw historical data, came from a network of sensors and actuators, up until the creation of knowledge and behavioral models of the system itself. To this approach belong machine learning and data mining; c) the expert-system approach, method that emulates the decision-making ability of a human expert by solving a problem by reasoning about knowledge, and not by following the procedure of a developer as is the case in conventional programming.…”

Data-Driven Fault Diagnosis for Electric Drives: A Review

“…After that, the mathematical model output (ŷ) is compared with the output of the real system (y), generating residual signals (r) which will determine if there is a fault in the system using a residual evaluator [36], as it can be seen in Figure 5. According to [36,39,40], there are three different model-based approaches: the parameter estimation approach, the parity space approach and the observer-based approach. • Data-driven methodology: The basis of DD methods is to take advantage of large amount of historic datasets acquired from the system under investigation by means of Machine Learning or advanced statistical models [36,41].…”

Design of a Metro Door System and Determination of Main Loads

“…Consequently, numerous requirements must be met, namely those related to fire protection, acoustic and thermal insulation [3,5], electronic devices, reliability, availability, maintainability, safety, protection against current and various environmental conditions and loads caused by vibrations, which rise when riding on a track at various speeds [12,33]. Great emphasis is put on noise protection, as this well-known negative phenomenon is a consequence of every braking process [6,7,24,28].…”