Table 1.
The overview of definitions and approaches connected to the condition monitoring of rail transport systems. Source: own elaboration based on references directly mentioned in the table.
| Definition | Year of Publication |
Source |
|---|---|---|
| “The condition monitoring systems developed so far in rail vehicle applications are mainly based on the direct measurement of relevant signals, which are analysed using time and/or frequency domain signal processing, e.g., to find features or signatures related to particular faults [43,44]).” | 2008 | [45] |
| “(…) condition monitoring in today’s complex systems is mostly regarded as an alarm tool for maintenance [40]. Even the ISO 17359 defines, how a condition monitoring policy should look like to establish a successful maintenance strategy [41].” | 2009 | [42] |
| “Condition monitoring systems are used to collect both digital and analogue signals within a location room utilizing distributed transducers connected to either point-to-point or digital bus communication links. They often contain some kind of alarm system based around thresholding techniques, the limits being set by local maintenance personnel who have to inspect the recorded signatures daily to attempt to anticipate any failures. No diagnostic capabilities are provided. (…) Fault detection and diagnosis systems are a more advanced version of condition monitoring systems, incorporating ‘intelligent’ algorithms capable of detecting faults prior to failure, diagnosing the incipient fault and providing some indication of the criticality of the detected fault.” | 2009 | [39] |
| “Condition monitoring is necessary in order to immediately detect vehicle faults. For condition monitoring, it is necessary to detect the fault from the signals of sensors attached to the vehicles [2]. Condition monitoring can be considered to be a part of the well-established and well-developed area of Fault Detection and Isolation (or Identification) (FDI).” | 2010 | [38] |
| “Condition monitoring measures are crucial to ensure safe and cost-effective train operation in the railroad transportation industry. A well-designed monitoring system substantially reduces hardware maintenance cost and improves service quality and overall safety.” | 2012 | [37] |
| “Condition monitoring technology within the railway industry has proliferated in recent years; this is due to the continuous improvement of electronic-based systems. This has created a unique situation for implementing proactive condition monitoring technology in the railway industry. This approach will create the possibilities of identifying failing systems while the asset is in operation before they create catastrophic damage. Economically, most of these proactive products are wayside condition monitoring systems and very few sensors are few sensors are directly mounted on the vehicles.” | 2012 | [6] |
| “Condition monitoring of vehicles allows to track the development of their technical degradation, which allows to implement rational preventive and remedial activities in order to avoid unpredictable downtimes related to the damages and serious failures. The reason for continuous improvement of vehicles’ condition monitoring methods are stricter and stricter requirements concerning the reliability and safety of both all transport system and separate means of transport.” | 2013 | [36] |
| “Condition monitoring requires the gathering of data and processing of that data into useful information to support design, availability, reliability and maintenance practices.” | 2014 | [35] |
| “Condition monitoring aims to record the current (real-time) condition of a system [33].” | 2014 | [34] |
| “Condition monitoring detects and identifies deterioration in structures and infrastructure before the deterioration causes a failure or prevents rail operations. In simple condition monitoring, sensors monitor the condition of a structure or machinery. If the sensor readings reach a predetermined limit or fault condition, then an alarm is activated. However, this simplistic approach may lead to a large number of false alarms and missed failures [31]. (…) Condition monitoring can be performed continuously or periodically. Continuous monitoring should detect a problem straight away but it is often expensive; energy hungry, which is a problem for WSNs where the network components need power; and the sensor data are very noisy, which requires careful preprocessing to ensure accurate diagnostics. Periodic monitoring is cheaper, uses less energy, and allows time for data cleaning and filtering but a problem will only be diagnosed at the next processing run. (…) In basic condition monitoring, the system is only able to distinguish between normal and abnormal conditions (no fault or fault).” | 2014 | [32] |
| “Under this framework, the condition-based monitoring (CBM), as a technique to provide prognosis and diagnosis of component degradation, allows to detect the in-service failures and contributes to the decision-making for improving the system performance [19,26]. Distinguished from the conventional fault detection carried out in the depot, this technique is aiming at the online identification of the component performance on the operational conditions.” | 2016 | [30] |
| “Technologies that can perform condition monitoring and condition-based maintenance are thus of significant interest to identify and predict progressing degradation trends and optimally schedule maintenance actions to lower maintenance costs and downtime.” | 2016 | [29] |
| “Condition monitoring is referred to as a process of monitoring the condition of the objective where the relevant parameters are measured in order to determine the significant changes which is indicative of a developing fault. Considering the railway system, the objectives to be monitored could be: [v]ehicle components such as wheels, axle bearings and brake pads, [i]nfrastructure such as the track, rail beds and bridges or [p]assengers/goods within train cars.” | 2017 | [28] |
| “Condition monitoring can be considered to be a part of the well-established area of Fault Detection and Isolation (or Identification) (FDI) [25]. Condition monitoring is mainly applicable to system that deteriorate in time. The aim of condition monitoring is to detect and isolate deterioration before it causes a failure [2,26].” | 2017 | [27] |
| “Railway track and rolling stock condition monitoring is essential in ensuring the safe and efficient function of railway systems. The ability to use an instrumented revenue vehicle for the condition assessment of rail tracks is particularly significant because this capability will not require track access during inspection. This instrumented vehicle can also provide useful data for the definition of the rail track input conditions for the assessment of the stability of a rail vehicle when traversing along the track.” | 2017 | [24] |
| “Railway inspection is normally conducted periodically every year or several months. It may take too much time to rapidly detect faults in the track that may cause collapse or huge loss, as is the case in the prompt identification of rail defects. (…) Hence, condition monitoring of rail infrastructure has become important for setting proper predictive maintenances before defect and failure take place. (…) Condition monitoring can reduce maintenance and its costs by detecting the faults before they can cause damage or prevent rail operations [22].” | 2018 | [23] |
| “Condition monitoring is defined as the practice of monitoring parameters of a system or component, with the intent of getting deeper knowledge of how that system changes and deteriorates with time. If key parameters that can be linked to wear, faults and degradation can be monitored, emerging problems can quickly be found or even predicted.” | 2018 | [21] |
| “Condition monitoring is based on the regular acquisition of machine conditions or their components by measuring and analyzing physical quantities. These are compared by the system with specified conditions and serve for diagnosis decisions [14,18,19].” | 2018 | [20] |
| “Condition monitoring is a suitable way to detect impending vehicle failures and acoustically critical trams immediately but under the aspect of conservation of resources (exploitation of wear reserves of tribological components). In order to implement such concepts, the tram operator has to be able to quickly and accurately record the current technical condition of the vehicle in order to initiate appropriate counteractions and keep downtimes to a minimum.” | 2019 | [17] |
| “A better way to avoid breakdowns is a maintenance strategy that monitors and report in real-time the condition of a machine or device in use, a key principle of Industry 4.0, so its remaining life can be estimated. This is called ‘condition monitoring’ and ‘diagnostic engineering management’. Researchers have noted considerable evidence that ‘condition-based maintenance’ gives economic advantages in most industries and is the best available strategy for preventing unexpected system downtime [11,12,13,14,15].” | 2019 | [16] |
| “The condition monitoring of railway vehicles has traditionally relied on signal processing and knowledge-based techniques but, on the other hand, modelling techniques give great potentials due to the a priori knowledge included in the model.” | 2019 | [10] |
| “Modern condition monitoring systems have led fault diagnosis to enter the era of big data, which lead to the obsolescence of traditional physics-based fault diagnosis methods [8].” | 2019 | [9] |
| “Condition monitoring of railway vehicle and track dynamics are monitored via track-based systems or vehicle-based systems ([6] [– actualized by the authors]. Systems that are track-based are usually used for monitoring the condition of wheelsets, where vehicle-based systems are used to monitor the condition of the bogie, suspension and ride comfort. (…) Condition monitoring systems are made up of sensors and collective data processing hardware are software this all has to be mounted onto the desired rolling stock in the correct location to gain the desired results.” | 2020, 2012 | [6,7] |
| “(…) the condition of complex systems is typically monitored by a large number of different types of sensors, capturing e.g., temperature, pressure, flow, vibration, images or even video streams of system conditions, resulting in very heterogeneous condition monitoring data at different time scales.” | 2020 | [5] |
| “Condition Monitoring (CM) is an efficient and achievable way to ensure the reliability of suspension systems, therefore, numerous scholars have focused on developing suitable approaches to monitor the suspension systems ([2,3]).” | 2020 | [4] |
| “(…) two generally concerned questions of condition monitoring [are the subject of researchers’ interest—added by the paper’s authors]: (i) evaluating the diagnosability and isolatability of a system with existing sensor network; and (ii) finding out a quantity-optimum set of sensors for a desired diagnosability and isolatability of a system.” | 2020 | [1] |