Application of Statistical Techniques and Neural Networks in Condition‐Based Maintenance

Abstract

In this paper, we have evaluated five prediction approaches from two disciplines for condition-based maintenance. It also includes a case study for vehicle tire pressure monitoring as an example application. Main focus of this paper is on two widely used areas in prediction: (i) statistics, (ii) neural networks. It is well known that these two areas have wide applications in forecasting. Statistical and neural network techniques are very powerful for predicting the future states based on current and previous states of the system or subsystem. Application of ARAR and Holt-Winters (HW) in CBM has been presented from the statistics point of view. On the other hand, application of focused time delay, linear predictor, and backpropagation neural network has also been presented to prove the robustness of statistical approaches. Paper presents detailed comparative simulation study to show the suitability and feasibility of all the techniques. We assumed that the sensors are directly mounted on tires externally and report the current tire pressure to control or analysis. The control unit performs tire pressure analysis and reports the decision to operator or intended group about current pressure as well as the impending pressure conditions. Finally, investigation ends with conclusion that HW is best suited among these five approaches for tire pressure prediction and could be useful to design a CBM application for any system.3.3.1. Neural network topologies and training. The neural networks exist mainly in two forms: static and dynamic. Static networks 28 are traditional input » process » output-based networks, also called feed-forward networks or memory-less networks. In such networks, input to a layer depends only on preceding layer. The static neural networks have wide applications in maintenance engineering and A. PRAJAPATI AND S. GANESAN The time-based maintenance 8 is a maintenance based on predefined intervals, no matter what is the condition at that time. For example, oil change in car is periodic either based on mileage or interval, significant portion of its life may be still left. B. Condition Based MaintenanceCondition Based maintenance 5 deals with monitoring the condition of mission critical and safety-critical parts in carrying out maintenance whenever necessary to avoid hazards rather than following a fixed schedule. C. Condition-Based Maintenance Plus (CBM+)The CBM + includes RCM analysis other than regular CBM component. Again air force definition of CBM + 5 is as follows, 'Condition Based Maintenance Plus (CBM+) expands upon these basic concepts, encompassing other technologies, processes, and procedures that enable improved maintenance and logistics practices. These future and existing technologies, processes, and capabilities will be addressed during the capabilities planning, acquisition, sustainment, and disposal of a weapon system.' D. Reliability Center MaintenanceRCM 2 enables the formulation of the maintenance strategy by selecting the right mix of corrective maintenance, scheduled based mainten...

Predictive maintenance, its implementation and latest trends

“…In addition to the above approach, that is, defining another type of maintenance that is beyond PdM, CBM+ was reported to be another type of maintenance: ‘The CBM+ includes RCM analysis other than regular CBM component’, RCM denoting reliability centre maintenance. 22…”

Single-stage Kanban system with deterioration failures and condition-based preventive maintenance

“…Ivy and Nembhard [22] propose an approach that integrates simulation, statistical quality control and partially observable Markov decision processes to construct maintenance policies. Prajapati and Ganesan [23] present a case study where statistical techniques and artificial neural networks are used to predict the future deterioration state of the controlled system in order to facilitate condition-based maintenance actions. Their work involves a vehicle tire pressure monitoring application.…”

Data Preparation in Machine Learning for Condition-based Maintenance

“…Diez-Olivan et al (2019) gave an extensive review on machinery diagnostics and prognostics implementing CBM. Since the success of this CBM strategy is highly dependent on the prediction accuracy, several researchers have focused on using ML algorithm to enhance the prediction of the failure state, (Prajapati and Ganesan, 2013). According to (Coraddu et al, 2016), ML approaches have the capability to identify complex pattern from the received sensory data and provide better estimation of the degradation state.…”