Condition-based Maintenance Planning Research Articles

Joint optimization of job scheduling, condition-based maintenance planning, and spare parts ordering for degrading production systems

The system degrades gradually due to intrinsic properties and the external environment while processing scheduling jobs. Maintenance plays an important role in restoring system performance during the job scheduling process. In contrast to traditional integration studies of scheduling and maintenance, this study further considers spare parts inventory in integrated decision-making. By integrating spare parts ordering information, engineers can meticulously organize maintenance and spare parts replenishment, thereby bolstering system reliability and ensuring smooth production scheduling. This paper presents a mathematical model that jointly optimizes job scheduling, condition-based maintenance planning, and spare parts ordering for deteriorating production systems. The system's degradation state and spare parts inventory state are identified and revealed at the end of the scheduling job. A condition-based maintenance and spare parts ordering policy is triggered based on the captured joint state. Subsequently, we developed a joint optimization model to determine the optimal maintenance thresholds, spare parts ordering thresholds, and job sequences, aimed at minimizing the total weighted expected cost within the scheduling horizon. Finally, an effective genetic algorithm is proposed, and a practical case study involving a rolling mill system is utilized to validate the proposed policy.

Integrated decision of production scheduling and condition-based maintenance planning for multi-unit systems with variable replacement thresholds

In practice, production scheduling and maintenance planning are two popular technologies that are interdependent, but they are most often performed independently. In this study, we have developed an integrated model for coordinating single-machine scheduling and condition-based maintenance planning. Firstly, we build upon existing scheduling research that often views the system as a whole and further consider the degradation and maintenance of multiple units within the system during the scheduling process. Secondly, in contrast to traditional degradation modeling which usually assumes a single threshold to trigger maintenance/replacement, we also consider the variability of replacement thresholds caused by the heterogeneity of scheduling tasks. Based on this foundation, we propose an integrated policy that considers both scheduling and condition-based maintenance. Furthermore, we have developed an integrated decision model for multi-unit systems. The model aims to minimize the total weighted expected completion time over the entire scheduling time horizon. Moreover, the genetic algorithm was employed to optimize the integrated model. Finally, we present an example of an SA adjustable multi-axis machine and conduct a sensitivity analysis of key parameters to validate the integration policy.

Playful Probes for Design Interaction with Machine Learning: A Tool for Aircraft Condition-Based Maintenance Planning and Visualisation

Aircraft maintenance is a complex domain where designing new systems that include Machine Learning (ML) algorithms can become a challenge. In the context of designing a tool for Condition-Based Maintenance (CBM) in aircraft maintenance planning, this case study addresses (1) the use of Playful Probing approach to obtain insights that allow understanding of how to design for interaction with ML algorithms, (2) the integration of a Reinforcement Learning (RL) agent for Human–AI collaboration in maintenance planning and (3) the visualisation of CBM indicators. Using a design science research approach, we designed a Playful Probe protocol and materials, and evaluated results by running a participatory design workshop. Our main contribution is to show how to elicit ideas for integration of maintenance planning practices with ML estimation tools and the RL agent. Through a participatory design workshop with participants’ observation, in which they played with CBM artefacts, Playful Probes favour the elicitation of user interaction requirements with the RL planning agent to aid the planner to obtain a reliable maintenance plan and turn possible to understand how to represent CBM indicators and visualise them through a trajectory prediction.

Deep reinforcement learning for condition-based maintenance planning of multi-component systems under dependent competing risks

Condition-Based Maintenance (CBM) planning for multi-component systems has been receiving increasing attention in recent years. Most existing research on CBM assumes that preventive maintenances should be conducted when the degradations of system components reach specific threshold levels upon inspection. However, the search of optimal maintenance threshold levels is often efficient for low-dimensional CBM but becomes challenging if the number of components gets large, especially when those components are subject to complex dependencies. To overcome the challenge, in this paper we propose a novel and flexible CBM model based on a customized deep reinforcement learning for multi-component systems with dependent competing risks. Both stochastic and economic dependencies among the components are considered. Specifically, different from the threshold-based decision making paradigm used in traditional CBM, the proposed model directly maps the multi-component degradation measurements at each inspection epoch to the maintenance decision space with a cost minimization objective, and the leverage of deep reinforcement learning enables high computational efficiencies and thus makes the proposed model suitable for both low and high dimensional CBM. Various numerical studies are conducted for model validations.

Integrated condition-based track maintenance planning and crew scheduling of railway networks

We develop a multi-level decision making approach for optimal condition-based maintenance planning of a railway network divided into a large number of sections with independent stochastic deterioration dynamics. At higher level, a chance-constrained Model Predictive Control (MPC) controller determines the long-term section-wise maintenance plan, minimizing condition deterioration and maintenance costs for a finite planning horizon, while ensuring that the deterioration level of each section stays below the maintenance threshold with a given probabilistic guarantee in the presence of parameter uncertainty. The resulting large MPC optimization problem containing both continuous and discrete decision variables is solved using Dantzig-Wolfe decomposition to improve the scalability of the proposed approach. At a lower level, the optimal short-term scheduling of the maintenance interventions suggested by the high-level controller and the optimal routing of the corresponding maintenance crew is formulated as a capacitated arc routing problem, which is solved exactly by transforming it into a node routing problem. The proposed approach is illustrated by a numerical case study on the optimal treatment of squats of a regional Dutch railway network. Simulation results show that the proposed approach is robust, non-conservative, and scalable.

The use of real option in condition-based maintenance scheduling for wind turbines with production and deterioration uncertainties

Preventive maintenance planning is an important problem for the handling of energy production systems with high down time costs. Throughout the last decade different maintenance strategies have been developed and optimized in order to minimize operational and maintenance costs whilst conserving and improving the system reliability and productivity. Preventive maintenance strategies are usually based on the monitoring and the prediction of the system behavior and its deterioration process. However, some industrial systems may be operating under a dynamic environment and/or variable working conditions. In this case both the deterioration and the production processes may not be deterministic and incorporate different types of uncertainties. In this paper, we consider the case of a preventive maintenance strategy for a production system subject to uncertainty. For this system, a decision-making procedure for condition-based maintenance planning is proposed. In order to consider uncertainty in production and deterioration processes, these latter are modeled by non-monotonic stochastic processes. The modeling of deterioration processes by means of jump-diffusion stochastic processes has been proposed in our previous work. In this paper, a decision-making approach for preventive maintenance strategies is proposed. Knowing the remaining useful life of a system, a simulation-based real options analysis is used in order to determine the best date to maintain. Considering a case study of a wind turbine with PHM structure, the decision-making approach is described and tested through an empirical example.

Heuristic hybrid game approach for fleet condition-based maintenance planning

The condition-based maintenance (CBM) method is commonly used to select appropriate maintenance opportunities according to equipment status over a period of time. The CBM of aircraft fleets is a fleet maintenance planning problem. In this problem, mission requirements, resource constraints, and aircraft statuses are considered to find an optimal strategy set. Given that the maintenance strategies for each aircraft are finite, fleet CBM can be treated as a combinatorial optimization problem. In this study, the process of making a decision on the CBM of military fleets is analyzed. The fleet CBM problem is treated as a two-stage dynamic decision-making problem. Aircraft are divided into dispatch and standby sets; thus, the problem scale is significantly reduced. A heuristic hybrid game (HHG) approach comprising a competition game and a cooperative game is proposed on the basis of heuristic rule. In the dispatch set, a competition game approach is proposed to search for a local optimal strategy matrix. A cooperative game method for the two sets is also proposed to ensure global optimization. Finally, a case study regarding a fleet comprising 20 aircraft is conducted, with the results proving that the approach efficiently generates outcomes that meet the mission risk-oriented schedule requirement.

Cost-benefit Analysis of Prognostics and Condition-based Maintenance Concepts for Commercial Aircraft Considering Prognostic Errors


 
 
 This paper provides a lifecycle cost-benefit analysis of the use of Prognostics and Health Management (PHM) systems in future or present commercial aircraft. The approach considers individual aircraft component’s failure behavior, prognostic performance levels including prognostic errors, and condition-based maintenance (CBM) concepts. The proposed methodology is based on a discrete-event simulation for aircraft operation and maintenance and uses an optimization algorithm for the planning and scheduling of condition-based maintenance (CBM) tasks. In the study, a 150-seat short-/medium-range aircraft equipped with PHM and subject to a CBM program is analyzed. The simulation results are evaluated from an operational and economic perspective. The analysis results can support the derivation of technical and economic requirements for prognostic systems and CBM planning concepts.
 
 

Realization of circuit breaker condition-based maintenance using optimal contact wear equation by the modified NM-PSO algorithm

The electrical circuit breaker (CB) is one of the absolutely essential devices in the electrical power system. The evaluation of CB condition and its reliability gain on importance. The contact wear of the CB monitored by Intelligent Electronic Device plays a crucial role in the condition-based maintenance (CBM). The present contact wear maintenance of the CB is based on the maintenance data provided by original manufacturers to compute the value of the accumulated contact wear. However, the evaluation of the contact wear always has a quite error. It may lead to over-maintenance or under-maintenance commonly found in maintenance planning and scheduling. Little literature has been down on the issue. By utilizing the modified hybrid Nelder–Mead simplex search and particle swarm optimization (PSO) algorithm, the paper proposes a curve-fitting technology to obtain an optimal contact wear equation for realizing the CBM of the CBs. The presented optimal contact wear equation minimizes the sum of squared errors that can be programmed in Intelligent Electronic Device. An effective CBM planning can enhance electricity substation reliability and cut maintenance costs. Compared with the conventional Nelder–Mead simplex search and PSO and PSO algorithms, two case studies are given to verify the effectiveness of the proposed method. The work may provide some valuable references for the related workers and researchers. Copyright © 2015 John Wiley & Sons, Ltd.

Condition based maintenance planning of highly productive machine tools

The competitiveness of producing enterprises in high-wage countries is extremely dependent on the productivity of the production line. Consequently, the availability of machines displays an essential index. The aim of the research project “Make-it” (Condition Based Maintenance Planning of Highly Productive Machine Tools) was to improve the availability of machine tools. Therefore, within this joint project, new methods and approaches for condition based maintenance were investigated. Thereby, an important objective was to develop an innovative maintenance algorithm which enables to calculate the most cost-effective maintenance times based on a continuous prognosis of the remaining life time, maintenance costs, and potential failure costs. This paper describes the results of the developed maintenance approach. Within this paper, the fundamental mathematical foundations of the innovative, cost-oriented maintenance algorithm and the use of the data of machine condition are presented in the first part. Moreover, the implementation of the algorithm in a computerized maintenance management system is described. The validation of the cost-oriented maintenance planning by means of event-oriented simulation will also be part of this paper.

Shipboard Controls of the Future

ABSTRACT Recent advances in computer networking and control system technologies present an opportunity to improve the capability of naval shipboard control systems. Most existing digital machinery control systems merely replace one‐for‐one their analog predecessors. These recent advances motivate rethinking the basic role and architecture of shipboard controls. Traditional machinery system control has remained largely separate from combat systems and other ship information systems. Existing machinery control systems have concentrated on four functions: machinery status, control, system stability, and fault response. To implement these functions, custom systems have been designed, built and debugged for each class of ship. This lack of commonality has been expensive in terms of development costs, maintenance costs over the lifetime of the ship, and also the unrealized benefits stemming from prohibitive costs of adapting machinery controls to take advantage of emerging technologies.This paper proposes a new paradigm for developing a shipboard control system based upon a functional decomposition of ships' missions that leads to defining technology independent interface standards. Multiple vendors may be able to independently develop control system hardware and software elements adhering to such interface standards without a priori knowledge of a particular ship application, leading to the ability to develop a total ship control system with low risk by integrating proven hardware and software elements to meet specific ship design requirements. With this new concept, other functions not normally associated with machinery controls are feasible: spontaneous reconfiguration after a damage event, integrated training, condition based maintenance planning, data archiving, operator assistance, and configuration management. This new approach may also allow for the integration of machinery controls into a total ship control system with seamless support for combat systems. This new shipboard control paradigm promises to speed control system development, improve performance, facilitate maintenance and modernization, and lead to lower life cycle costs.