Search

This study considers a repairable production system operated under an age-based preventive replacement policy that is subject to independent random production waits and failures. In addition to the age-based replacement policy, we propose a maintenance model that uses production waits to schedule preventive replacement. That is, a decision maker can preventively replace the system either during a production wait or at the age threshold, whereas if a failure occurs during production, the decision maker must decide whether to perform a minimal repair or a corrective replacement to restore the system. Under the above setting, we develop a semi-Markov decision process (SMDP) to obtain the optimal maintenance policy that minimizes the long-run average maintenance cost rate. We establish the existence of the optimal maintenance policy and provide an algorithm to numerically obtain the optimal action for each state. We further generalize the model to incorporate imperfect maintenance and the nonhomogeneous arrival of production waits. In the latter case, it is computationally intractable to optimize the SMDP using a value iteration algorithm due to the curse of dimensionality. To address this challenge, we further develop an approximate dynamic programming framework to generate high-quality solutions. An attractive feature of our model is its generality, such that the model includes many existing maintenance models as special cases. A real-world example from a steel factory is used to demonstrate the proposed model.

Maintenance of miter gates in navigation locks is crucial to facilitate water navigation of cargo ships. Scheduled and unscheduled maintenance are the two types of actions performed to keep miter gates continuously operational. In practice, visual inspections and rating systems are used to monitor the current state of miter gate components in order to prioritize maintenance. This paper shows an example of how to find the optimal time to plan for maintenance using deterioration curves obtained from real visual inspection assessments of components in miter gates. Predictive deterioration curves are derived using a Markov Chain approach. In addition, the advantages of implementing Structural Health Monitoring (SHM) are discussed.

The selection of an optimal maintenance strategy is one of the principal strategic decisions that must be taken in many contexts in order to maintain an asset with minimum deterioration and to deliver maximum output with high quality. When considering maintenance cost, reliability, and safety level of industrial assets, decision makers must select an appropriate maintenance strategy, preferably, with a known degree of uncertainty. This article utilizes a new interval type-2 fuzzy (IT2F) multicriteria decision-making method based on the analytic hierarchy process (AHP) and the technique for order of preference by similarity to ideal solution (TOPSIS), which can effectively handle the degree of uncertainty in group decision making and assist in the selection of the most feasible and optimal industrial asset maintenance strategy. The proposed method is compared with the results obtained from the conventional AHP-TOPSIS and type-1 fuzzy AHP-TOPSIS—the rank obtained from IT2F-AHP-TOPSIS is identical to those methods and can be used as an effective alternative to the type-1 fuzzy method. Compared with conventional AHP-TOPSIS and type-1 fuzzy AHP, IT2F-AHP-TOPSIS has the added advantage that it allows decision makers to define the membership function with greater flexibility and is able to handle uncertainty during decision making.

The Industrial Internet of Things (I-IoT) enables a smarter maintenance approach for various industrial applications, such as manufacturing, logistics, etc. This approach is based on continuously observing system data to predict device failures and increase device efficiency. This smart maintenance, also known as predictive maintenance (PDM), finds an optimal maintenance schedule to reduce operational and capital costs. Accurate remaining useful life (RUL) prediction is critical for an effective PDM system. Data-driven RUL estimation methods are quite popular owing to their easier implementation. We observe that the performance of data-driven methods varies drastically based on the data set and underlying system parameters, thus making it difficult to have a single algorithm and a parameter set that work best for all settings. We propose an ensemble learning framework where accurate and diverse base learners are selected out of 20 different state-of-the-art deep learning models. For accuracy, we discover the optimal weights of base learners by constructing an optimization problem. For diversity, we measure the similarity among base learner predictions and iteratively select the most diversified set of models while keeping the accuracy at a certain level. We show that our approach can have 39.2% faster retraining compared to an accuracy-based ensemble with only 3.4% loss in accuracy.

This paper presents a systematic approach to evaluate the time interval of optimal maintenance strategy for the subsea process system influenced by Microbiological Influenced Corrosion (MIC) within multiple defects. The proposed method incorporates the non-homogeneous Poisson, homogeneous gamma, and non-homogeneous Markov processes for modeling the generation of multiple defects, the average pit depth growth, and maximum pit depth, respectively. The maintenance strategy comprises industrial procedure, probability of failure detection, errors sizing in-line inspection tools, management actions costs, and failure cost. The developed framework simulates maintenance strategies considering time interval, cost, probability of detection, average pit depth, and maximum pit depth and identifies the optimal strategy. The practical application is demonstrated in a North Sea subsea pipeline system under MIC’s influence. This work assists decision-makers in selecting the optimal conditioned-based maintenance strategy for the processing system. While the application is demonstrated to subsea process systems under MIC influence, the developed approach is equally applicable to other process systems.

This paper analyzes a condition-based maintenance (CBM) model for a system with two heterogeneous components in which degradation follows a bivariate gamma process. Unlike the traditional CBM formulation that assumes an infinite planning horizon, this paper evaluates the maintenance cost in a finite planning horizon, which is the practical case for most systems. In the proposed CBM policy, both components are periodically inspected and a preventive or corrective replacement might be carried out based on the state of degradation at inspection. The CBM model is formulated as a Markov decision process (MDP) and dynamic programming is used to compute the expected maintenance cost over a finite planning horizon. The expected maintenance cost is minimized with respect to the preventive replacement thresholds for the two components. Unlike an infinite-horizon CBM problem, which leads to a stationary maintenance policy, the optimal policy in the finite-horizon case turns out to be non-stationary in the sense that the optimal actions vary at each inspection epoch. A numerical example is presented to illustrate the proposed model and investigate the influence of economic dependency and correlation between the degradation processes on the optimal maintenance policy. Numerical results show that a higher dependence between the degradation processes actually reduces the maintenance cost, while a higher economic dependence leads to higher preventive replacement thresholds.

Preventive maintenance (PM) activities in battery energy storage systems (BESSs) aim to achieve a better status in long-term operation. In this article, we develop a reinforcement learning-based PM method for the optimal PM management of BESSs equipped with prognostics and health management capabilities. A multilevel PM framework is established to generate a PM action strategy considering costs, capacity, and reliability simultaneously. Finite costs are the constraints, and reliability is the objective according to capacity degradation, respectively. The proposed PM agent with an integrated Monte Carlo tree search and a deep neural network (DNN) utilizes the state-of-health information of large-scale batteries in the BESS and selects optimal maintenance actions. The DNN is used as the state-action value function to extend the ability to address PM problems with large state-action spaces. The case of a BESS with 9 × 12 × 4 batteries in a fleet is simulated via Python. The results show that the PM agent can achieve efficient and steady decision-making proficiency in BESS PM management.

Modern engineering systems are usually equipped with a variety of sensors to measure real-time operating conditions. Based on the condition monitoring data from multiple sensor sources, this paper deals with a dynamic predictive maintenance scheduling using deep learning ensemble for system health prognostics. The deep learning ensemble model is composed of deep autoencoder and bidirectional long short-term memory in series, and aims to accurately estimate the system health state and remaining useful life. The deep autoencoder is used to extract the deep representative features hidden in condition monitoring data, whereas the inclusion of the bidirectional long short-term memory allows learning the temporal correlation information of features in both forward and backward time directions. Thus, the combination of the two models forms an effective model. With obtained prognostic information, optimal maintenance decisions are determined by two designed rules. The first rule presets a reliable remaining useful life threshold to dynamically judge whether maintenance is carried out at current inspection time, while the second one selects a degradation state to dynamically determine whether to place a spare part order. The performance of the proposed dynamic predictive maintenance strategy is measured by the maintenance cost per unit operating time (cost rate) using the aero-engine dataset from NASA. Its effectiveness is demonstrated by comparing with recent publications.

The Markov decision process (MDP) model has been widely studied and used in sequential decision making problems. In particular, it has been proved to be effective in maintenance policy optimization problems where the system state is supposed to continuously evolve under sequential maintenance policies. In traditional MDP models for maintenance, the long-run expected total discounted cost is concerned as the objective function. The maintenance manager’s target is to evaluate an optimal policy that incurs the minimum expected total discounted cost through the corresponding MDP model. However, a significant drawback of these existing MDP-based maintenance strategies is that they fail to incorporate and characterize the safety issues of the system during the maintenance process. Therefore, in some applications that are sensitive to functional risks, such strategies fail to accommodate the requirement of risk awareness. In this study, we apply the concept of risk-aversion in the MDP maintenance model to develop risk-aware maintenance policies. Specifically, we use risk functions to measure some indexes of the system that reflect the safety level and formulate a safety constraint. Then, we summarize the problem as a constrained MDP model and use the linear programming approach to evaluate the proposed risk-aware optimal maintenance policy under concern.

We consider a multi-state system whose deterioration is modeled as a semi-Markov Process with an absorbing state. The system can suffer major and minor failures. When the system reaches the absorbing state, major failure occurs and the system is replaced. Meanwhile, minor failure can occur at each state. Upon the occurrence of minor failure, the system is minimally repaired. For the system, we propose a state-age-dependent replacement policy which minimizes the expected long-run cost rate. We investigate structural properties of the optimal replacement policy and show that a control-limit policy holds under several assumptions.

Maintenance routines on ships today follow either a reactive maintenance (RM) or preventive maintenance (PvM) approach. RM can be regarded as post-failure repair, which might create large costs. PvM uses predetermined maintenance intervals, which often involves unnecessary maintenance. Recently, prognostics and health management (PHM) has emerged as a potential way to develop an ideal maintenance policy. PHM aims to provide optimal maintenance schedule through the use of sensor measurement for fault detection and fault prognostics, among which fault detection is the first and fundamental action. In this paper, a long-short term memory based variational autoencoder (LSTM-VAE) is proposed for fault detection of maritime components onboard. It is a semi-supervised approach that requires only fault-free data for training. Therefore, it is widely applicable in the maritime industry since operational data in normal conditions already exists. Real-world operation data collected from a diesel engine on the research vessel (RV) Gunnerus is used to validate the method. Results show that the LSTM-VAE can detect the fault accurately.

Wireless sensor networks (WSNs) are commonly used to monitor a remote environment over an extended period of time. One important design consideration is the WSN's reliability of area coverage, as sensors fail over time and functionality of the network degrades. When the WSN no longer sufficiently covers the region, maintenance actions may consider repairing failed nodes or deploying new sensors to re-establish network capability. Toward identifying an optimal maintenance policy, specifically the deployment of new sensors, in this article, we present an optimization model formulated using the network destruction spectrum (D-spectrum), which seeks to determine a time-based deployment policy balancing cost and reliability. While the benefits of using the D-spectrum in reliability are widely researched, the application of the D-spectrum to enable the modeling and solving of an optimization problem is new. With the complexity already present in estimating reliability, the significance of this optimization model is that it decouples the complexity of estimating the D-spectrum from the estimation of network reliability in the presence of a given deployment policy. This key feature allows us to quickly evaluate a wide range of time-based deployment policies. Additionally, we present an efficient destruction algorithm that performs a vital subroutine in estimating the D-spectrum, allowing for a large number of replications to be performed in the Monte Carlo simulation, thereby reducing the variance of the resulting reliability estimate. Finally, the optimization model is illustrated through a numerical example.

Suspension bridges are critical components of transport infrastructure around the world. Therefore, their operating conditions should be effectively monitored to ensure their safety and reliability. However, the main cables of suspension bridges inevitably deteriorate over time due to corrosion, as a result of their operational and environmental conditions. Thus, accurate annual corrosion rate predictions are crucial for maintaining reliable structures and optimal maintenance operations. However, the corrosion rate is a chaotic and complex phenomenon with highly nonlinear behavior. This paper proposes a novel predictive model for the estimation of the annual corrosion rate in the main cables of suspension bridges. This is a hybrid model based on the multilayer perceptron (MLP) technique optimized using marine predators algorithm (MPA). In addition, well-known metaheuristic approaches such as the genetic algorithm (GA) and particle swarm algorithm (PSO) are employed to optimize the MLP. In order to implement the proposed model, a comprehensive database composed of 309 sample tests on the annual corrosion rate from all around the world, including various factors related to the surrounding environmental properties, is utilized. In addition, several input combinations are proposed for investigating the trigger factors in modeling the annual corrosion rate. The performance of the proposed models is evaluated using various statistical and graphical criteria. The results of this study demonstrate that the proposed hybrid MLP-MPA model provides stable and accurate predictions, while it transcends the previously developed approaches for solving this problem. The effectiveness of the MLP-MPA model shows that it can be used for further studies on the reliability analysis of the main cables of suspension bridges.

In this paper, we introduce a new, single-component model for maintenance optimization under time-varying costs, specifically oriented at offshore wind turbine maintenance. We extend the standard age replacement policy (ARP), block replacement policy (BRP) and modified block replacement policy (MBRP) to address time-varying costs. We prove that an optimal maintenance policy under time-varying costs is a time-dependent ARP policy. Via a discretization of time, the optimal time-dependent ARP can be found using a linear programming formulation. We also present mixed integer linear programming models for parameter optimization of BRP and MBRP. We present a business case and apply our policies for maintenance planning of a wind turbine gearbox and show that we can achieve savings up-to 23%.

This paper proposes an optimal maintenance and warranty policy for the repairable second-hand product incorporating a periodic preventive maintenance strategy to slow down the deterioration of the product and derives an optimal length of non-renewing warranty period. Although a number of maintenance policies for the second-hand product have been discussed in the literature, there exist very few works dealing with the periodic preventive maintenance strategy under non-renewing warranty to obtain an optimal warranty period for the second-hand product. This work considers a non-renewing warranty policy, during which a periodic preventive maintenance is adopted to diminish the degradation process of the product and determines an optimal length of warranty period by optimizing the expected cost rate incurred to the dealer during the maintenance cycle. Since the replacement of the failed second-hand product may not be practical in general, we adopt a concept of full refund instead of replacement in this paper. By pre-setting a repair time threshold, either the refund or minimal repair is provided by the dealer depending on whether the failed second-hand product can be repaired within the repair time threshold or not. The maintenance cycle of the second-hand product starts with the purchase of the product and ends when either the refund occurs within the warranty period or the warranty expires. Given a certain cost structure charged to the dealer, we formulate the expected cost rate during the maintenance cycle of the product and determine an optimal length of warranty period minimizing the objective function. Assuming the power law process for the product’s failures and a Weibull distribution for the repair times, we present a numerical example and investigate the effects of periodic preventive maintenances and other relevant parameters on the optimal solution.

In recent years, to attain a competitive edge, merely optimizing the production efficiency is no longer the whole story that the manufacturing enterprises concentrate on. Instead, the increasing energy costs are driving manufacturing enterprises to seek an energy-oriented approach further to improve the overall performance of the production systems. Therefore, an opportunistic maintenance policy under energy and quality constraints is developed for a degrading batch production system in this paper. First and foremost, the degradation process of the production system is modeled using the Levy-type processes, meanwhile, the concept of the multielement-dependent degradation model was first put forward to describe the energy and quality degradation in production systems during the work period. Secondly, the degradation constraint threshold, energy constraint threshold, and quality constraint threshold are developed to determine the maintenance groups which include the machines that require two types of maintenance, preventive and corrective. Subsequently, in order not to interrupt the batch production activities, the changeover time between every two batches is regarded as an energy saving window to perform maintenance actions for the integrated maintenance groups. Thirdly, an energy-oriented integrated model that optimizes the total cost rate in consideration of energy and quality is developed, and the optimal maintenance combination scheme can be obtained by the Monte Carlo method. Finally, a numerical example is used to prove the effectiveness of the proposed policy.

A forklift is a lifting tool that functions to move goods from one place to another, with a short distance and a certain height, this heavy equipment is very useful because it can move very heavy goods in a vertical or horizontal direction. Problems that are often especially related to damage to unit components at PT.XXX, which are composed of the main part, namely the forklift engine. Damage to this section can result in downtime and delay in the production process which results in machine performance being less effective and efficient. Effectiveness in the production process requires the right strategy to keep the machine in operation by determining the optimal maintenance time interval using the criticality analysis method. After calculating with the criticality analysis method, it is found that the components of the hydraulic system and transmission are critical components. Furthermore, preventive replacement measures for hydraulic system components can be taken after 6800 hours of operation. The transmission component can also be done after operating for 900 hours or during an overhaul. While the inspection action for hydraulic system components is carried out after operating for 620.76 hours, the transmission component is carried out after operating for 540.39 hours. After checking and inspection, the avaibility value of the two components is above 95%, which means that the inspection can increase availability and prevent downtime in the unit and optimize the production process.

This article is a study on the reliability characteristics of a system under a failure model called the generalized mixed [Formula: see text]-shock model. We assume that the system is subject to shocks according to a stochastic process. Each shock may cause some damage to the system. The system fails either the magnitude of the damage caused by a shock exceeds a threshold [Formula: see text] or the time between two consecutive shocks is less than a pre-specified threshold [Formula: see text] and simultaneously magnitude of the damage is bigger than a pre-specified critical threshold [Formula: see text] ([Formula: see text]). The survival function and other characteristics of the system lifetime are investigated. By imposing a cost function, we arrive at an optimal replacement policy for the system based on the proposed failure model. Several examples are provided under which we illustrate the theoretical results numerically and graphically.

One of the key objectives of a pavement management system (PMS) is to find the optimal maintenance strategy, which minimises the sum of a road agency and user costs by maximising the net benefit to...

A formulation to assess a breakwater damage probability and to select the optimal maintenance strategy is presented and illustrated with a case study in Mexico. The formulation includes the calcula...

In order to improve the reliability of the production line and reduce its maintenance costs, this paper establishes preventive maintenance (PM) models of the equipment, which are classified into different levels based on mixed failure rate. The differential and targeted maintaining strategies are formulated as well. First, a method for dividing important equipment and secondary equipment of a production line based on grey interval Analytic Hierarchy Process- (AHP-) Entropy method is proposed. Next, the dynamic service age regression factor and the dynamic failure rate increasing factor are combined to establish a mixed failure rate model. Finally, for the important equipment and secondary equipment, two PM models are established with the constraint of reliability, the objective of maximum availability, and minimum maintenance cost rate to determine the optimal number of PM and cycles. Combined with an example of production line equipment, the optimal maintenance strategies for important equipment and secondary equipment are obtained. The result verified the feasibility of the model, which effectively improved the reliability of the production line equipment and reduced maintenance costs.

Steam traps in large facilities need continuous maintenance to prevent corrosion and other damage that could pose a considerable threat to a facility and its workers. However, a significant amount of human resources is required for the maintenance of steam traps. An automatic method to inform stakeholders regarding maintenance cycles will be beneficial for the maintenance process. Therefore, an optimal maintenance priority decision model is developed in this study to establish an efficient steam trap management system. First, the frequency of failures, installation locations, and specifications of steam traps were determined as parameters causing a failure. A relative score and conversion score are calculated for each parameter. The final conversion score is the sum of the conversion score multiplied by the corresponding steam trap data weight factor. Steam traps within the range requiring inspection are classified as high priority cases. Experimental results confirmed that the failure accuracy rate is approximately 95%, and the average failure error rate is within 3%. Additionally, the number of steam traps to be checked was reduced by 3616. The proposed model significantly reduces maintenance in commercial industries.

The complex structure and harsh working environment of wind turbines cause frequent failures and unavailability of these turbines in wind farms. To promote the long-term stable development of wind power and enhance its market competitiveness, the reduction of operation and maintenance costs is particularly important, which are estimated to account for approximately 1/3 of the total life cycle cost. With the continuous increase in the size and number of wind turbines, wind farm maintenance tasks and resources are increasing and becoming unpredictable. The realization of the dynamic scheduling of maintenance tasks and resources under various constraints has become vital. In this study, an optimal multi-objective model of maintenance planning and resource allocation for wind farms is established. The maintenance tasks are obtained according to the preset maintenance strategy and current operating status of the wind turbine components. The dynamic requirements of maintenance planning and resource allocation for different wind farms in adjacent areas are periodically generated, and the Non-dominated sorting genetic algorithm-ΙΙ (NSGA-ΙΙ) is adopted to conduct a combinatorial optimization process. The validity of the proposed model are verified by a corresponding case study, along with a comparative analysis with other optimization algorithms and a sensitivity study of different parameters.

The construction and maintenance of a railway track is an expensive process. Therefore, nowadays, except for advanced countries, considerable attention must be paid to apply the optimal maintenance of railway lines. In Hungary, until 2020 nearly 11% of railway tracks were renewed and rehabilitated from EU support, which means millions of Euros, i.e. billions of Hungarian Forints. It also follows from the support that planned preventive maintenance works must be performed on the renewed and rehabilitated lines. On the other hand, it takes away significant costs from the non-renewed (non-rehabilitated) lines maintenance works, but naturally, less money does not mean less failures, so cost-effective technologies are needed. A segment of maintenance is the local substructure problem(s). In this article, this segment will be mentioned from the development of the failures, through the applied technologies, to the possible new solutions like injection and the using of geosynthetic cementitious composite mats (so called GCCMs).

A study optimising maintenance cost of water borehole schemes in South Eastern states of Nigeria (Abia, Anambra, Ebonyi, Enugu and Imo States) was carried out. Data was collected from 260 boreholes spread across all local government areas in the states. Optimisation results showed that for boreholes (submersible pumps) pumping once per day, the optimal preventive maintenance frequency and resulting savings in cost are 2 and ₦521,076 for Abia; 2 and ₦783,963 for Anambra; 2 and ₦458,242 for Ebonyi; 2 and ₦740,964 for Enugu; 2 and ₦605,187 Imo. For boreholes pumping twice per day, the optimal preventive maintenance frequency and resulting savings in cost are 5 and ₦1,896,301 for Abia; 4 and ₦3,692,655 for Anambra; 5 and ₦786,913 for Ebonyi; 4 and ₦4,187,161 for Enugu; 4 and ₦2,477,609 for Imo; and for boreholes pumping thrice per day; 8 and ₦2,798,330 for Abia; 7 and ₦8,372,862 for Anambra; 7 and ₦6,485,293 for Ebonyi; 10 and ₦4,014,240 for Enugu; 10 and ₦6,021,503 for Imo; with no downtime as opposed to the wasteful current practice of no preventive maintenance with downtime of up to 12 months or more. As a recommendation for a borehole scheme, there should be a check on the type of submersible pump and generator capacity as the choice made directly affects the total operational cost.